Support ignoring instance tags

amazon_msk/datadog_checks/amazon_msk/data/conf.yaml.example

@@ -194,6 +194,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

azure_iot_edge/datadog_checks/azure_iot_edge/data/conf.yaml.example

@@ -162,6 +162,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

cilium/datadog_checks/cilium/data/conf.yaml.example

@@ -165,6 +165,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

cockroachdb/datadog_checks/cockroachdb/data/conf.yaml.example

@@ -157,6 +157,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

coredns/datadog_checks/coredns/data/conf.yaml.example

@@ -176,6 +176,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

crio/datadog_checks/crio/data/conf.yaml.example

@@ -157,6 +157,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

datadog_checks_base/datadog_checks/base/checks/openmetrics/mixins.py

@@ -318,6 +318,21 @@ def create_scraper_configuration(self, instance=None):
         # Custom tags that will be sent with each metric
         config['custom_tags'] = instance.get('tags', [])
 
+        # Some tags can be ignored to reduce the cardinality.
+        # This can be useful for cost optimization in containerized environments
+        # when the openmetrics check is configured to collect custom metrics.
+        # Even when the Agent's Tagger is configured to add low-cardinality tags only,
+        # some tags can still generate unwanted metric contexts (e.g pod annotations as tags).
+        ignore_tags = instance.get('ignore_tags', default_instance.get('ignore_tags', []))
+        if ignore_tags:
+            ignored_tag_patterns = set()
+            for ignored_tag in ignore_tags:
+                ignored_tag_patterns.add(translate(ignored_tag))
+
+            if ignored_tag_patterns:
+                ignored_tags_re = compile('|'.join(ignored_tag_patterns))
+                config['custom_tags'] = [tag for tag in config['custom_tags'] if not ignored_tags_re.search(tag)]
+
         # Additional tags to be sent with each metric
         config['_metric_tags'] = []
 

datadog_checks_base/datadog_checks/base/checks/openmetrics/v2/scraper.py

@@ -144,6 +144,21 @@ def __init__(self, check, config):
             if not isinstance(entry, str):
                 raise ConfigurationError(f'Entry #{i} of setting `tags` must be a string')
 
+        # Some tags can be ignored to reduce the cardinality.
+        # This can be useful for cost optimization in containerized environments
+        # when the openmetrics check is configured to collect custom metrics.
+        # Even when the Agent's Tagger is configured to add low-cardinality tags only,
+        # some tags can still generate unwanted metric contexts (e.g pod annotations as tags).
+        ignore_tags = config.get('ignore_tags', [])
+        if ignore_tags:
+            ignored_tag_patterns = set()
+            for ignored_tag in ignore_tags:
+                ignored_tag_patterns.add(fnmatch.translate(ignored_tag))
+
+            if ignored_tag_patterns:
+                ignored_tags_re = re.compile('|'.join(ignored_tag_patterns))
+                custom_tags = [tag for tag in custom_tags if not ignored_tags_re.search(tag)]
+
         # 16 KiB seems optimal, and is also the standard chunk size of the Bittorrent protocol:
         # https://www.bittorrent.org/beps/bep_0003.html
         self.request_size = int(float(config.get('request_size') or 16) * KIBIBYTE)

datadog_checks_base/tests/openmetrics/test_options.py

@@ -550,3 +550,25 @@ def test_excluded_metric(self, aggregator, dd_run_check, mock_http_response):
         )
 
         aggregator.assert_all_metrics_covered()
+
+
+class TestIgnoreTags:
+    def test(self, aggregator, dd_run_check, mock_http_response):
+        mock_http_response(
+            """
+            # HELP go_memstats_alloc_bytes Number of bytes allocated and still in use.
+            # TYPE go_memstats_alloc_bytes gauge
+            go_memstats_alloc_bytes 6.396288e+06
+            """
+        )
+
+        all_tags = ['foo', 'foofoo', 'bar', 'bar:baz']
+        ignored_tags = ['foo*', 'bar:baz']
+        check = get_check({'metrics': ['go_memstats_alloc_bytes'], 'tags': all_tags, 'ignore_tags': ignored_tags})
+        dd_run_check(check)
+
+        aggregator.assert_metric(
+            'test.go_memstats_alloc_bytes', 6396288, metric_type=aggregator.GAUGE, tags=['endpoint:test', 'bar']
+        )
+
+        aggregator.assert_all_metrics_covered()

datadog_checks_base/tests/test_openmetrics.py

@@ -2781,3 +2781,20 @@ def test_empty_namespace(aggregator, mocked_prometheus_check, text_data, ref_gau
     check.process_metric(ref_gauge, config)
 
     aggregator.assert_metric('process.vm.bytes', count=1)
+
+
+def test_ignore_tags(aggregator, mocked_prometheus_check, ref_gauge):
+    """
+    Test that tags matching ignored tag patterns are properly discarded.
+    """
+    check = mocked_prometheus_check
+    instance = copy.deepcopy(PROMETHEUS_CHECK_INSTANCE)
+    instance['tags'] = ['foo', 'foofoo', 'bar', 'bar:baz']
+    instance['ignore_tags'] = ['foo*', 'bar:baz']
+
+    config = check.get_scraper_config(instance)
+    config['_dry_run'] = False
+
+    check.process_metric(ref_gauge, config)
+
+    aggregator.assert_metric('prometheus.process.vm.bytes', tags=['bar'], count=1)

datadog_checks_dev/datadog_checks/dev/tooling/templates/configuration/instances/openmetrics.yaml

@@ -300,5 +300,16 @@
   value:
     example: false
     type: boolean
+- name: ignore_tags
+  description: A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+  value:
+    type: array
+    items:
+      type: string
+    example:
+      - <FULL:TAG>
+      - <TAG_PREFIX*>
+      - <*TAG_SUFFIX>
+      - <*SUBSTRING*>
 - template: instances/http
 - template: instances/default

datadog_checks_dev/datadog_checks/dev/tooling/templates/configuration/instances/openmetrics_legacy.yaml

@@ -167,5 +167,16 @@
     example:
       <KEY_1>: [<LABEL_1>, <LABEL_2>]
       <KEY_2>: ['*']
+- name: ignore_tags
+  description: A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+  value:
+    type: array
+    items:
+      type: string
+    example:
+      - <FULL:TAG>
+      - <TAG_PREFIX*>
+      - <*TAG_SUFFIX>
+      - <*SUBSTRING*>
 - template: instances/http
 - template: instances/default

etcd/datadog_checks/etcd/data/conf.yaml.example

@@ -163,6 +163,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

external_dns/datadog_checks/external_dns/data/conf.yaml.example

@@ -157,6 +157,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

gitlab/datadog_checks/gitlab/data/conf.yaml.example

@@ -127,6 +127,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

gitlab_runner/datadog_checks/gitlab_runner/data/conf.yaml.example

@@ -211,6 +211,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

haproxy/datadog_checks/haproxy/data/conf.yaml.example

@@ -304,6 +304,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

istio/datadog_checks/istio/data/conf.yaml.example

@@ -196,6 +196,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

kong/datadog_checks/kong/data/conf.yaml.example

@@ -237,6 +237,15 @@ instances:
     #
     # telemetry: false
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

kube_apiserver_metrics/datadog_checks/kube_apiserver_metrics/data/conf.yaml.example

@@ -164,6 +164,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

kube_scheduler/datadog_checks/kube_scheduler/data/conf.yaml.example

@@ -173,6 +173,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

linkerd/datadog_checks/linkerd/data/conf.yaml.example

@@ -157,6 +157,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##

nginx_ingress_controller/datadog_checks/nginx_ingress_controller/data/conf.yaml.example

@@ -165,6 +165,15 @@ instances:
     #   <KEY_2>:
     #   - '*'
 
+    ## @param ignore_tags - list of strings - optional
+    ## A list of tags to ignore, the "*" wildcard can be used to match multiple tag strings.
+    #
+    # ignore_tags:
+    #   - <FULL:TAG>
+    #   - <TAG_PREFIX*>
+    #   - <*TAG_SUFFIX>
+    #   - <*SUBSTRING*>
+
     ## @param proxy - mapping - optional
     ## This overrides the `proxy` setting in `init_config`.
     ##