Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[kube_apiserver_metrics] Rename aggregator_unavailable_apiservice name tag to apiservice_name (#14738) #14751

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
FROM datadog/agent:latest
# COPY datadog_checks_base/datadog_checks/base/checks/base.py /opt/datadog-agent/embedded/lib/python3.8/site-packages/datadog_checks/base/checks/base.py
COPY kubelet/datadog_checks/kubelet/kubelet.py /opt/datadog-agent/embedded/lib/python3.8/site-packages/datadog_checks/kubelet/kubelet.py
COPY kubelet/datadog_checks/kubelet/probes.py /opt/datadog-agent/embedded/lib/python3.8/site-packages/datadog_checks/kubelet/probes.py
COPY kubelet/datadog_checks/kubelet/prometheus.py /opt/datadog-agent/embedded/lib/python3.8/site-packages/datadog_checks/kubelet/prometheus.py
COPY kube_apiserver_metrics/datadog_checks/kube_apiserver_metrics/kube_apiserver_metrics.py /opt/datadog-agent/embedded/lib/python3.8/site-packages/datadog_checks/kube_apiserver_metrics/kube_apiserver_metrics.py

2 changes: 1 addition & 1 deletion kube_apiserver_metrics/assets/dashboards/overview.json
Original file line number Diff line number Diff line change
Expand Up @@ -380,7 +380,7 @@
{
"data_source": "metrics",
"name": "query1",
"query": "max:kube_apiserver.aggregator_unavailable_apiservice{$cluster,$scope} by {kube_namespace,name}",
"query": "max:kube_apiserver.aggregator_unavailable_apiservice{$cluster,$scope} by {kube_namespace, apiservice_name}",
"aggregator": "avg"
}
],
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,6 @@
# fmt: on
# For Kubernetes >= 1.14
# (https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.14.md#deprecated-metrics)
'aggregator_unavailable_apiservice': 'aggregator_unavailable_apiservice',
'rest_client_request_duration_seconds': 'rest_client_request_latency_seconds',
'apiserver_admission_webhook_admission_duration_seconds': 'admission_webhook_admission_latencies_seconds',
'apiserver_admission_step_admission_duration_seconds': 'admission_step_admission_latencies_seconds',
Expand Down Expand Up @@ -94,6 +93,7 @@ class KubeAPIServerMetricsCheck(OpenMetricsBaseCheck):
def __init__(self, name, init_config, instances=None):
# Set up metrics_transformers
self.metric_transformers = {
'aggregator_unavailable_apiservice': self.aggregator_unavailable_apiservice,
'apiserver_audit_event_total': self.apiserver_audit_event_total,
'rest_client_requests_total': self.rest_client_requests_total,
'apiserver_request_count': self.apiserver_request_count,
Expand Down Expand Up @@ -157,7 +157,7 @@ def _create_kube_apiserver_metrics_instance(self, instance):

return kube_apiserver_metrics_instance

def submit_as_gauge_and_monotonic_count(self, metric_suffix, metric, scraper_config):
def submit_metric(self, metric_suffix, metric, scraper_config, gauge=True, monotonic_count=True):
"""
submit a kube_apiserver_metrics metric both as a gauge (for compatibility) and as a monotonic_count
"""
Expand All @@ -168,34 +168,45 @@ def submit_as_gauge_and_monotonic_count(self, metric_suffix, metric, scraper_con

for label_name, label_value in iteritems(sample[self.SAMPLE_LABELS]):
_tags.append('{}:{}'.format(label_name, label_value))
# submit raw metric
self.gauge(metric_name, sample[self.SAMPLE_VALUE], _tags)
# submit rate metric
self.monotonic_count(metric_name + '.count', sample[self.SAMPLE_VALUE], _tags)
if gauge:
# submit raw metric
self.gauge(metric_name, sample[self.SAMPLE_VALUE], _tags)
if monotonic_count:
# submit rate metric
self.monotonic_count(metric_name + '.count', sample[self.SAMPLE_VALUE], _tags)

def aggregator_unavailable_apiservice(self, metric, scraper_config):
"""
This function replaces the tag "name" by "apiservice_name".
It assumes that every sample is tagged with `name`.
"""
for sample in metric.samples:
sample[self.SAMPLE_LABELS]["apiservice_name"] = sample[self.SAMPLE_LABELS].pop("name")
self.submit_metric('.aggregator_unavailable_apiservice', metric, scraper_config, monotonic_count=False)

def apiserver_audit_event_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.audit_event', metric, scraper_config)
self.submit_metric('.audit_event', metric, scraper_config)

def rest_client_requests_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.rest_client_requests_total', metric, scraper_config)
self.submit_metric('.rest_client_requests_total', metric, scraper_config)

def http_requests_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.http_requests_total', metric, scraper_config)
self.submit_metric('.http_requests_total', metric, scraper_config)

def apiserver_request_count(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.apiserver_request_count', metric, scraper_config)
self.submit_metric('.apiserver_request_count', metric, scraper_config)

def apiserver_dropped_requests_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.apiserver_dropped_requests_total', metric, scraper_config)
self.submit_metric('.apiserver_dropped_requests_total', metric, scraper_config)

def authenticated_user_requests(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.authenticated_user_requests', metric, scraper_config)
self.submit_metric('.authenticated_user_requests', metric, scraper_config)

def apiserver_request_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.apiserver_request_total', metric, scraper_config)
self.submit_metric('.apiserver_request_total', metric, scraper_config)

def apiserver_request_terminations_total(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.apiserver_request_terminations_total', metric, scraper_config)
self.submit_metric('.apiserver_request_terminations_total', metric, scraper_config)

def apiserver_admission_webhook_fail_open_count(self, metric, scraper_config):
self.submit_as_gauge_and_monotonic_count('.apiserver_admission_webhook_fail_open_count', metric, scraper_config)
self.submit_metric('.apiserver_admission_webhook_fail_open_count', metric, scraper_config)
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ class TestKubeAPIServerMetrics:
'aggregator_unavailable_apiservice',
'envelope_encryption_dek_cache_fill_percent',
]

COUNT_METRICS = [
'audit_event.count',
'rest_client_requests_total.count',
Expand All @@ -86,4 +87,6 @@ def test_check(self, dd_run_check, aggregator, mock_http_response):
metric_to_assert = NAMESPACE + "." + metric
aggregator.assert_metric(metric_to_assert)
aggregator.assert_metric_has_tag(metric_to_assert, customtag)
if "aggregator_unavailable_apiservice" in metric:
aggregator.assert_metric_has_tag(metric_to_assert, "apiservice_name:v1.")
aggregator.assert_all_metrics_covered()
Original file line number Diff line number Diff line change
Expand Up @@ -92,4 +92,6 @@ def test_check(self, dd_run_check, aggregator, mock_http_response):
metric_to_assert = NAMESPACE + "." + metric
aggregator.assert_metric(metric_to_assert)
aggregator.assert_metric_has_tag(metric_to_assert, customtag)
if "aggregator_unavailable_apiservice" in metric:
aggregator.assert_metric_has_tag(metric_to_assert, "apiservice_name:v1.")
aggregator.assert_all_metrics_covered()
Original file line number Diff line number Diff line change
Expand Up @@ -94,4 +94,6 @@ def test_check(self, dd_run_check, aggregator, mock_http_response):
metric_to_assert = NAMESPACE + "." + metric
aggregator.assert_metric(metric_to_assert)
aggregator.assert_metric_has_tag(metric_to_assert, customtag)
if "aggregator_unavailable_apiservice" in metric:
aggregator.assert_metric_has_tag(metric_to_assert, "apiservice_name:v1.")
aggregator.assert_all_metrics_covered()
Original file line number Diff line number Diff line change
Expand Up @@ -113,4 +113,6 @@ def test_check(self, dd_run_check, aggregator, mock_get):
for metric in self.METRICS + self.COUNT_METRICS:
aggregator.assert_metric(metric)
aggregator.assert_metric_has_tag(metric, customtag)
if "aggregator_unavailable_apiservice" in metric:
aggregator.assert_metric_has_tag(metric, "apiservice_name:v1.")
aggregator.assert_all_metrics_covered()
Original file line number Diff line number Diff line change
Expand Up @@ -90,4 +90,6 @@ def test_check(self, dd_run_check, aggregator, mock_http_response):
metric_to_assert = NAMESPACE + "." + metric
aggregator.assert_metric(metric_to_assert)
aggregator.assert_metric_has_tag(metric_to_assert, customtag)
if "aggregator_unavailable_apiservice" in metric:
aggregator.assert_metric_has_tag(metric_to_assert, "apiservice_name:v1.")
aggregator.assert_all_metrics_covered()