Merge "Handle deprecated "cpu_util" metric" into stable/2023.2

The Nova collector json schema validation started [1][2] failing after
the jsonschema upper constraint was bumped from 4.17.3 to 4.19.1 [3].

The reason is that jsonschema v4.18.0a1 switched to a reference
resolving library [4], which treats the aggregate "id" as a jsonschema
id and expects it to be a string [5]. For this reason, we're now getting
AttributeError exceptions.

As a workaround, we'll rename the "id" ref element as "host_aggr_id".

Also, the watcher-tempest-multinode job is configured to use Focal,
which is no longer supported by Devstack [6]. That being considered,
we'll switch to Ubuntu Jammy (22.04).

While at it, we're disabling Cinder Backup, which isn't used while
testing Watched. It currently causes Devstack failures since it
uses the Swift backend by default, which is disabled.

[1] https://paste.opendev.org/raw/bjQ1uIdbDMnmA1UEhxLL/
[2] https://paste.opendev.org/raw/bNgxqulBwBLYB7tNhrU4/
[3] ab0dcbdda2
[4] https://github.com/python-jsonschema/jsonschema/releases/tag/v4.18.0a1
[5] c23a5dc1c9/referencing/jsonschema.py (L54-L55C18)
[6] https://paste.openstack.org/raw/bSoSyXgbtmq6d9768HQn/

Change-Id: I300620c2ec4857b1e0d402a9b57a637f576eeb24
(cherry picked from commit 922478fbda)

.gitreview

@@ -2,3 +2,4 @@
 host=review.opendev.org
 port=29418
 project=openstack/watcher.git
+defaultbranch=stable/2023.2

.zuul.yaml

@@ -1,8 +1,9 @@
 - project:
+    queue: watcher
     templates:
       - check-requirements
       - openstack-cover-jobs
-      - openstack-python3-yoga-jobs
+      - openstack-python3-jobs
       - publish-openstack-docs-pti
       - release-notes-jobs-python3
     check:
@@ -14,7 +15,6 @@
         - watcherclient-tempest-functional
         - watcher-tempest-functional-ipv6-only
     gate:
-      queue: watcher
       jobs:
         - watcher-tempest-functional
         - watcher-tempest-functional-ipv6-only
@@ -89,7 +89,7 @@
 - job:
     name: watcher-tempest-multinode
     parent: watcher-tempest-functional
-    nodeset: openstack-two-node-focal
+    nodeset: openstack-two-node-jammy
     roles:
       - zuul: openstack/tempest
     group-vars:
@@ -107,6 +107,7 @@
           watcher-api: false
           watcher-decision-engine: true
           watcher-applier: false
+          c-bak: false
           ceilometer: false
           ceilometer-acompute: false
           ceilometer-acentral: false

doc/source/conf.py

@@ -56,8 +56,8 @@ source_suffix = '.rst'
 master_doc = 'index'
 
 # General information about the project.
-project = u'Watcher'
-copyright = u'OpenStack Foundation'
+project = 'Watcher'
+copyright = 'OpenStack Foundation'
 
 # A list of ignored prefixes for module index sorting.
 modindex_common_prefix = ['watcher.']
@@ -91,14 +91,14 @@ pygments_style = 'native'
 # List of tuples 'sourcefile', 'target', u'title', u'Authors name', 'manual'
 
 man_pages = [
-    ('man/watcher-api', 'watcher-api', u'Watcher API Server',
-     [u'OpenStack'], 1),
-    ('man/watcher-applier', 'watcher-applier', u'Watcher Applier',
-     [u'OpenStack'], 1),
+    ('man/watcher-api', 'watcher-api', 'Watcher API Server',
+     ['OpenStack'], 1),
+    ('man/watcher-applier', 'watcher-applier', 'Watcher Applier',
+     ['OpenStack'], 1),
     ('man/watcher-db-manage', 'watcher-db-manage',
-     u'Watcher Db Management Utility', [u'OpenStack'], 1),
+     'Watcher Db Management Utility', ['OpenStack'], 1),
     ('man/watcher-decision-engine', 'watcher-decision-engine',
-     u'Watcher Decision Engine', [u'OpenStack'], 1),
+     'Watcher Decision Engine', ['OpenStack'], 1),
 ]
 
 # -- Options for HTML output --------------------------------------------------
@@ -128,8 +128,8 @@ openstackdocs_bug_tag = ''
 latex_documents = [
     ('index',
      'doc-watcher.tex',
-     u'Watcher Documentation',
-     u'OpenStack Foundation', 'manual'),
+     'Watcher Documentation',
+     'OpenStack Foundation', 'manual'),
 ]
 
 # If false, no module index is generated.

doc/source/configuration/configuring.rst

@@ -372,7 +372,7 @@ You can configure and install Ceilometer by following the documentation below :
 #. https://docs.openstack.org/ceilometer/latest
 
 The built-in strategy 'basic_consolidation' provided by watcher requires
-"**compute.node.cpu.percent**" and "**cpu_util**" measurements to be collected
+"**compute.node.cpu.percent**" and "**cpu**" measurements to be collected
 by Ceilometer.
 The measurements available depend on the hypervisors that OpenStack manages on
 the specific implementation.

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

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

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

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

doc/source/strategies/saving_energy.rst

@@ -89,9 +89,9 @@ step 2: Create audit to do optimization
 .. code-block:: shell
 
     $ openstack optimize audittemplate create \
-      at1 saving_energy --strategy saving_energy
+      saving_energy_template1 saving_energy --strategy saving_energy
 
-    $ openstack optimize audit create -a at1 \
+    $ openstack optimize audit create -a saving_energy_audit1 \
       -p free_used_percent=20.0
 
 External Links

doc/source/strategies/vm_workload_consolidation.rst

@@ -22,8 +22,7 @@ The *vm_workload_consolidation* strategy requires the following metrics:
 ============================ ============ ======= =========================
 metric                       service name plugins comment
 ============================ ============ ======= =========================
-``cpu_util``                 ceilometer_  none    cpu_util has been removed
-                                                  since Stein.
+``cpu``                      ceilometer_  none
 ``memory.resident``          ceilometer_  none
 ``memory``                   ceilometer_  none
 ``disk.root.size``           ceilometer_  none

doc/source/strategies/workload-stabilization.rst

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

doc/source/strategies/workload_balance.rst

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

releasenotes/source/2023.1.rst

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

releasenotes/source/conf.py

@@ -53,7 +53,7 @@ source_suffix = '.rst'
 master_doc = 'index'
 
 # General information about the project.
-copyright = u'2016, Watcher developers'
+copyright = '2016, Watcher developers'
 
 # Release notes are version independent
 # The short X.Y version.
@@ -196,8 +196,8 @@ latex_elements = {
 # 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', u'Watcher Documentation',
-   u'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
@@ -226,8 +226,8 @@ latex_documents = [
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'watcher', u'Watcher Documentation',
-     [u'Watcher developers'], 1)
+    ('index', 'watcher', 'Watcher Documentation',
+     ['Watcher developers'], 1)
 ]
 
 # If true, show URL addresses after external links.
@@ -240,8 +240,8 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'watcher', u'Watcher Documentation',
-   u'Watcher developers', 'watcher', 'One line description of project.',
+  ('index', 'watcher', 'Watcher Documentation',
+   'Watcher developers', 'watcher', 'One line description of project.',
    'Miscellaneous'),
 ]
 

releasenotes/source/index.rst

@@ -21,6 +21,9 @@ Contents:
    :maxdepth: 1
 
    unreleased
+   2023.1
+   zed
+   yoga
    xena
    wallaby
    victoria

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

@@ -1,15 +1,17 @@
 # Andi Chandler <andi@gowling.com>, 2017. #zanata
 # Andi Chandler <andi@gowling.com>, 2018. #zanata
 # Andi Chandler <andi@gowling.com>, 2020. #zanata
+# Andi Chandler <andi@gowling.com>, 2022. #zanata
+# Andi Chandler <andi@gowling.com>, 2023. #zanata
 msgid ""
 msgstr ""
 "Project-Id-Version: python-watcher\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2020-10-27 04:13+0000\n"
+"POT-Creation-Date: 2023-08-14 03:05+0000\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"PO-Revision-Date: 2020-10-28 11:13+0000\n"
+"PO-Revision-Date: 2023-06-21 07:54+0000\n"
 "Last-Translator: Andi Chandler <andi@gowling.com>\n"
 "Language-Team: English (United Kingdom)\n"
 "Language: en_GB\n"
@@ -58,12 +60,18 @@ msgstr "1.9.0"
 msgid "2.0.0"
 msgstr "2.0.0"
 
+msgid "2023.1 Series Release Notes"
+msgstr "2023.1 Series Release Notes"
+
 msgid "3.0.0"
 msgstr "3.0.0"
 
 msgid "4.0.0"
 msgstr "4.0.0"
 
+msgid "6.0.0"
+msgstr "6.0.0"
+
 msgid "A ``watcher-status upgrade check`` has been added for this."
 msgstr "A ``watcher-status upgrade check`` has been added for this."
 
@@ -744,6 +752,23 @@ msgstr ""
 "The configuration options for query retries in `[gnocchi_client]` are "
 "deprecated and the option in `[watcher_datasources]` should now be used."
 
+msgid ""
+"The default value of ``[oslo_policy] policy_file`` config option has been "
+"changed from ``policy.json`` to ``policy.yaml``. Operators who are utilizing "
+"customized or previously generated static policy JSON files (which are not "
+"needed by default), should generate new policy files or convert them in YAML "
+"format. Use the `oslopolicy-convert-json-to-yaml <https://docs.openstack.org/"
+"oslo.policy/latest/cli/oslopolicy-convert-json-to-yaml.html>`_ tool to "
+"convert a JSON to YAML formatted policy file in backward compatible way."
+msgstr ""
+"The default value of ``[oslo_policy] policy_file`` config option has been "
+"changed from ``policy.json`` to ``policy.yaml``. Operators who are utilizing "
+"customized or previously generated static policy JSON files (which are not "
+"needed by default), should generate new policy files or convert them in YAML "
+"format. Use the `oslopolicy-convert-json-to-yaml <https://docs.openstack.org/"
+"oslo.policy/latest/cli/oslopolicy-convert-json-to-yaml.html>`_ tool to "
+"convert a JSON to YAML formatted policy file in backward compatible way."
+
 msgid ""
 "The graph model describes how VMs are associated to compute hosts. This "
 "allows for seeing relationships upfront between the entities and hence can "
@@ -799,6 +824,21 @@ msgstr "Train Series Release Notes"
 msgid "Upgrade Notes"
 msgstr "Upgrade Notes"
 
+msgid ""
+"Use of JSON policy files was deprecated by the ``oslo.policy`` library "
+"during the Victoria development cycle. As a result, this deprecation is "
+"being noted in the Wallaby cycle with an anticipated future removal of "
+"support by ``oslo.policy``. As such operators will need to convert to YAML "
+"policy files. Please see the upgrade notes for details on migration of any "
+"custom policy files."
+msgstr ""
+"Use of JSON policy files was deprecated by the ``oslo.policy`` library "
+"during the Victoria development cycle. As a result, this deprecation is "
+"being noted in the Wallaby cycle with an anticipated future removal of "
+"support by ``oslo.policy``. As such operators will need to convert to YAML "
+"policy files. Please see the upgrade notes for details on migration of any "
+"custom policy files."
+
 msgid ""
 "Using ``watcher/api/app.wsgi`` script is deprecated and it will be removed "
 "in U release. Please switch to automatically generated ``watcher-api-wsgi`` "
@@ -814,6 +854,9 @@ msgstr "Ussuri Series Release Notes"
 msgid "Victoria Series Release Notes"
 msgstr "Victoria Series Release Notes"
 
+msgid "Wallaby Series Release Notes"
+msgstr "Wallaby Series Release Notes"
+
 msgid ""
 "Watcher can continuously optimize the OpenStack cloud for a specific "
 "strategy or goal by triggering an audit periodically which generates an "
@@ -924,6 +967,15 @@ msgstr "We also add some new properties:"
 msgid "Welcome to watcher's Release Notes documentation!"
 msgstr "Welcome to watcher's Release Notes documentation!"
 
+msgid "Xena Series Release Notes"
+msgstr "Xena Series Release Notes"
+
+msgid "Yoga Series Release Notes"
+msgstr "Yoga Series Release Notes"
+
+msgid "Zed Series Release Notes"
+msgstr "Zed Series Release Notes"
+
 msgid "``[watcher_datasources] datasources = gnocchi,monasca,ceilometer``"
 msgstr "``[watcher_datasources] datasources = gnocchi,monasca,ceilometer``"
 

releasenotes/source/yoga.rst

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

releasenotes/source/zed.rst

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

requirements.txt

@@ -17,7 +17,7 @@ oslo.context>=2.21.0 # Apache-2.0
 oslo.db>=4.44.0 # Apache-2.0
 oslo.i18n>=3.20.0 # Apache-2.0
 oslo.log>=3.37.0 # Apache-2.0
-oslo.messaging>=8.1.2 # Apache-2.0
+oslo.messaging>=14.1.0 # Apache-2.0
 oslo.policy>=3.6.0 # Apache-2.0
 oslo.reports>=1.27.0 # Apache-2.0
 oslo.serialization>=2.25.0 # Apache-2.0

test-requirements.txt

@@ -12,3 +12,4 @@ 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

tox.ini

@@ -1,7 +1,6 @@
 [tox]
 minversion = 3.18.0
 envlist = py3,pep8
-skipsdist = True
 ignore_basepython_conflict = True
 
 [testenv]
@@ -9,7 +8,7 @@ basepython = python3
 usedevelop = True
 allowlist_externals = find
                       rm
-install_command = pip install -c{env:TOX_CONSTRAINTS_FILE:https://releases.openstack.org/constraints/upper/master} {opts} {packages}
+install_command = pip install -c{env:TOX_CONSTRAINTS_FILE:https://releases.openstack.org/constraints/upper/2023.2} {opts} {packages}
 setenv =
    VIRTUAL_ENV={envdir}
 deps =
@@ -19,13 +18,19 @@ commands =
   rm -f .testrepository/times.dbm
   find . -type f -name "*.py[c|o]" -delete
   stestr run {posargs}
-passenv = http_proxy HTTP_PROXY https_proxy HTTPS_PROXY no_proxy NO_PROXY
+passenv =
+  http_proxy
+  HTTP_PROXY
+  https_proxy
+  HTTPS_PROXY
+  no_proxy
+  NO_PROXY
 
 [testenv:pep8]
 commands =
     doc8 doc/source/ CONTRIBUTING.rst HACKING.rst README.rst
     flake8
-    bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
+    #bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
 
 [testenv:venv]
 setenv = PYTHONHASHSEED=0

watcher/common/rpc.py

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

watcher/conf/grafana_client.py

@@ -134,7 +134,13 @@ GRAFANA_CLIENT_OPTS = [
                      "InfluxDB this will be the retention period. "
                      "These queries will need to be constructed using tools "
                      "such as Postman. Example: SELECT cpu FROM {4}."
-                     "cpu_percent WHERE host == '{1}' AND time > now()-{2}s")]
+                     "cpu_percent WHERE host == '{1}' AND time > now()-{2}s"),
+    cfg.IntOpt('http_timeout',
+               min=0,
+               default=60,
+               mutable=True,
+               help='Timeout for Grafana request')
+]
 
 
 def register_opts(conf):

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

@@ -6,6 +6,7 @@ Create Date: 2017-03-24 11:21:29.036532
 
 """
 from alembic import op
+from sqlalchemy import inspect
 import sqlalchemy as sa
 
 from watcher.db.sqlalchemy import models
@@ -14,8 +15,17 @@ from watcher.db.sqlalchemy import models
 revision = '0f6042416884'
 down_revision = '001'
 
+def _table_exists(table_name):
+    bind = op.get_context().bind
+    insp = inspect(bind)
+    names = insp.get_table_names()
+    return any(t == table_name for t in names)
+
 
 def upgrade():
+    if _table_exists('apscheduler_jobs'):
+        return
+
     op.create_table(
         'apscheduler_jobs',
         sa.Column('id', sa.Unicode(191, _warn_on_bytestring=False),

watcher/db/sqlalchemy/api.py

@@ -44,7 +44,11 @@ _FACADE = None
 def _create_facade_lazily():
     global _FACADE
     if _FACADE is None:
-        _FACADE = db_session.EngineFacade.from_config(CONF)
+        # FIXME(amoralej): Remove autocommit=True (and ideally use of
+        # LegacyEngineFacade) asap since it's not compatible with SQLAlchemy
+        # 2.0.
+        _FACADE = db_session.EngineFacade.from_config(CONF,
+                                                      autocommit=True)
     return _FACADE
 
 

watcher/decision_engine/datasources/gnocchi.py

@@ -38,7 +38,7 @@ class GnocchiHelper(base.DataSourceBase):
                       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_cpu_usage='cpu',
                       instance_ram_usage='memory.resident',
                       instance_ram_allocated='memory',
                       instance_l3_cache_usage='cpu_l3_cache',
@@ -93,6 +93,25 @@ class GnocchiHelper(base.DataSourceBase):
 
             resource_id = resources[0]['id']
 
+        if meter_name == "instance_cpu_usage":
+            if resource_type != "instance":
+                LOG.warning("Unsupported resource type for metric "
+                            "'instance_cpu_usage': ", resource_type)
+                return
+
+            # The "cpu_util" gauge (percentage) metric has been removed.
+            # We're going to obtain the same result by using the rate of change
+            # aggregate operation.
+            if aggregate not in ("mean", "rate:mean"):
+                LOG.warning("Unsupported aggregate for instance_cpu_usage "
+                            "metric: %s. "
+                            "Supported aggregates: mean, rate:mean ",
+                            aggregate)
+                return
+
+            # TODO(lpetrut): consider supporting other aggregates.
+            aggregate = "rate:mean"
+
         raw_kwargs = dict(
             metric=meter,
             start=start_time,
@@ -117,6 +136,17 @@ class GnocchiHelper(base.DataSourceBase):
                 # Airflow from hardware.ipmi.node.airflow is reported as
                 # 1/10 th of actual CFM
                 return_value *= 10
+            if meter_name == "instance_cpu_usage":
+                # "rate:mean" can return negative values for migrated vms.
+                return_value = max(0, return_value)
+
+                # We're converting the cumulative cpu time (ns) to cpu usage
+                # percentage.
+                vcpus = resource.vcpus
+                if not vcpus:
+                    LOG.warning("instance vcpu count not set, assuming 1")
+                    vcpus = 1
+                return_value *= 100 / (granularity * 10e+8) / vcpus
 
         return return_value
 

watcher/decision_engine/datasources/grafana.py

@@ -138,7 +138,8 @@ class GrafanaHelper(base.DataSourceBase):
             raise exception.DataSourceNotAvailable(self.NAME)
 
         resp = requests.get(self._base_url + str(project_id) + '/query',
-                            params=params, headers=self._headers)
+                            params=params, headers=self._headers,
+                            timeout=CONF.grafana_client.http_timeout)
         if resp.status_code == HTTPStatus.OK:
             return resp
         elif resp.status_code == HTTPStatus.BAD_REQUEST:

watcher/decision_engine/model/collector/nova.py

@@ -48,7 +48,7 @@ class NovaClusterDataModelCollector(base.BaseClusterDataModelCollector):
                     "type": "array",
                     "items": {
                         "anyOf": [
-                            {"$ref": HOST_AGGREGATES + "id"},
+                            {"$ref": HOST_AGGREGATES + "host_aggr_id"},
                             {"$ref": HOST_AGGREGATES + "name"},
                         ]
                     }
@@ -98,7 +98,8 @@ class NovaClusterDataModelCollector(base.BaseClusterDataModelCollector):
                                 "type": "array",
                                 "items": {
                                     "anyOf": [
-                                        {"$ref": HOST_AGGREGATES + "id"},
+                                        {"$ref":
+                                            HOST_AGGREGATES + "host_aggr_id"},
                                         {"$ref": HOST_AGGREGATES + "name"},
                                     ]
                                 }
@@ -129,7 +130,7 @@ class NovaClusterDataModelCollector(base.BaseClusterDataModelCollector):
             "additionalProperties": False
         },
         "host_aggregates": {
-            "id": {
+            "host_aggr_id": {
                 "properties": {
                     "id": {
                         "oneOf": [

watcher/decision_engine/strategy/strategies/base.py

@@ -252,9 +252,6 @@ class BaseStrategy(loadable.Loadable, metaclass=abc.ABCMeta):
         if not self.compute_model:
             raise exception.ClusterStateNotDefined()
 
-        if self.compute_model.stale:
-            raise exception.ClusterStateStale()
-
         LOG.debug(self.compute_model.to_string())
 
     def execute(self, audit=None):

watcher/decision_engine/strategy/strategies/saving_energy.py

@@ -206,13 +206,13 @@ class SavingEnergy(base.SavingEnergyBaseStrategy):
             for node in random.sample(self.free_poweron_node_pool,
                                       (len_poweron - need_poweron)):
                 self.add_action_poweronoff_node(node, 'off')
-                LOG.debug("power off %s", node.uuid)
+                LOG.info("power off %s", node.uuid)
         elif len_poweron < need_poweron:
             diff = need_poweron - len_poweron
             for node in random.sample(self.free_poweroff_node_pool,
                                       min(len_poweroff, diff)):
                 self.add_action_poweronoff_node(node, 'on')
-                LOG.debug("power on %s", node.uuid)
+                LOG.info("power on %s", node.uuid)
 
     def pre_execute(self):
         self._pre_execute()

watcher/decision_engine/strategy/strategies/workload_balance.py

@@ -295,7 +295,7 @@ class WorkloadBalance(base.WorkloadStabilizationBaseStrategy):
                         self.threshold)
             return self.solution
 
-        # choose the server with largest cpu_util
+        # choose the server with largest cpu usage
         source_nodes = sorted(source_nodes,
                               reverse=True,
                               key=lambda x: (x[self._meter]))

watcher/locale/en_GB/LC_MESSAGES/watcher.po

@@ -1,15 +1,16 @@
 # Andi Chandler <andi@gowling.com>, 2017. #zanata
 # Andi Chandler <andi@gowling.com>, 2018. #zanata
 # Andi Chandler <andi@gowling.com>, 2020. #zanata
+# Andi Chandler <andi@gowling.com>, 2022. #zanata
 msgid ""
 msgstr ""
 "Project-Id-Version: watcher VERSION\n"
 "Report-Msgid-Bugs-To: https://bugs.launchpad.net/openstack-i18n/\n"
-"POT-Creation-Date: 2020-10-27 04:14+0000\n"
+"POT-Creation-Date: 2022-08-29 03:03+0000\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"PO-Revision-Date: 2020-10-28 11:02+0000\n"
+"PO-Revision-Date: 2022-05-31 08:38+0000\n"
 "Last-Translator: Andi Chandler <andi@gowling.com>\n"
 "Language-Team: English (United Kingdom)\n"
 "Language: en_GB\n"
@@ -507,6 +508,9 @@ msgstr ""
 msgid "Plugins"
 msgstr "Plugins"
 
+msgid "Policy File JSON to YAML Migration"
+msgstr "Policy File JSON to YAML Migration"
+
 #, python-format
 msgid "Policy doesn't allow %(action)s to be performed."
 msgstr "Policy doesn't allow %(action)s to be performed."

watcher/tests/common/test_service.py

@@ -80,13 +80,13 @@ class TestService(base.TestCase):
         super(TestService, self).setUp()
 
     @mock.patch.object(om.rpc.server, "RPCServer")
-    def test_start(self, m_handler):
+    def _test_start(self, m_handler):
         dummy_service = service.Service(DummyManager)
         dummy_service.start()
         self.assertEqual(1, m_handler.call_count)
 
     @mock.patch.object(om.rpc.server, "RPCServer")
-    def test_stop(self, m_handler):
+    def _test_stop(self, m_handler):
         dummy_service = service.Service(DummyManager)
         dummy_service.stop()
         self.assertEqual(1, m_handler.call_count)

watcher/tests/decision_engine/datasources/test_gnocchi_helper.py

@@ -40,17 +40,25 @@ class TestGnocchiHelper(base.BaseTestCase):
         self.addCleanup(stat_agg_patcher.stop)
 
     def test_gnocchi_statistic_aggregation(self, mock_gnocchi):
+        vcpus = 2
+        mock_instance = mock.Mock(
+            id='16a86790-327a-45f9-bc82-45839f062fdc',
+            vcpus=vcpus)
+
         gnocchi = mock.MagicMock()
+        # cpu time rate of change (ns)
+        mock_rate_measure = 360 * 10e+8 * vcpus * 5.5 / 100
         expected_result = 5.5
 
-        expected_measures = [["2017-02-02T09:00:00.000000", 360, 5.5]]
+        expected_measures = [
+            ["2017-02-02T09:00:00.000000", 360, mock_rate_measure]]
 
         gnocchi.metric.get_measures.return_value = expected_measures
         mock_gnocchi.return_value = gnocchi
 
         helper = gnocchi_helper.GnocchiHelper()
         result = helper.statistic_aggregation(
-            resource=mock.Mock(id='16a86790-327a-45f9-bc82-45839f062fdc'),
+            resource=mock_instance,
             resource_type='instance',
             meter_name='instance_cpu_usage',
             period=300,
@@ -59,6 +67,14 @@ class TestGnocchiHelper(base.BaseTestCase):
         )
         self.assertEqual(expected_result, result)
 
+        gnocchi.metric.get_measures.assert_called_once_with(
+            metric="cpu",
+            start=mock.ANY,
+            stop=mock.ANY,
+            resource_id=mock_instance.uuid,
+            granularity=360,
+            aggregation="rate:mean")
+
     def test_gnocchi_statistic_series(self, mock_gnocchi):
         gnocchi = mock.MagicMock()
         expected_result = {