feat(resilience4j): add new integration

.codecov.yml

@@ -171,6 +171,10 @@ coverage:
         target: 75
         flags:
         - redpanda
+      Resilience4j:
+        target: 75
+        flags:
+        - resilience4j
       Riak_MDC_Replication:
         target: 75
         flags:
@@ -577,6 +581,11 @@ flags:
     paths:
     - redpanda/datadog_checks/redpanda
     - redpanda/tests
+  resilience4j:
+    carryforward: true
+    paths:
+    - resilience4j/datadog_checks/resilience4j
+    - resilience4j/tests
   riak_repl:
     carryforward: true
     paths:

.github/CODEOWNERS

@@ -164,6 +164,7 @@
 /redis_enterprise/                       @redis-field-engineering [email protected]
 /redis_sentinel/                         @DataDog/agent-integrations
 /redpanda/                               @redpanda-data [email protected]
+/resilience4j/                           @willianccs [email protected]
 /resin/                                  @brentm5
 /retool/                                 @jamiecuffe @DataDog/ecosystems-review
 /riak_repl/                              @abtreece
@@ -318,7 +319,7 @@
 /aqua/*metadata.csv                      @DataDog/container-integrations @DataDog/documentation
 /aqua/manifest.json                      @DataDog/container-integrations @DataDog/documentation
 /aqua/README.md                          @DataDog/container-integrations @DataDog/documentation
-/aqua/assets/dashboards                  @DataDog/container-integrations @DataDog/documentation @DataDog/reporting-and-sharing 
+/aqua/assets/dashboards                  @DataDog/container-integrations @DataDog/documentation @DataDog/reporting-and-sharing
 /aqua/assets/monitors                    @DataDog/container-integrations @DataDog/documentation @DataDog/alerting-product
 
 /auth0/*metadata.csv                     @DataDog/agent-integrations @DataDog/documentation
@@ -1098,8 +1099,8 @@
 /sosivio/assets/dashboards                    @danarlowski @DataDog/documentation @DataDog/reporting-and-sharing @DataDog/agent-integrations
 /sosivio/assets/monitors                      @danarlowski @DataDog/documentation @DataDog/alerting-product @DataDog/agent-integrations
 
-/emnify/*metadata.csv                 @EMnify/development @EMnify/rademade @DataDog/documentation 
-/emnify/manifest.json                 @EMnify/development @EMnify/rademade @DataDog/documentation 
+/emnify/*metadata.csv                 @EMnify/development @EMnify/rademade @DataDog/documentation
+/emnify/manifest.json                 @EMnify/development @EMnify/rademade @DataDog/documentation
 /emnify/README.md                     @EMnify/development @EMnify/rademade @DataDog/documentation
 /emnify/assets/dashboards             @EMnify/development @EMnify/rademade @DataDog/documentation @DataDog/reporting-and-sharing
 /emnify/assets/monitors               @EMnify/development @EMnify/rademade @DataDog/documentation @DataDog/alerting-product

.github/workflows/test-all.yml

@@ -1056,6 +1056,25 @@ jobs:
       test-py3: ${{ inputs.test-py3 }}
       setup-env-vars: "${{ inputs.setup-env-vars }}"
     secrets: inherit
+  j09df637:
+    uses: DataDog/integrations-core/.github/workflows/test-target.yml@master
+    with:
+      job-name: Resilience4j
+      target: resilience4j
+      platform: linux
+      runner: '["ubuntu-22.04"]'
+      repo: "${{ inputs.repo }}"
+      python-version: "${{ inputs.python-version }}"
+      standard: ${{ inputs.standard }}
+      latest: ${{ inputs.latest }}
+      agent-image: "${{ inputs.agent-image }}"
+      agent-image-py2: "${{ inputs.agent-image-py2 }}"
+      agent-image-windows: "${{ inputs.agent-image-windows }}"
+      agent-image-windows-py2: "${{ inputs.agent-image-windows-py2 }}"
+      test-py2: ${{ inputs.test-py2 }}
+      test-py3: ${{ inputs.test-py3 }}
+      setup-env-vars: "${{ inputs.setup-env-vars }}"
+    secrets: inherit
   jc5ec7c0:
     uses: DataDog/integrations-core/.github/workflows/test-target.yml@master
     with:

resilience4j/CHANGELOG.md

@@ -0,0 +1,8 @@
+# CHANGELOG - Resilience4j
+
+## 1.0.0 / 2025-01-24
+
+***Added***:
+
+* Initial Release
+

resilience4j/README.md

@@ -0,0 +1,60 @@
+# Agent Check: Resilience4j
+
+## Overview
+
+[Resilience4j](https://github.com/resilience4j/resilience4j) is a lightweight fault tolerance library inspired by Netflix Hystrix, but designed for functional programming. This check monitors [Resilience4j][1] through the Datadog Agent.
+
+## Setup
+
+### Installation
+
+To install the Resilience4j check on your host:
+
+1. Install the [developer toolkit]
+(<https://docs.datadoghq.com/developers/integrations/python/>)
+ on any machine.
+
+2. Run `ddev release build resilience4j` to build the package.
+
+3. [Download the Datadog Agent][2].
+
+4. Upload the build artifact to any host with an Agent and
+ run `datadog-agent integration install -w
+ path/to/resilience4j/dist/<ARTIFACT_NAME>.whl`.
+
+### Configuration
+
+1. Edit the `resilience4j/conf.yaml` file in the `conf.d/` folder at the root of your Agent's configuration directory to start collecting your Resilience4j performance data. See the [sample resilience4j/conf.yaml][4] for all available configuration options.
+
+2. [Restart the Agent][5].
+
+### Validation
+
+[Run the Agent's status subcommand][6] and look for `resilience4j` under the Checks section.
+
+## Data Collected
+
+### Metrics
+
+See [metadata.csv][7] for a list of metrics provided by this integration.
+
+### Service Checks
+
+See [service_checks.json][8] for a list of service checks provided by this integration.
+
+### Events
+
+Resilience4j does not include any events.
+
+## Troubleshooting
+
+Need help? Contact [Datadog support][3].
+
+[1]: https://resilience4j.readme.io/docs/micrometer#prometheus
+[2]: https://app.datadoghq.com/account/settings/agent/latest
+[3]: https://docs.datadoghq.com/agent/kubernetes/integrations/
+[4]: https://github.com/DataDog/integrations-extras/blob/master/resilience4j/datadog_checks/resilience4j/data/conf.yaml.example
+[5]: https://docs.datadoghq.com/agent/guide/agent-commands/#start-stop-and-restart-the-agent
+[6]: https://docs.datadoghq.com/agent/guide/agent-commands/#agent-status-and-information
+[7]: https://github.com/DataDog/integrations-extras/blob/master/resilience4j/metadata.csv
+[8]: https://github.com/DataDog/integrations-extras/blob/master/resilience4j/assets/service_checks.json

resilience4j/assets/configuration/spec.yaml

@@ -0,0 +1,10 @@
+name: Resilience4j
+files:
+- name: resilience4j.yaml
+  options:
+  - template: init_config
+    options:
+    - template: init_config/default
+  - template: instances
+    options:
+    - template: instances/default

resilience4j/assets/dashboards/resilience4j_overview.json

@@ -0,0 +1 @@
+{"title":"Resilience4j Circuit Breaker Overview","description":"This dashboard is designed to monitor the health and performance of Resilience4j Circuit Breakers and providing insights into the behavior of the circuit breakers in a Spring Boot application. It uses Spring Boot Actuator to expose metrics and Prometheus to collect and store these metrics. \n\n-   [Resilience4j Metrics](https://resilience4j.readme.io/docs/micrometer#prometheus)\nClone this template dashboard to make changes and add your own graph widgets.","widgets":[{"id":3501442757873750,"definition":{"title":"Summary","background_color":"gray","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":3494549748379606,"definition":{"title":"Number of closed CircuitBreaker","title_size":"16","title_align":"left","type":"query_value","requests":[{"response_format":"scalar","queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.state{state:closed}","aggregator":"last"}],"conditional_formats":[{"comparator":">","value":0,"palette":"white_on_green"}],"formulas":[{"formula":"query1"}]}],"autoscale":true,"precision":0,"timeseries_background":{"yaxis":{"include_zero":true},"type":"area"}},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":5787006276604120,"definition":{"title":"Number of open CircuitBreaker","title_size":"16","title_align":"left","type":"query_value","requests":[{"response_format":"scalar","queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.state{state:open}","aggregator":"last"}],"conditional_formats":[{"comparator":"=","value":0,"palette":"white_on_green"},{"comparator":">=","value":1,"palette":"white_on_yellow"}],"formulas":[{"formula":"query1"}]}],"autoscale":true,"precision":0,"timeseries_background":{"yaxis":{"include_zero":true},"type":"area"}},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5152242796496788,"definition":{"title":"Number of half_open CircuitBreaker","title_size":"16","title_align":"left","type":"query_value","requests":[{"response_format":"scalar","queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.state{state:half_open}","aggregator":"last"}],"conditional_formats":[{"comparator":"=","value":0,"palette":"white_on_green"},{"comparator":">=","value":1,"palette":"white_on_yellow"}],"formulas":[{"formula":"query1"}]}],"autoscale":true,"precision":0,"timeseries_background":{"yaxis":{"include_zero":true},"type":"area"}},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":5317812649799226,"definition":{"title":"CircuitBreaker states","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.state{$service,$state} by {state,service}"}],"response_format":"timeseries","style":{"palette":"dog_classic","order_by":"values","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":2,"width":12,"height":4}}]},"layout":{"x":0,"y":0,"width":12,"height":7}},{"id":911329350165930,"definition":{"title":"Circuit Breaker","background_color":"yellow","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":1469478086748770,"definition":{"title":"Failure Rate: $circuit_breaker_name","title_size":"16","title_align":"left","type":"query_value","requests":[{"response_format":"scalar","queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.failure.rate{$circuit_breaker_name}","aggregator":"last"}],"conditional_formats":[{"comparator":">","value":50,"palette":"white_on_red"},{"comparator":">=","value":40,"palette":"white_on_yellow"},{"comparator":"<","value":40,"palette":"white_on_green"}],"formulas":[{"formula":"default_zero(cutoff_min(query1, 0))"}]}],"autoscale":true,"precision":0,"timeseries_background":{"type":"area"}},"layout":{"x":0,"y":0,"width":6,"height":3}},{"id":5088831156945942,"definition":{"title":"Call rate: $circuit_breaker_name","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"},{"formula":"query2"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:resilience4j.circuitbreaker.calls.seconds.count{$service, $state}.as_rate()"},{"data_source":"metrics","name":"query2","query":"sum:resilience4j.circuitbreaker.calls.seconds.sum{$service, $state} by {service}.as_rate()"}],"response_format":"timeseries","style":{"palette":"dog_classic","order_by":"values","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":6,"y":0,"width":6,"height":3}},{"id":8277186327531272,"definition":{"title":"Buffered calls: $circuit_breaker_name","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.buffered.calls{$service, $circuit_breaker_name}"}],"response_format":"timeseries","style":{"palette":"dog_classic","order_by":"values","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":3,"width":6,"height":3}},{"id":8901593457473692,"definition":{"title":"Average call durations","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"per_minute(query1)"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:resilience4j.circuitbreaker.calls.seconds.sum{$service}.as_rate()"}],"response_format":"timeseries","style":{"palette":"dog_classic","order_by":"values","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":6,"y":3,"width":6,"height":3}}]},"layout":{"x":0,"y":0,"width":12,"height":7,"is_column_break":true}}],"template_variables":[{"name":"service","prefix":"service","available_values":[],"default":"*"},{"name":"state","prefix":"state","available_values":["closed","disabled","forced_open","half_open","metrics_only","open"],"default":"*"},{"name":"circuit_breaker_name","prefix":"circuit_breaker_name","available_values":[],"default":"*"}],"layout_type":"ordered","notify_list":[],"reflow_type":"fixed"}

resilience4j/assets/monitors/circuitbreaker_state_open.json

@@ -0,0 +1,38 @@
+{
+    "version": 2,
+    "created_at": "2025-01-24",
+    "last_updated_at": "2025-01-24",
+    "title": "Circuit Breaker State Alert",
+    "tags": [
+      "integration:resilience4j"
+    ],
+    "description": "This monitor alerts when the Circuit Breaker state change.",
+    "definition": {
+      "message": "The percentage of impacted services due to circuit breaker state is above 50%.\n\nService: {{name.name}}\n\nState: {{state.name}}",
+      "name": "[Resilience4j] Circuit Breaker State Alert for {{name.name}} with state {{state.name}}",
+      "options": {
+        "escalation_message": "The circuit breaker `{{name.name}}` has been `{{state.name}}` for more than **30 minutes**.",
+        "include_tags": true,
+        "new_group_delay": 300,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "renotify_interval": 30,
+        "renotify_statuses": [
+          "alert"
+        ],
+        "require_full_window": false,
+        "thresholds": {
+          "critical": 50,
+          "critical_recovery": 0,
+          "warning": 15,
+          "warning_recovery": 10
+        },
+        "timeout_h": 0
+      },
+      "query": "sum(last_5m):max:resilience4j.circuitbreaker.state{state IN (open,half_open,forced_open)} by {name,state} / max:kubernetes.pods.running{*} * 100 >= 50",
+      "tags": [
+        "integration:resilience4j"
+      ],
+      "type": "query alert"
+    }
+  }

resilience4j/assets/monitors/circuitbreaker_state_open_slow_calls.json

@@ -0,0 +1,32 @@
+{
+    "version": 2,
+    "created_at": "2025-01-24",
+    "last_updated_at": "2025-01-24",
+    "title": "Circuit Breaker State Alert with Slow Calls",
+    "tags": [
+      "integration:resilience4j"
+    ],
+    "description": "This monitor alerts when the Circuit Breaker state with slow calls.",
+    "definition": {
+      "message": "The percentage of slow calls for the circuit breaker {{name.name}} is above 85%.\n\nService: {{name.name}}\n\nState: {{state.name}}",
+      "name": "[Resilience4j] Circuit Breaker State Alert Slow Calls for {{name.name}}",
+      "options": {
+        "include_tags": true,
+        "locked": false,
+        "new_group_delay": 300,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "require_full_window": false,
+        "thresholds": {
+          "critical": 85,
+          "warning": 70
+        },
+        "evaluation_delay": 30
+      },
+      "query": "avg(last_5m):sum:resilience4j.circuitbreaker.slow.calls.count{*} by {name,state} / sum:resilience4j.circuitbreaker.calls.seconds.count{*} by {name,state} * 100 > 85",
+      "tags": [
+        "integration:resilience4j"
+      ],
+      "type": "query alert"
+    }
+  }

resilience4j/assets/service_checks.json

@@ -0,0 +1,17 @@
+[
+    {
+        "agent_version": "7.59.0",
+        "integration": "Resilience4j",
+        "check": "resilience4j.prometheus.health",
+        "statuses": [
+            "ok",
+            "critical"
+        ],
+        "groups": [
+            "host",
+            "endpoint"
+        ],
+        "name": "Resilience4j endpoint health",
+        "description": "Returns `CRITICAL` if the Agent is unable to connect to the Resilience4j endpoint, otherwise returns `OK`."
+    }
+]

resilience4j/datadog_checks/__init__.py

@@ -0,0 +1 @@
+__path__ = __import__('pkgutil').extend_path(__path__, __name__)  # type: ignore

resilience4j/datadog_checks/resilience4j/__about__.py

@@ -0,0 +1 @@
+__version__ = '1.0.0'

resilience4j/datadog_checks/resilience4j/__init__.py

@@ -0,0 +1,4 @@
+from .__about__ import __version__
+from .check import Resilience4jCheck
+
+__all__ = ['__version__', 'Resilience4jCheck']

resilience4j/datadog_checks/resilience4j/check.py

@@ -0,0 +1,39 @@
+from datadog_checks.base import ConfigurationError, OpenMetricsBaseCheck
+
+from .metrics import METRIC_MAP
+
+
+class Resilience4jCheck(OpenMetricsBaseCheck):
+    DEFAULT_METRIC_LIMIT = 0
+
+    def __init__(self, name, init_config, instances):
+        default_instances = {
+            'resilience4j': {
+                'metrics': [METRIC_MAP],
+                'send_distribution_sums_as_monotonic': 'true',
+                'send_distribution_counts_as_monotonic': 'true',
+            }
+        }
+
+        super(Resilience4jCheck, self).__init__(
+            name, init_config, instances, default_instances=default_instances, default_namespace='resilience4j'
+        )
+
+    def _http_check(self, url, check_name):
+        try:
+            response = self.http.get(url)
+            response.raise_for_status()
+        except Exception as e:
+            self.service_check(check_name, self.CRITICAL, message=str(e))
+        else:
+            if response.status_code == 200:
+                self.service_check(check_name, self.OK)
+            else:
+                self.service_check(check_name, self.WARNING)
+
+    def check(self, instance):
+        prometheus_url = instance.get("prometheus_url")
+        if prometheus_url is None:
+            raise ConfigurationError("Each instance must have a url to the metrics endpoint")
+
+        super(Resilience4jCheck, self).check(instance)

resilience4j/datadog_checks/resilience4j/config_models/__init__.py

@@ -0,0 +1,20 @@
+# This file is autogenerated.
+# To change this file you should edit assets/configuration/spec.yaml and then run the following commands:
+#     ddev -x validate config -s <INTEGRATION_NAME>
+#     ddev -x validate models -s <INTEGRATION_NAME>
+
+from .instance import InstanceConfig
+from .shared import SharedConfig
+
+
+class ConfigMixin:
+    _config_model_instance: InstanceConfig
+    _config_model_shared: SharedConfig
+
+    @property
+    def config(self) -> InstanceConfig:
+        return self._config_model_instance
+
+    @property
+    def shared_config(self) -> SharedConfig:
+        return self._config_model_shared

resilience4j/datadog_checks/resilience4j/config_models/defaults.py

@@ -0,0 +1,16 @@
+# This file is autogenerated.
+# To change this file you should edit assets/configuration/spec.yaml and then run the following commands:
+#     ddev -x validate config -s <INTEGRATION_NAME>
+#     ddev -x validate models -s <INTEGRATION_NAME>
+
+
+def instance_disable_generic_tags():
+    return False
+
+
+def instance_empty_default_hostname():
+    return False
+
+
+def instance_min_collection_interval():
+    return 15