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-jammy
+    nodeset: openstack-two-node-noble
     roles:
       - zuul: openstack/tempest
     group-vars:
@@ -170,6 +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
@@ -186,7 +146,7 @@
       - openstack/python-watcherclient
       - openstack/watcher-tempest-plugin
     vars: *base_vars
-    irrelevant-files:
+    irrelevant-files: &irrelevent_files
       - ^(test-|)requirements.txt$
       - ^.*\.rst$
       - ^api-ref/.*$
@@ -206,3 +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_auth_token_middleware $WATCHER_CONF watcher $WATCHER_AUTH_CACHE_DIR "watcher_clients_auth"
+    configure_keystone_authtoken_middleware $WATCHER_CONF watcher
+    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
-# 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
+sphinx>=2.1.1 # BSD
 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

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
-unavailable as well as `instance_l3_cpu_cache`::
+require Ironic such as ``host_airflow and`` ``host_power`` will still be
+unavailable as well as ``instance_l3_cpu_cache``
 
-        [[local|localrc]]
-        enable_plugin watcher https://opendev.org/openstack/watcher
+.. code-block:: ini
 
-        enable_plugin watcher-dashboard https://opendev.org/openstack/watcher-dashboard
+   [[local|localrc]]
 
-        enable_plugin ceilometer https://opendev.org/openstack/ceilometer.git
-        CEILOMETER_BACKEND=gnocchi
+   enable_plugin watcher https://opendev.org/openstack/watcher
+   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
-        enable_plugin panko https://opendev.org/openstack/panko
-
-        [[post-config|$NOVA_CONF]]
-        [DEFAULT]
-        compute_monitors=cpu.virt_driver
+   CEILOMETER_BACKEND=gnocchi
+   [[post-config|$NOVA_CONF]]
+   [DEFAULT]
+   compute_monitors=cpu.virt_driver
 
 Detailed DevStack Instructions
 ==============================
 
-#. 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
-   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
-   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
-   machine via VirtualBox if you prefer. DevStack currently recommends that
-   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.
+#.  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
+    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
+    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
+    machine via VirtualBox if you prefer. DevStack currently recommends that
+    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.
 
-#. 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
-       sudo apt-get install git
-       git clone https://opendev.org/openstack/devstack.git
-       sudo ./devstack/tools/create-stack-user.sh
+   .. code-block:: bash
+
+        sudo apt-get update
+        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
-       cd ~
-       git clone https://opendev.org/openstack/devstack.git
+#. Switch to the stack user and clone the DevStack repo again
+
+   .. 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
-   one), then change the enable plugin line::
+   .. NOTE::
+        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
-   sure that is also available or specify WATCHERCLIENT_REPO in the local.conf
+   python-watcherclient repo from ``<your_local_git_repo>/../``, so either make
+   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
-   local.conf file. By default it will use the master branch.
+   .. NOTE::
+        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
-   WATCHER_USE_MOD_WSGI=FALSE if you do not wish to run under apache/httpd.
-   For development environment it is suggested to set WATHCER_USE_MOD_WSGI
-   to FALSE. For Production environment it is suggested to keep it at the
-   default TRUE value.
+   .. Note::
+        watcher-api will default run under apache/httpd, set the variable
+        WATCHER_USE_MOD_WSGI=FALSE if you do not wish to run under apache/httpd.
+        For development environment it is suggested to set WATHCER_USE_MOD_WSGI
+        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
-   `Multi-Node DevStack Environment`_ section for more details.
+   .. seealso::
+        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
-can serve as the NFS server if needed::
+    Nova supports live migration with local block storage so by default NFS
+    is not required and is considered an advance configuration.
+    The minimum requirements for live migration are:
 
-    sudo apt-get install nfs-kernel-server
-    sudo mkdir -p /nfs/instances
-    sudo chown stack:stack /nfs/instances
+        - all hostnames are resolvable on each host
+        - all hosts have a passwordless ssh key that is trusted by the other hosts
+        - all hosts have a known_hosts file that lists each hosts
 
-Add an entry to `/etc/exports` with the appropriate gateway and netmask
-information::
-
-    /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
+    If these requirements are met live migration will be possible.
+    Shared storage such as ceph, booting form cinder volume or nfs are recommend
+    when testing evacuate if you want to preserve vm data.
 
 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]
-enabled = False
+    sudo apt-get install nfs-kernel-server
+    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/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
-`/api/datasource/proxy` is the default path without any subdirectories.
+would be: ``https://mygrafana.org/api/datasource/proxy/`` were
+``/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
-the `[watcher_datasources]` group.
+datasources with the launch of each audit. To do this specify
+``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
-format will currently have give attributes exposed to it labeled `{0}` to
-`{4}`. Every occurrence of these characters within the string will be replaced
+Queries will be formatted using the .format string method within Python.
+This format will currently have give attributes exposed to it labeled
+``{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
-  supported.
-- {1} is the attribute as specified in the attribute parameter.
-- {2} 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.
+{0}
+    is the aggregate typically ``mean``, ``min``, ``max`` but ``count``
+    is also supported.
+{1}
+    is the attribute as specified in the attribute parameter.
+{2}
+    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/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
-format), your can append `-p` to input required parameters:
+defines some parameters (command ``watcher strategy show`` to check 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

@@ -3,4 +3,4 @@
 ===========================
 
 .. release-notes::
-   :branch: stable/2023.1
+   :branch: unmaintained/2023.1

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').
-#'papersize': 'letterpaper',
+    # The paper size ('letterpaper' or 'a4paper').
+    # 'papersize': 'letterpaper',
 
-# The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
+    # The font size ('10pt', '11pt' or '12pt').
+    # 'pointsize': '10pt',
 
-# Additional stuff for the LaTeX preamble.
-#'preamble': '',
+    # Additional stuff for the LaTeX 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',
-   'Watcher developers', 'manual'),
+    ('index', 'watcher.tex', 'Watcher Documentation',
+     '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',
-   'Watcher developers', 'watcher', 'One line description of project.',
-   'Miscellaneous'),
+    ('index', 'watcher', 'Watcher Documentation',
+     'Watcher developers', 'watcher', 'One line description of project.',
+     '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 +21,8 @@ Contents:
    :maxdepth: 1
 
    unreleased
+   2024.2
+   2024.1
    2023.2
    2023.1
    zed

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

@@ -3,15 +3,16 @@
 # 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: 2023-08-14 03:05+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: 2023-06-21 07:54+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"
@@ -63,12 +64,21 @@ 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"
 
@@ -210,6 +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 "
@@ -329,6 +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."
@@ -405,6 +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 "
@@ -511,6 +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:"
 

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
-# of appearance. Changing the order has an impact on the overall integration
-# process, which may cause wedges in the gate later.
-
+# Requirements lower bounds listed here are our best effort to keep them up to
+# date but we do not test them so no guarantee of having them all correct. If
+# 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
@@ -18,12 +18,12 @@ 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>=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 = >=3.8
+python_requires = >=3.9
 classifier =
     Environment :: OpenStack
     Intended Audience :: Information Technology
@@ -17,10 +17,10 @@ classifier =
     Programming Language :: Python :: Implementation :: CPython
     Programming Language :: Python :: 3 :: Only
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
     Programming Language :: Python :: 3.11
+    Programming Language :: Python :: 3.12
 
 [files]
 packages =
@@ -109,3 +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
-bandit>=1.6.0 # Apache-2.0
-WebTest>=2.0.27 # MIT
+WebTest>=2.0.27 # MIT

tox.ini

@@ -10,7 +10,11 @@ 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
@@ -26,12 +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
-    flake8
-    #bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
+    pre-commit run --all-files --show-diff-on-failure
+
 
 [testenv:venv]
 setenv = PYTHONHASHSEED=0
@@ -82,7 +96,6 @@ commands =
 commands = python setup.py bdist_wheel
 
 [testenv:pdf-docs]
-envdir = {toxworkdir}/docs
 deps = {[testenv:docs]deps}
 allowlist_externals =
   rm
@@ -97,8 +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
-commands = bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
+skip_install = true
+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(),
-                     start_time=datetime.datetime.utcnow(),
-                     end_time=datetime.datetime.utcnow())
+                     next_run_time=timeutils.utcnow(),
+                     start_time=timeutils.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/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
-
-eventlet.monkey_patch()
-
-# Monkey patch the original current_thread to use the up-to-date _active
-# global variable. See https://bugs.launchpad.net/bugs/1863021 and
-# https://github.com/eventlet/eventlet/issues/592
-import __original_module_threading as orig_threading  # noqa
-import threading  # noqa
-orig_threading.current_thread.__globals__['_active'] = threading._active
+# 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.
+# 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.
+# apscheduler does not technically support eventlet but it has mostly worked
+# until now, apscheduler is used to provide a job schedulers which mixes
+# monkey patched and non monkey patched code in the same process.
+# That is problematic and can lead to errors on python 3.12+.
+# The maas support added asyncio to the codebase which is unsafe to mix
+# 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

@@ -27,12 +27,6 @@ from novaclient import client as nvclient
 from watcher.common import exception
 from watcher.common import utils
 
-try:
-    from ceilometerclient import client as ceclient
-    HAS_CEILCLIENT = True
-except ImportError:
-    HAS_CEILCLIENT = False
-
 try:
     from maas import client as maas_client
 except ImportError:
@@ -77,7 +71,6 @@ class OpenStackClients(object):
         self._glance = None
         self._gnocchi = None
         self._cinder = None
-        self._ceilometer = None
         self._monasca = None
         self._neutron = None
         self._ironic = None
@@ -188,24 +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:

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") %
-                              name_or_id))
+                    message=(_("Project name seems ambiguous: %s") %
+                             name_or_id))
             return projects[0]
 
     def get_domain(self, name_or_id):

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(
-                'Waiting the resize of {0}  to {1}'.format(
-                    instance, flavor_id))
+            LOG.debug('Waiting the resize of %s to %s', 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(
-                        'Waiting the migration of {0}'.format(instance.id))
+                    LOG.debug('Waiting the migration of %s', 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(
-                    'Waiting the migration of {0}  to {1}'.format(
-                        instance,
-                        getattr(instance,
-                                'OS-EXT-SRV-ATTR:host')))
+                LOG.debug('Waiting the migration of %s to %s',
+                          instance,
+                          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/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,
-                                 background.BackgroundScheduler):
-    def __init__(self, gconfig={}, **options):
+class BackgroundSchedulerService(
+        service.ServiceBase, background.BackgroundScheduler):
+    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__(
-            gconfig, **options)
+        super().__init__(gconfig or {}, **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/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
@@ -42,6 +41,7 @@ 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
@@ -64,9 +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)

watcher/conf/applier.py

@@ -47,7 +47,7 @@ APPLIER_OPTS = [
     cfg.BoolOpt('rollback_when_actionplan_failed',
                 default=False,
                 help='If set True, the failed actionplan will rollback '
-                     'when executing. Defaule value is False.'),
+                     'when executing. Default value is False.'),
 ]
 
 

watcher/conf/ceilometer_client.py

@@ -1,63 +0,0 @@
-# -*- encoding: utf-8 -*-
-# Copyright (c) 2016 Intel Corp
-#
-# Authors: Prudhvi Rao Shedimbi <prudhvi.rao.shedimbi@intel.com>
-#
-# 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
-
-ceilometer_client = cfg.OptGroup(name='ceilometer_client',
-                                 title='Configuration Options for Ceilometer')
-
-CEILOMETER_CLIENT_OPTS = [
-    cfg.StrOpt('api_version',
-               default='2',
-               deprecated_for_removal=True,
-               deprecated_since="1.13.0",
-               deprecated_reason="""
-               Ceilometer API is deprecated since Ocata release.
-               Any related configuration options are deprecated too.
-               """,
-               help='Version of Ceilometer API to use in '
-                    'ceilometerclient.'),
-    cfg.StrOpt('endpoint_type',
-               default='internalURL',
-               deprecated_for_removal=True,
-               deprecated_since="1.13.0",
-               deprecated_reason="""
-               Ceilometer API is deprecated since Ocata release.
-               Any related configuration options are deprecated too.
-               """,
-               help='Type of endpoint to use in ceilometerclient. '
-                    'Supported values: internalURL, publicURL, adminURL. '
-                    'The default is internalURL.'),
-    cfg.StrOpt('region_name',
-               deprecated_for_removal=True,
-               deprecated_since="1.13.0",
-               deprecated_reason="""
-               Ceilometer API is deprecated since Ocata release.
-               Any related configuration options are deprecated too.
-               """,
-               help='Region in Identity service catalog to use for '
-                    'communication with the OpenStack service.')]
-
-
-def register_opts(conf):
-    conf.register_group(ceilometer_client)
-    conf.register_opts(CEILOMETER_CLIENT_OPTS, group=ceilometer_client)
-
-
-def list_opts():
-    return [(ceilometer_client, CEILOMETER_CLIENT_OPTS)]

watcher/conf/prometheus_client.py

@@ -0,0 +1,62 @@
+# Copyright 2024 Red Hat, Inc.
+#
+# 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
+
+prometheus_client = cfg.OptGroup(name='prometheus_client',
+                                 title='Configuration Options for Prometheus',
+                                 help="See https://docs.openstack.org/watcher/"
+                                      "latest/datasources/prometheus.html for "
+                                      "details on how these options are used.")
+
+PROMETHEUS_CLIENT_OPTS = [
+    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."),
+]
+
+
+def register_opts(conf):
+    conf.register_group(prometheus_client)
+    conf.register_opts(PROMETHEUS_CLIENT_OPTS, group=prometheus_client)
+
+
+def list_opts():
+    return [(prometheus_client, PROMETHEUS_CLIENT_OPTS)]

watcher/db/sqlalchemy/alembic/env.py

@@ -13,8 +13,8 @@
 from logging import config as log_config
 
 from alembic import context
+from oslo_db.sqlalchemy import enginefacade
 
-from watcher.db.sqlalchemy import api as sqla_api
 from watcher.db.sqlalchemy import models
 
 # this is the Alembic Config object, which provides
@@ -43,7 +43,7 @@ def run_migrations_online():
     and associate a connection with the context.
 
     """
-    engine = sqla_api.get_engine()
+    engine = enginefacade.writer.get_engine()
     with engine.connect() as connection:
         context.configure(connection=connection,
                           target_metadata=target_metadata)

watcher/db/sqlalchemy/alembic/versions/0f6042416884_add_apscheduler_jobs.py

@@ -28,7 +28,7 @@ def upgrade():
 
     op.create_table(
         'apscheduler_jobs',
-        sa.Column('id', sa.Unicode(191, _warn_on_bytestring=False),
+        sa.Column('id', sa.Unicode(191),
                   nullable=False),
         sa.Column('next_run_time', sa.Float(25), index=True),
         sa.Column('job_state', sa.LargeBinary, nullable=False),

watcher/db/sqlalchemy/api.py

@@ -19,10 +19,12 @@
 import collections
 import datetime
 import operator
+import threading
 
 from oslo_config import cfg
+from oslo_db import api as oslo_db_api
 from oslo_db import exception as db_exc
-from oslo_db.sqlalchemy import session as db_session
+from oslo_db.sqlalchemy import enginefacade
 from oslo_db.sqlalchemy import utils as db_utils
 from oslo_utils import timeutils
 from sqlalchemy.inspection import inspect
@@ -38,24 +40,7 @@ from watcher import objects
 
 CONF = cfg.CONF
 
-_FACADE = None
-
-
-def _create_facade_lazily():
-    global _FACADE
-    if _FACADE is None:
-        _FACADE = db_session.EngineFacade.from_config(CONF)
-    return _FACADE
-
-
-def get_engine():
-    facade = _create_facade_lazily()
-    return facade.get_engine()
-
-
-def get_session(**kwargs):
-    facade = _create_facade_lazily()
-    return facade.get_session(**kwargs)
+_CONTEXT = threading.local()
 
 
 def get_backend():
@@ -63,14 +48,15 @@ def get_backend():
     return Connection()
 
 
-def model_query(model, *args, **kwargs):
-    """Query helper for simpler session usage.
+def _session_for_read():
+    return enginefacade.reader.using(_CONTEXT)
 
-    :param session: if present, the session to use
-    """
-    session = kwargs.get('session') or get_session()
-    query = session.query(model, *args)
-    return query
+
+# NOTE(tylerchristie) Please add @oslo_db_api.retry_on_deadlock decorator to
+# any new methods using _session_for_write (as deadlocks happen on write), so
+# that oslo_db is able to retry in case of deadlocks.
+def _session_for_write():
+    return enginefacade.writer.using(_CONTEXT)
 
 
 def add_identity_filter(query, value):
@@ -93,8 +79,6 @@ def add_identity_filter(query, value):
 
 def _paginate_query(model, limit=None, marker=None, sort_key=None,
                     sort_dir=None, query=None):
-    if not query:
-        query = model_query(model)
     sort_keys = ['id']
     if sort_key and sort_key not in sort_keys:
         sort_keys.insert(0, sort_key)
@@ -244,24 +228,24 @@ class Connection(api.BaseConnection):
         for relationship in relationships:
             if not relationship.uselist:
                 # We have a One-to-X relationship
-                query = query.options(joinedload(relationship.key))
+                query = query.options(joinedload(
+                    getattr(model, relationship.key)))
         return query
 
+    @oslo_db_api.retry_on_deadlock
     def _create(self, model, values):
-        session = get_session()
-        with session.begin():
+        with _session_for_write() as session:
             obj = model()
             cleaned_values = {k: v for k, v in values.items()
                               if k not in self._get_relationships(model)}
             obj.update(cleaned_values)
-            obj.save(session=session)
-            session.commit()
-        return obj
+            session.add(obj)
+            session.flush()
+            return obj
 
     def _get(self, context, model, fieldname, value, eager):
-        session = get_session()
-        with session.begin():
-            query = model_query(model, session=session)
+        with _session_for_read() as session:
+            query = session.query(model)
             if eager:
                 query = self._set_eager_options(model, query)
 
@@ -274,13 +258,13 @@ class Connection(api.BaseConnection):
             except exc.NoResultFound:
                 raise exception.ResourceNotFound(name=model.__name__, id=value)
 
-        return obj
+            return obj
 
     @staticmethod
+    @oslo_db_api.retry_on_deadlock
     def _update(model, id_, values):
-        session = get_session()
-        with session.begin():
-            query = model_query(model, session=session)
+        with _session_for_write() as session:
+            query = session.query(model)
             query = add_identity_filter(query, id_)
             try:
                 ref = query.with_for_update().one()
@@ -288,13 +272,14 @@ class Connection(api.BaseConnection):
                 raise exception.ResourceNotFound(name=model.__name__, id=id_)
 
             ref.update(values)
-        return ref
+
+            return ref
 
     @staticmethod
+    @oslo_db_api.retry_on_deadlock
     def _soft_delete(model, id_):
-        session = get_session()
-        with session.begin():
-            query = model_query(model, session=session)
+        with _session_for_write() as session:
+            query = session.query(model)
             query = add_identity_filter(query, id_)
             try:
                 row = query.one()
@@ -306,10 +291,10 @@ class Connection(api.BaseConnection):
             return row
 
     @staticmethod
+    @oslo_db_api.retry_on_deadlock
     def _destroy(model, id_):
-        session = get_session()
-        with session.begin():
-            query = model_query(model, session=session)
+        with _session_for_write() as session:
+            query = session.query(model)
             query = add_identity_filter(query, id_)
 
             try:
@@ -322,14 +307,15 @@ class Connection(api.BaseConnection):
     def _get_model_list(self, model, add_filters_func, context, filters=None,
                         limit=None, marker=None, sort_key=None, sort_dir=None,
                         eager=False):
-        query = model_query(model)
-        if eager:
-            query = self._set_eager_options(model, query)
-        query = add_filters_func(query, filters)
-        if not context.show_deleted:
-            query = query.filter(model.deleted_at.is_(None))
-        return _paginate_query(model, limit, marker,
-                               sort_key, sort_dir, query)
+        with _session_for_read() as session:
+            query = session.query(model)
+            if eager:
+                query = self._set_eager_options(model, query)
+            query = add_filters_func(query, filters)
+            if not context.show_deleted:
+                query = query.filter(model.deleted_at.is_(None))
+            return _paginate_query(model, limit, marker,
+                                   sort_key, sort_dir, query)
 
     # NOTE(erakli): _add_..._filters methods should be refactored to have same
     # content. join_fieldmap should be filled with JoinMap instead of dict
@@ -424,11 +410,12 @@ class Connection(api.BaseConnection):
             plain_fields=plain_fields, join_fieldmap=join_fieldmap)
 
         if 'audit_uuid' in filters:
-            stmt = model_query(models.ActionPlan).join(
-                models.Audit,
-                models.Audit.id == models.ActionPlan.audit_id)\
-                .filter_by(uuid=filters['audit_uuid']).subquery()
-            query = query.filter_by(action_plan_id=stmt.c.id)
+            with _session_for_read() as session:
+                stmt = session.query(models.ActionPlan).join(
+                    models.Audit,
+                    models.Audit.id == models.ActionPlan.audit_id)\
+                    .filter_by(uuid=filters['audit_uuid']).subquery()
+                query = query.filter_by(action_plan_id=stmt.c.id)
 
         return query
 
@@ -606,20 +593,21 @@ class Connection(api.BaseConnection):
         if not values.get('uuid'):
             values['uuid'] = utils.generate_uuid()
 
-        query = model_query(models.AuditTemplate)
-        query = query.filter_by(name=values.get('name'),
-                                deleted_at=None)
+        with _session_for_write() as session:
+            query = session.query(models.AuditTemplate)
+            query = query.filter_by(name=values.get('name'),
+                                    deleted_at=None)
 
-        if len(query.all()) > 0:
-            raise exception.AuditTemplateAlreadyExists(
-                audit_template=values['name'])
+            if len(query.all()) > 0:
+                raise exception.AuditTemplateAlreadyExists(
+                    audit_template=values['name'])
 
-        try:
-            audit_template = self._create(models.AuditTemplate, values)
-        except db_exc.DBDuplicateEntry:
-            raise exception.AuditTemplateAlreadyExists(
-                audit_template=values['name'])
-        return audit_template
+            try:
+                audit_template = self._create(models.AuditTemplate, values)
+            except db_exc.DBDuplicateEntry:
+                raise exception.AuditTemplateAlreadyExists(
+                    audit_template=values['name'])
+            return audit_template
 
     def _get_audit_template(self, context, fieldname, value, eager):
         try:
@@ -681,25 +669,26 @@ class Connection(api.BaseConnection):
         if not values.get('uuid'):
             values['uuid'] = utils.generate_uuid()
 
-        query = model_query(models.Audit)
-        query = query.filter_by(name=values.get('name'),
-                                deleted_at=None)
+        with _session_for_write() as session:
+            query = session.query(models.Audit)
+            query = query.filter_by(name=values.get('name'),
+                                    deleted_at=None)
 
-        if len(query.all()) > 0:
-            raise exception.AuditAlreadyExists(
-                audit=values['name'])
+            if len(query.all()) > 0:
+                raise exception.AuditAlreadyExists(
+                    audit=values['name'])
 
-        if values.get('state') is None:
-            values['state'] = objects.audit.State.PENDING
+            if values.get('state') is None:
+                values['state'] = objects.audit.State.PENDING
 
-        if not values.get('auto_trigger'):
-            values['auto_trigger'] = False
+            if not values.get('auto_trigger'):
+                values['auto_trigger'] = False
 
-        try:
-            audit = self._create(models.Audit, values)
-        except db_exc.DBDuplicateEntry:
-            raise exception.AuditAlreadyExists(audit=values['uuid'])
-        return audit
+            try:
+                audit = self._create(models.Audit, values)
+            except db_exc.DBDuplicateEntry:
+                raise exception.AuditAlreadyExists(audit=values['uuid'])
+            return audit
 
     def _get_audit(self, context, fieldname, value, eager):
         try:
@@ -723,14 +712,13 @@ class Connection(api.BaseConnection):
     def destroy_audit(self, audit_id):
         def is_audit_referenced(session, audit_id):
             """Checks whether the audit is referenced by action_plan(s)."""
-            query = model_query(models.ActionPlan, session=session)
+            query = session.query(models.ActionPlan)
             query = self._add_action_plans_filters(
                 query, {'audit_id': audit_id})
             return query.count() != 0
 
-        session = get_session()
-        with session.begin():
-            query = model_query(models.Audit, session=session)
+        with _session_for_write() as session:
+            query = session.query(models.Audit)
             query = add_identity_filter(query, audit_id)
 
             try:
@@ -797,9 +785,8 @@ class Connection(api.BaseConnection):
             context, fieldname="uuid", value=action_uuid, eager=eager)
 
     def destroy_action(self, action_id):
-        session = get_session()
-        with session.begin():
-            query = model_query(models.Action, session=session)
+        with _session_for_write() as session:
+            query = session.query(models.Action)
             query = add_identity_filter(query, action_id)
             count = query.delete()
             if count != 1:
@@ -815,9 +802,8 @@ class Connection(api.BaseConnection):
 
     @staticmethod
     def _do_update_action(action_id, values):
-        session = get_session()
-        with session.begin():
-            query = model_query(models.Action, session=session)
+        with _session_for_write() as session:
+            query = session.query(models.Action)
             query = add_identity_filter(query, action_id)
             try:
                 ref = query.with_for_update().one()
@@ -825,7 +811,7 @@ class Connection(api.BaseConnection):
                 raise exception.ActionNotFound(action=action_id)
 
             ref.update(values)
-        return ref
+            return ref
 
     def soft_delete_action(self, action_id):
         try:
@@ -869,14 +855,13 @@ class Connection(api.BaseConnection):
     def destroy_action_plan(self, action_plan_id):
         def is_action_plan_referenced(session, action_plan_id):
             """Checks whether the action_plan is referenced by action(s)."""
-            query = model_query(models.Action, session=session)
+            query = session.query(models.Action)
             query = self._add_actions_filters(
                 query, {'action_plan_id': action_plan_id})
             return query.count() != 0
 
-        session = get_session()
-        with session.begin():
-            query = model_query(models.ActionPlan, session=session)
+        with _session_for_write() as session:
+            query = session.query(models.ActionPlan)
             query = add_identity_filter(query, action_plan_id)
 
             try:
@@ -900,9 +885,8 @@ class Connection(api.BaseConnection):
 
     @staticmethod
     def _do_update_action_plan(action_plan_id, values):
-        session = get_session()
-        with session.begin():
-            query = model_query(models.ActionPlan, session=session)
+        with _session_for_write() as session:
+            query = session.query(models.ActionPlan)
             query = add_identity_filter(query, action_plan_id)
             try:
                 ref = query.with_for_update().one()
@@ -910,7 +894,7 @@ class Connection(api.BaseConnection):
                 raise exception.ActionPlanNotFound(action_plan=action_plan_id)
 
             ref.update(values)
-        return ref
+            return ref
 
     def soft_delete_action_plan(self, action_plan_id):
         try:

watcher/db/sqlalchemy/job_store.py

@@ -16,23 +16,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from oslo_serialization import jsonutils
+import pickle  # nosec: B403
 
 from apscheduler.jobstores.base import ConflictingIdError
 from apscheduler.jobstores import sqlalchemy
 from apscheduler.util import datetime_to_utc_timestamp
 from apscheduler.util import maybe_ref
+from apscheduler.util import utc_timestamp_to_datetime
+from oslo_serialization import jsonutils
 
 from watcher.common import context
 from watcher.common import service
 from watcher import objects
 
-try:
-    import cPickle as pickle
-except ImportError:  # pragma: nocover
-    import pickle
-
-from sqlalchemy import Table, MetaData, select, and_
+from sqlalchemy import Table, MetaData, select, and_, null
 from sqlalchemy.exc import IntegrityError
 
 
@@ -58,8 +55,7 @@ class WatcherJobStore(sqlalchemy.SQLAlchemyJobStore):
         super(WatcherJobStore, self).__init__(url, engine, tablename,
                                               metadata, pickle_protocol)
         metadata = maybe_ref(metadata) or MetaData()
-        self.jobs_t = Table(tablename, metadata, autoload=True,
-                            autoload_with=engine)
+        self.jobs_t = Table(tablename, metadata, autoload_with=engine)
         service_ident = service.ServiceHeartbeat.get_service_name()
         self.tag = tag or {'host': service_ident[0], 'name': service_ident[1]}
         self.service_id = objects.Service.list(context=context.make_context(),
@@ -79,7 +75,8 @@ class WatcherJobStore(sqlalchemy.SQLAlchemyJobStore):
             'tag': jsonutils.dumps(self.tag)
         })
         try:
-            self.engine.execute(insert)
+            with self.engine.begin() as conn:
+                conn.execute(insert)
         except IntegrityError:
             raise ConflictingIdError(job.id)
 
@@ -88,20 +85,36 @@ class WatcherJobStore(sqlalchemy.SQLAlchemyJobStore):
         self._fix_paused_jobs_sorting(jobs)
         return jobs
 
+    def get_next_run_time(self):
+        selectable = select(self.jobs_t.c.next_run_time).\
+            where(self.jobs_t.c.next_run_time != null()).\
+            order_by(self.jobs_t.c.next_run_time).limit(1)
+        with self.engine.begin() as connection:
+            # NOTE(danms): The apscheduler implementation of this gets a
+            # decimal.Decimal back from scalar() which causes
+            # utc_timestamp_to_datetime() to choke since it is expecting a
+            # python float. Assume this is SQLAlchemy 2.0 stuff, so just
+            # coerce to a float here.
+            next_run_time = connection.execute(selectable).scalar()
+            return utc_timestamp_to_datetime(float(next_run_time)
+                                             if next_run_time is not None
+                                             else None)
+
     def _get_jobs(self, *conditions):
         jobs = []
         conditions += (self.jobs_t.c.service_id == self.service_id,)
         selectable = select(
-            [self.jobs_t.c.id, self.jobs_t.c.job_state, self.jobs_t.c.tag]
+            self.jobs_t.c.id, self.jobs_t.c.job_state, self.jobs_t.c.tag
         ).order_by(self.jobs_t.c.next_run_time).where(and_(*conditions))
         failed_job_ids = set()
-        for row in self.engine.execute(selectable):
-            try:
-                jobs.append(self._reconstitute_job(row.job_state))
-            except Exception:
-                self._logger.exception(
-                    'Unable to restore job "%s" -- removing it', row.id)
-                failed_job_ids.add(row.id)
+        with self.engine.begin() as conn:
+            for row in conn.execute(selectable):
+                try:
+                    jobs.append(self._reconstitute_job(row.job_state))
+                except Exception:
+                    self._logger.exception(
+                        'Unable to restore job "%s" -- removing it', row.id)
+                    failed_job_ids.add(row.id)
 
         # Remove all the jobs we failed to restore
         if failed_job_ids:

watcher/db/sqlalchemy/migration.py

@@ -20,9 +20,9 @@ import alembic
 from alembic import config as alembic_config
 import alembic.migration as alembic_migration
 from oslo_db import exception as db_exc
+from oslo_db.sqlalchemy import enginefacade
 
 from watcher._i18n import _
-from watcher.db.sqlalchemy import api as sqla_api
 from watcher.db.sqlalchemy import models
 
 
@@ -39,7 +39,7 @@ def version(engine=None):
     :rtype: string
     """
     if engine is None:
-        engine = sqla_api.get_engine()
+        engine = enginefacade.reader.get_engine()
     with engine.connect() as conn:
         context = alembic_migration.MigrationContext.configure(conn)
         return context.get_current_revision()
@@ -63,7 +63,7 @@ def create_schema(config=None, engine=None):
     Can be used for initial installation instead of upgrade('head').
     """
     if engine is None:
-        engine = sqla_api.get_engine()
+        engine = enginefacade.writer.get_engine()
 
     # NOTE(viktors): If we will use metadata.create_all() for non empty db
     #                schema, it will only add the new tables, but leave

watcher/db/sqlalchemy/models.py

@@ -93,14 +93,6 @@ class WatcherBase(models.SoftDeleteMixin,
             d[c.name] = self[c.name]
         return d
 
-    def save(self, session=None):
-        import watcher.db.sqlalchemy.api as db_api
-
-        if session is None:
-            session = db_api.get_session()
-
-        super(WatcherBase, self).save(session)
-
 
 Base = declarative_base(cls=WatcherBase)
 

watcher/decision_engine/audit/continuous.py

@@ -19,9 +19,10 @@
 
 
 import datetime
-from dateutil import tz
 
 from croniter import croniter
+from dateutil import tz
+from oslo_utils import timeutils
 
 from watcher.common import context
 from watcher.common import scheduling
@@ -52,7 +53,7 @@ class ContinuousAuditHandler(base.AuditHandler):
             self._audit_scheduler = scheduling.BackgroundSchedulerService(
                 jobstores={
                     'default': job_store.WatcherJobStore(
-                        engine=sq_api.get_engine()),
+                        engine=sq_api.enginefacade.writer.get_engine()),
                 }
             )
         return self._audit_scheduler
@@ -97,7 +98,7 @@ class ContinuousAuditHandler(base.AuditHandler):
     @staticmethod
     def _next_cron_time(audit):
         if utils.is_cron_like(audit.interval):
-            return croniter(audit.interval, datetime.datetime.utcnow()
+            return croniter(audit.interval, timeutils.utcnow()
                             ).get_next(datetime.datetime)
 
     @classmethod
@@ -111,7 +112,7 @@ class ContinuousAuditHandler(base.AuditHandler):
             finally:
                 if utils.is_int_like(audit.interval):
                     audit.next_run_time = (
-                        datetime.datetime.utcnow() +
+                        timeutils.utcnow() +
                         datetime.timedelta(seconds=int(audit.interval)))
                 else:
                     audit.next_run_time = self._next_cron_time(audit)
@@ -129,7 +130,7 @@ class ContinuousAuditHandler(base.AuditHandler):
                                **trigger_args)
 
     def check_audit_expired(self, audit):
-        current = datetime.datetime.utcnow()
+        current = timeutils.utcnow()
         # Note: if audit still didn't get into the timeframe,
         #       skip it
         if audit.start_time and audit.start_time > current:
@@ -196,7 +197,7 @@ class ContinuousAuditHandler(base.AuditHandler):
                     # to restore it after shutdown
                     if audit.next_run_time is not None:
                         old_run_time = audit.next_run_time
-                        current = datetime.datetime.utcnow()
+                        current = timeutils.utcnow()
                         if old_run_time < current:
                             delta = datetime.timedelta(
                                 seconds=(int(audit.interval) - (
@@ -206,7 +207,7 @@ class ContinuousAuditHandler(base.AuditHandler):
                         next_run_time = audit.next_run_time
                     # if audit is new one
                     else:
-                        next_run_time = datetime.datetime.utcnow()
+                        next_run_time = timeutils.utcnow()
                     self._add_job('interval', audit, audit_context,
                                   seconds=int(audit.interval),
                                   next_run_time=next_run_time)

watcher/decision_engine/datasources/base.py

@@ -91,8 +91,8 @@ class DataSourceBase(object):
             except Exception as e:
                 LOG.exception(e)
                 self.query_retry_reset(e)
-                LOG.warning("Retry {0} of {1} while retrieving metrics retry "
-                            "in {2} seconds".format(i+1, num_retries, timeout))
+                LOG.warning("Retry %d of %d while retrieving metrics retry "
+                            "in %d seconds", i+1, num_retries, timeout)
                 time.sleep(timeout)
 
     @abc.abstractmethod

watcher/decision_engine/datasources/ceilometer.py

@@ -1,276 +0,0 @@
-# -*- encoding: utf-8 -*-
-# Copyright (c) 2015 b<>com
-#
-# Authors: Jean-Emile DARTOIS <jean-emile.dartois@b-com.com>
-#
-# 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 datetime
-
-from oslo_log import log
-from oslo_utils import timeutils
-
-from watcher._i18n import _
-from watcher.common import clients
-from watcher.common import exception
-from watcher.decision_engine.datasources import base
-
-
-LOG = log.getLogger(__name__)
-
-
-try:
-    from ceilometerclient import exc
-    HAS_CEILCLIENT = True
-except ImportError:
-    HAS_CEILCLIENT = False
-
-
-class CeilometerHelper(base.DataSourceBase):
-
-    NAME = 'ceilometer'
-    METRIC_MAP = dict(host_cpu_usage='compute.node.cpu.percent',
-                      host_ram_usage='hardware.memory.used',
-                      host_outlet_temp='hardware.ipmi.node.outlet_temperature',
-                      host_inlet_temp='hardware.ipmi.node.temperature',
-                      host_airflow='hardware.ipmi.node.airflow',
-                      host_power='hardware.ipmi.node.power',
-                      instance_cpu_usage='cpu_util',
-                      instance_ram_usage='memory.resident',
-                      instance_ram_allocated='memory',
-                      instance_l3_cache_usage='cpu_l3_cache',
-                      instance_root_disk_size='disk.root.size',
-                      )
-
-    def __init__(self, osc=None):
-        """:param osc: an OpenStackClients instance"""
-        self.osc = osc if osc else clients.OpenStackClients()
-        self.ceilometer = self.osc.ceilometer()
-        LOG.warning("Ceilometer API is deprecated and Ceilometer Datasource "
-                    "module is no longer maintained. We recommend to use "
-                    "Gnocchi instead.")
-
-    @staticmethod
-    def format_query(user_id, tenant_id, resource_id,
-                     user_ids, tenant_ids, resource_ids):
-        query = []
-
-        def query_append(query, _id, _ids, field):
-            if _id:
-                _ids = [_id]
-            for x_id in _ids:
-                query.append({"field": field, "op": "eq", "value": x_id})
-
-        query_append(query, user_id, (user_ids or []), "user_id")
-        query_append(query, tenant_id, (tenant_ids or []), "project_id")
-        query_append(query, resource_id, (resource_ids or []), "resource_id")
-
-        return query
-
-    def _timestamps(self, start_time, end_time):
-
-        def _format_timestamp(_time):
-            if _time:
-                if isinstance(_time, datetime.datetime):
-                    return _time.isoformat()
-                return _time
-            return None
-
-        start_timestamp = _format_timestamp(start_time)
-        end_timestamp = _format_timestamp(end_time)
-
-        if ((start_timestamp is not None) and (end_timestamp is not None) and
-                (timeutils.parse_isotime(start_timestamp) >
-                 timeutils.parse_isotime(end_timestamp))):
-            raise exception.Invalid(
-                _("Invalid query: %(start_time)s > %(end_time)s") % dict(
-                    start_time=start_timestamp, end_time=end_timestamp))
-        return start_timestamp, end_timestamp
-
-    def build_query(self, user_id=None, tenant_id=None, resource_id=None,
-                    user_ids=None, tenant_ids=None, resource_ids=None,
-                    start_time=None, end_time=None):
-        """Returns query built from given parameters.
-
-        This query can be then used for querying resources, meters and
-        statistics.
-        :param user_id: user_id, has a priority over list of ids
-        :param tenant_id: tenant_id, has a priority over list of ids
-        :param resource_id: resource_id, has a priority over list of ids
-        :param user_ids: list of user_ids
-        :param tenant_ids: list of tenant_ids
-        :param resource_ids: list of resource_ids
-        :param start_time: datetime from which measurements should be collected
-        :param end_time: datetime until which measurements should be collected
-        """
-
-        query = self.format_query(user_id, tenant_id, resource_id,
-                                  user_ids, tenant_ids, resource_ids)
-
-        start_timestamp, end_timestamp = self._timestamps(start_time,
-                                                          end_time)
-
-        if start_timestamp:
-            query.append({"field": "timestamp", "op": "ge",
-                          "value": start_timestamp})
-        if end_timestamp:
-            query.append({"field": "timestamp", "op": "le",
-                          "value": end_timestamp})
-        return query
-
-    def query_retry_reset(self, exception_instance):
-        if isinstance(exception_instance, exc.HTTPUnauthorized):
-            self.osc.reset_clients()
-            self.ceilometer = self.osc.ceilometer()
-
-    def list_metrics(self):
-        """List the user's meters."""
-        meters = self.query_retry(f=self.ceilometer.meters.list)
-        if not meters:
-            return set()
-        else:
-            return meters
-
-    def check_availability(self):
-        status = self.query_retry(self.ceilometer.resources.list)
-        if status:
-            return 'available'
-        else:
-            return 'not available'
-
-    def query_sample(self, meter_name, query, limit=1):
-        return self.query_retry(f=self.ceilometer.samples.list,
-                                meter_name=meter_name,
-                                limit=limit,
-                                q=query)
-
-    def statistic_aggregation(self, resource=None, resource_type=None,
-                              meter_name=None, period=300, granularity=300,
-                              aggregate='mean'):
-        end_time = datetime.datetime.utcnow()
-        start_time = end_time - datetime.timedelta(seconds=int(period))
-
-        meter = self._get_meter(meter_name)
-
-        if aggregate == 'mean':
-            aggregate = 'avg'
-        elif aggregate == 'count':
-            aggregate = 'avg'
-            LOG.warning('aggregate type count not supported by ceilometer,'
-                        ' replaced with mean.')
-
-        resource_id = resource.uuid
-        if resource_type == 'compute_node':
-            resource_id = "%s_%s" % (resource.hostname, resource.hostname)
-
-        query = self.build_query(
-            resource_id=resource_id, start_time=start_time, end_time=end_time)
-        statistic = self.query_retry(f=self.ceilometer.statistics.list,
-                                     meter_name=meter,
-                                     q=query,
-                                     period=period,
-                                     aggregates=[
-                                         {'func': aggregate}])
-
-        item_value = None
-        if statistic:
-            item_value = statistic[-1]._info.get('aggregate').get(aggregate)
-            if meter_name == 'host_airflow':
-                # Airflow from hardware.ipmi.node.airflow is reported as
-                # 1/10 th of actual CFM
-                item_value *= 10
-        return item_value
-
-    def statistic_series(self, resource=None, resource_type=None,
-                         meter_name=None, start_time=None, end_time=None,
-                         granularity=300):
-        raise NotImplementedError(
-            _('Ceilometer helper does not support statistic series method'))
-
-    def get_host_cpu_usage(self, resource, period,
-                           aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_cpu_usage', period,
-            aggregate, granularity)
-
-    def get_host_ram_usage(self, resource, period,
-                           aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_ram_usage', period,
-            aggregate, granularity)
-
-    def get_host_outlet_temp(self, resource, period,
-                             aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_outlet_temp', period,
-            aggregate, granularity)
-
-    def get_host_inlet_temp(self, resource, period,
-                            aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_inlet_temp', period,
-            aggregate, granularity)
-
-    def get_host_airflow(self, resource, period,
-                         aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_airflow', period,
-            aggregate, granularity)
-
-    def get_host_power(self, resource, period,
-                       aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'compute_node', 'host_power', period,
-            aggregate, granularity)
-
-    def get_instance_cpu_usage(self, resource, period,
-                               aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'instance', 'instance_cpu_usage', period,
-            aggregate, granularity)
-
-    def get_instance_ram_usage(self, resource, period,
-                               aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'instance', 'instance_ram_usage', period,
-            aggregate, granularity)
-
-    def get_instance_ram_allocated(self, resource, period,
-                                   aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'instance', 'instance_ram_allocated', period,
-            aggregate, granularity)
-
-    def get_instance_l3_cache_usage(self, resource, period,
-                                    aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'instance', 'instance_l3_cache_usage', period,
-            aggregate, granularity)
-
-    def get_instance_root_disk_size(self, resource, period,
-                                    aggregate, granularity=None):
-
-        return self.statistic_aggregation(
-            resource, 'instance', 'instance_root_disk_size', period,
-            aggregate, granularity)

watcher/decision_engine/datasources/gnocchi.py

@@ -16,12 +16,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from datetime import datetime
 from datetime import timedelta
 
 from gnocchiclient import exceptions as gnc_exc
 from oslo_config import cfg
 from oslo_log import log
+from oslo_utils import timeutils
 
 from watcher.common import clients
 from watcher.decision_engine.datasources import base
@@ -69,7 +69,7 @@ class GnocchiHelper(base.DataSourceBase):
     def statistic_aggregation(self, resource=None, resource_type=None,
                               meter_name=None, period=300, aggregate='mean',
                               granularity=300):
-        stop_time = datetime.utcnow()
+        stop_time = timeutils.utcnow()
         start_time = stop_time - timedelta(seconds=(int(period)))
 
         meter = self._get_meter(meter_name)
@@ -90,8 +90,8 @@ class GnocchiHelper(base.DataSourceBase):
                 **kwargs)
 
             if not resources:
-                LOG.warning("The {0} resource {1} could not be "
-                            "found".format(self.NAME, resource_id))
+                LOG.warning("The %s resource %s could not be found",
+                            self.NAME, resource_id)
                 return
 
             resource_id = resources[0]['id']
@@ -99,7 +99,7 @@ class GnocchiHelper(base.DataSourceBase):
         if meter_name == "instance_cpu_usage":
             if resource_type != "instance":
                 LOG.warning("Unsupported resource type for metric "
-                            "'instance_cpu_usage': ", resource_type)
+                            "'instance_cpu_usage': %s", resource_type)
                 return
 
             # The "cpu_util" gauge (percentage) metric has been removed.
@@ -172,8 +172,8 @@ class GnocchiHelper(base.DataSourceBase):
                 **kwargs)
 
             if not resources:
-                LOG.warning("The {0} resource {1} could not be "
-                            "found".format(self.NAME, resource_id))
+                LOG.warning("The %s resource %s could not be found",
+                            self.NAME, resource_id)
                 return
 
             resource_id = resources[0]['id']