[Karpenter Integration]: add missed metrics based on karpenter v1.4 documentations

karpenter/changelog.d/20110.added

@@ -0,0 +1 @@
+add missed karpenter v1.4 metrics

karpenter/datadog_checks/karpenter/metrics.py

@@ -9,13 +9,20 @@
 # https://karpenter.sh/docs/reference/metrics/
 
 METRIC_MAP = {
+    'aws_sdk_go_request': 'aws.sdk_go.request',
+    'aws_sdk_go_request_retry': 'aws.sdk_go.request.retry',
+    'aws_sdk_go_request_duration_seconds': 'aws.sdk_go.request.duration_seconds',
+    'aws_sdk_go_request_attempt': 'aws.sdk_go.request_attempt',
+    'aws_sdk_go_request_attempt_duration_seconds': 'aws.sdk_go.request_attempt.duration_seconds',
     'certwatcher_read_certificate': 'certwatcher.read.certificate',
     'certwatcher_read_certificate_errors': 'certwatcher.read.certificate.errors',
     'controller_runtime_active_workers': 'controller.runtime.active_workers',
     'controller_runtime_max_concurrent_reconciles': 'controller.runtime.max.concurrent_reconciles',
     'controller_runtime_reconcile': 'controller.runtime.reconcile',
     'controller_runtime_reconcile_errors': 'controller.runtime.reconcile_errors',
+    'controller_runtime_reconcile_panics': 'controller.runtime.reconcile_panics',
     'controller_runtime_reconcile_time_seconds': 'controller.runtime.reconcile.time_seconds',
+    'controller_runtime_terminal_reconcile_errors': 'controller.runtime.terminal.reconcile.errors',
     'go_gc_duration_seconds': 'go.gc.duration_seconds',
     'go_goroutines': 'go_goroutines',
     'go_info': 'go_info',
@@ -69,6 +76,7 @@
     'karpenter_disruption_queue_depth': 'disruption.queue_depth',
     'karpenter_disruption_pods_disrupted': 'disruption.pods.disrupted',
     'karpenter_disruption_nodes_disrupted': 'disruption.nodes.disrupted',
+    'karpenter_ignored_pod_count': 'ignored_pod_count',
     'karpenter_interruption_actions_performed': 'interruption.actions_performed',
     'karpenter_interruption_deleted_messages': 'interruption.deleted_messages',
     'karpenter_interruption_message_latency_time_seconds': 'interruption.message.latency.time_seconds',
@@ -84,9 +92,11 @@
     'karpenter_nodeclaims_disrupted': 'nodeclaims_disrupted',
     'karpenter_nodeclaims_drifted': 'nodeclaims_drifted',
     'karpenter_nodeclaims_initialized': 'nodeclaims_initialized',
+    'karpenter_nodeclaims_instance_termination_duration_seconds': 'nodeclaims_instance_termination.duration_seconds',
     'karpenter_nodeclaims_launched': 'nodeclaims_launched',
     'karpenter_nodeclaims_registered': 'nodeclaims_registered',
     'karpenter_nodeclaims_terminated': 'nodeclaims_terminated',
+    'karpenter_nodeclaims_termination_duration_seconds': 'nodeclaims_termination.duration_seconds',
     'karpenter_nodepool_limit': 'nodepool_limit',
     'karpenter_nodepool_usage': 'nodepool_usage',
     'karpenter_nodes_allocatable': 'nodes.allocatable',
@@ -109,8 +119,11 @@
     'karpenter_provisioner_usage': 'provisioner.usage',
     'karpenter_provisioner_usage_pct': 'provisioner.usage.pct',
     'karpenter_cluster_state_synced': 'cluster_state.synced',
+    'karpenter_cluster_state_unsynced_time_seconds': 'cluster_state.unsynced.time_seconds',
     'karpenter_cluster_state_node_count': 'cluster_state.node_count',
+    'karpenter_cluster_utilization_percent': 'cluster.utilization.percent',
     'leader_election_master_status': 'leader_election.master_status',
+    'leader_election_slowpath': 'leader_election.slowpath',
     'process_cpu_seconds': 'process.cpu_seconds',
     'process_max_fds': 'process.max_fds',
     'process_open_fds': 'process.open_fds',
@@ -140,6 +153,23 @@
     'karpenter_interruption_message_queue_duration_seconds': 'interruption.message.latency.time_seconds',
     'karpenter_nodepools_usage': 'nodepool_usage',
     'karpenter_nodepools_limit': 'nodepool_limit',
+    'operator_ec2nodeclass_status_condition_transitions': 'operator.ec2nodeclass.status_condition.transitions',
+    'operator_ec2nodeclass_status_condition_current_status_seconds': 'operator.ec2nodeclass.status_condition.current_status.seconds',
+    'operator_ec2nodeclass_status_condition_count': 'operator.ec2nodeclass.status_condition_count',
+    'operator_node_event_count': 'operator.node.event_count',
+    'operator_node_status_condition_transitions': 'operator.node.status_condition.transitions',
+    'operator_node_status_condition_transition_seconds': 'operator.node.status_condition.transitions.seconds',
+    'operator_node_status_condition_current_status_seconds': 'operator.node.status_condition.current_status.seconds',
+    'operator_node_status_condition_count': 'operator.node.status_condition_count',
+    'operator_node_termination_duration_seconds': 'operator.node.termination.duration_seconds',
+    'operator_nodeclaim_status_condition_transitions': 'operator.nodeclaim.status_condition.transitions',
+    'operator_nodeclaim_status_condition_transition_seconds': 'operator.nodeclaim.status_condition.transitions.seconds',
+    'operator_nodeclaim_status_condition_current_status_seconds': 'operator.nodeclaim.status_condition.current_status.seconds',
+    'operator_nodeclaim_status_condition_count': 'operator.nodeclaim.status_condition_count',
+    'operator_nodeclaim_termination_duration_seconds': 'operator.nodeclaim.termination.duration_seconds',
+    'operator_nodepool_status_condition_transitions': 'operator.nodepool.status_condition.transitions',
+    'operator_nodepool_status_condition_current_status_seconds': 'operator.nodepool.status_condition.current_status.seconds',
+    'operator_nodepool_status_condition_count': 'operator.nodepool.status_condition_count',
 }
 
 RENAME_LABELS_MAP = {

karpenter/metadata.csv

@@ -1,4 +1,12 @@
 metric_name,metric_type,interval,unit_name,per_unit_name,description,orientation,integration,short_name,curated_metric,sample_tags
+karpenter.aws.sdk_go.request.count,count,,,,The total number of AWS SDK Go requests,0,karpenter,,,
+karpenter.aws.sdk_go.request.duration_seconds.bucket,count,,,,Latency of AWS SDK Go requests histogram buckets,0,karpenter,,,
+karpenter.aws.sdk_go.request.duration_seconds.count,count,,,,Count of AWS SDK Go request durations,0,karpenter,,,
+karpenter.aws.sdk_go.request.duration_seconds.sum,count,,second,,Sum of AWS SDK Go request durations,0,karpenter,,,
+karpenter.aws.sdk_go.request_attempt.count,count,,,,The total number of AWS SDK Go request attempts,0,karpenter,,,
+karpenter.aws.sdk_go.request_attempt.duration_seconds.bucket,count,,second,,Latency of AWS SDK Go request attempts histogram buckets,0,karpenter,,,
+karpenter.aws.sdk_go.request_attempt.duration_seconds.count,count,,request,,Count of AWS SDK Go request attempt durations,0,karpenter,,,
+karpenter.aws.sdk_go.request_attempt.duration_seconds.sum,count,,second,,Sum of AWS SDK Go request attempt durations,0,karpenter,,,
 karpenter.build_info,gauge,,,,A metric with a constant '1' value labeled by version from which Karpenter was built.,0,karpenter,,,
 karpenter.certwatcher.read.certificate.count,count,,read,,The count of certificate reads,0,karpenter,,,
 karpenter.certwatcher.read.certificate.errors.count,count,,error,,The count of certificate read errors,0,karpenter,,,
@@ -16,8 +24,10 @@ karpenter.cloudprovider.instance.type.cpu_cores,gauge,,core,,VCPUs cores for a g
 karpenter.cloudprovider.instance.type.memory_bytes,gauge,,byte,,"Memory, in bytes, for a given instance type",0,karpenter,,,
 karpenter.cloudprovider.instance.type.offering_available,gauge,,,,"Instance type offering availability, based on instance type, capacity type, and zone",0,karpenter,,,
 karpenter.cloudprovider.instance.type.price_estimate,gauge,,,,Estimated hourly price used when making informed decisions on node cost calculation. This is updated once on startup and then every 12 hours,0,karpenter,,,
+karpenter.cluster.utilization.percent,gauge,,percent,,Utilization of allocatable resources by pod requests,0,karpenter,,,
 karpenter.cluster_state.node_count,gauge,,node,,Current count of nodes in cluster state.,0,karpenter,,,
 karpenter.cluster_state.synced,gauge,,,,Returns 1 if cluster state is synced and 0 otherwise. Synced checks that nodeclaims and nodes that are stored in the APIServer have the same representation as Karpenter's cluster state,0,karpenter,,,
+karpenter.cluster_state.unsynced.time_seconds,gauge,,second,,The time for which cluster state is not synced,0,karpenter,,,
 karpenter.consistency.errors,gauge,,error,,Number of consistency checks that have failed,0,karpenter,,,
 karpenter.controller.runtime.active_workers,gauge,,worker,,Number of currently used workers per controller,0,karpenter,,,
 karpenter.controller.runtime.max.concurrent_reconciles,gauge,,,,Maximum number of concurrent reconciles per controller,0,karpenter,,,
@@ -26,6 +36,8 @@ karpenter.controller.runtime.reconcile.time_seconds.bucket,count,,,,The count of
 karpenter.controller.runtime.reconcile.time_seconds.count,count,,,,The count of observations in the reconciliation per controller histogram,0,karpenter,,,
 karpenter.controller.runtime.reconcile.time_seconds.sum,count,,second,,The sum of time per reconciliation per controller,0,karpenter,,,
 karpenter.controller.runtime.reconcile_errors.count,count,,error,,The count of reconciliation errors per controller,0,karpenter,,,
+karpenter.controller.runtime.reconcile_panics.count,count,,,,Total number of reconciliation panics per controller,0,karpenter,,,
+karpenter.controller.runtime.terminal.reconcile.errors.count,count,,,,Total number of terminal reconciliation errors per controller,0,karpenter,,,
 karpenter.deprovisioning.actions_performed.count,count,,execution,,The count of deprovisioning actions performed. Labeled by deprovisioner,0,karpenter,,,
 karpenter.deprovisioning.consolidation_timeouts,gauge,,timeout,,Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type,0,karpenter,,,
 karpenter.deprovisioning.eligible_machines,gauge,,,,Number of machines eligible for deprovisioning by Karpenter. Labeled by deprovisioner,0,karpenter,,,
@@ -97,9 +109,15 @@ karpenter.nodeclaims_created,gauge,,,,Number of nodeclaims created in total by K
 karpenter.nodeclaims_disrupted,gauge,,,,Number of nodeclaims disrupted in total by Karpenter. Labeled by disruption type of the nodeclaim and the owning nodepool,0,karpenter,,,
 karpenter.nodeclaims_drifted,gauge,,,,Number of nodeclaims drifted reasons in total by Karpenter. Labeled by drift type of the nodeclaim and the owning nodepool,0,karpenter,,,
 karpenter.nodeclaims_initialized,gauge,,,,Number of nodeclaims initialized in total by Karpenter. Labeled by the owning nodepool,0,karpenter,,,
+karpenter.nodeclaims_instance_termination.duration_seconds.bucket,count,,,,Histogram buckets for CloudProvider Instance termination duration,0,karpenter,,,
+karpenter.nodeclaims_instance_termination.duration_seconds.count,count,,,,Count of CloudProvider Instance termination observations,0,karpenter,,,
+karpenter.nodeclaims_instance_termination.duration_seconds.sum,count,,second,,Sum of CloudProvider Instance termination durations,0,karpenter,,,
 karpenter.nodeclaims_launched,gauge,,,,Number of nodeclaims launched in total by Karpenter. Labeled by the owning nodepool,0,karpenter,,,
 karpenter.nodeclaims_registered,gauge,,,,Number of nodeclaims registered in total by Karpenter. Labeled by the owning nodepool,0,karpenter,,,
 karpenter.nodeclaims_terminated,gauge,,,,Number of nodeclaims terminated in total by Karpenter. Labeled by reason the nodeclaim was terminated and the owning nodepool,0,karpenter,,,
+karpenter.nodeclaims_termination.duration_seconds.bucket,count,,,,Histogram buckets for NodeClaim termination duration,0,karpenter,,,
+karpenter.nodeclaims_termination.duration_seconds.count,count,,,,Count of NodeClaim termination duration observations,0,karpenter,,,
+karpenter.nodeclaims_termination.duration_seconds.sum,count,,second,,Sum of NodeClaim termination durations,0,karpenter,,,
 karpenter.nodepool_limit,gauge,,,,The nodepool limits are the limits specified on the provisioner that restrict the quantity of resources provisioned. Labeled by nodepool name and resource type,0,karpenter,,,
 karpenter.nodepool_usage,gauge,,,,The nodepool usage is the amount of resources that have been provisioned by a particular nodepool. Labeled by nodepool name and resource type,0,karpenter,,,
 karpenter.nodes.allocatable,gauge,,,,The amount of resources allocatable by nodes,0,karpenter,,,
@@ -115,6 +133,22 @@ karpenter.nodes.total.daemon_limits,gauge,,,,Total resources specified by Daemon
 karpenter.nodes.total.daemon_requests,gauge,,,,Total resources requested by DaemonSet pods,0,karpenter,,,
 karpenter.nodes.total.pod_limits,gauge,,,,Total pod resources specified by non-DaemonSet pod limits,0,karpenter,,,
 karpenter.nodes.total.pod_requests,gauge,,,,Total pod resources requested by non-DaemonSet pods bound,0,karpenter,,,
+karpenter.operator.ec2nodeclass.status_condition.current_status.seconds,gauge,,second,,Time current status condition has been active for ec2nodeclass,0,karpenter,,,
+karpenter.operator.ec2nodeclass.status_condition.transitions.count,count,,,,Count of status condition transitions for ec2nodeclass,0,karpenter,,,
+karpenter.operator.ec2nodeclass.status_condition_count,gauge,,,,Number of conditions for ec2nodeclass,0,karpenter,,,
+karpenter.operator.node.status_condition.current_status.seconds,gauge,,second,,Time current status condition has been active for node,0,karpenter,,,
+karpenter.operator.node.status_condition.transitions.count,count,,,,Count of status condition transitions for node,0,karpenter,,,
+karpenter.operator.node.status_condition.transitions.seconds.bucket,count,,second,,Histogram of condition state durations for node,0,karpenter,,,
+karpenter.operator.node.status_condition_count,gauge,,,,Number of conditions for node,0,karpenter,,,
+karpenter.operator.node.termination.duration_seconds.bucket,count,,second,,Histogram buckets for node termination durations,0,karpenter,,,
+karpenter.operator.nodeclaim.status_condition.current_status.seconds,gauge,,second,,Time current status condition has been active for nodeclaim,0,karpenter,,,
+karpenter.operator.nodeclaim.status_condition.transitions.count,count,,,,Count of status condition transitions for nodeclaim,0,karpenter,,,
+karpenter.operator.nodeclaim.status_condition.transitions.seconds.bucket,count,,second,,Histogram of condition state durations for nodeclaim,0,karpenter,,,
+karpenter.operator.nodeclaim.status_condition_count,gauge,,,,Number of conditions for nodeclaim,0,karpenter,,,
+karpenter.operator.nodeclaim.termination.duration_seconds.bucket,count,,,,Histogram buckets for nodeclaim termination durations,0,karpenter,,,
+karpenter.operator.nodepool.status_condition.current_status.seconds,gauge,,second,,Time current status condition has been active for nodepool,0,karpenter,,,
+karpenter.operator.nodepool.status_condition.transitions.count,count,,,,Count of status condition transitions for nodepool,0,karpenter,,,
+karpenter.operator.nodepool.status_condition_count,gauge,,,,Number of conditions for nodepool,0,karpenter,,,
 karpenter.pods.startup.time_seconds.count,count,,,,The count of the observations in the pod startup summary,0,karpenter,,,
 karpenter.pods.startup.time_seconds.quantile,gauge,,,,The time taken between pod creation and the pod being in a running state by `quantile`,0,karpenter,,,
 karpenter.pods.startup.time_seconds.sum,count,,second,,The sum of the time from pod creation and the pod being in a running state,0,karpenter,,,

karpenter/tests/common.py

@@ -179,6 +179,40 @@ def get_fixture_path(filename):
     'karpenter.interruption.message.latency.time_seconds.bucket',
     'karpenter.nodepool_usage',
     'karpenter.nodepool_limit',
+    'karpenter.aws.sdk_go.request.count',
+    'karpenter.aws.sdk_go.request.duration_seconds.bucket',
+    'karpenter.aws.sdk_go.request.duration_seconds.count',
+    'karpenter.aws.sdk_go.request.duration_seconds.sum',
+    'karpenter.aws.sdk_go.request_attempt.count',
+    'karpenter.aws.sdk_go.request_attempt.duration_seconds.bucket',
+    'karpenter.aws.sdk_go.request_attempt.duration_seconds.count',
+    'karpenter.aws.sdk_go.request_attempt.duration_seconds.sum',
+    'karpenter.cluster.utilization.percent',
+    'karpenter.cluster_state.unsynced.time_seconds',
+    'karpenter.controller.runtime.reconcile_panics.count',
+    'karpenter.controller.runtime.terminal.reconcile.errors.count',
+    'karpenter.nodeclaims_instance_termination.duration_seconds.bucket',
+    'karpenter.nodeclaims_instance_termination.duration_seconds.count',
+    'karpenter.nodeclaims_instance_termination.duration_seconds.sum',
+    'karpenter.nodeclaims_termination.duration_seconds.bucket',
+    'karpenter.nodeclaims_termination.duration_seconds.count',
+    'karpenter.nodeclaims_termination.duration_seconds.sum',
+    'karpenter.operator.ec2nodeclass.status_condition.current_status.seconds',
+    'karpenter.operator.ec2nodeclass.status_condition.transitions.count',
+    'karpenter.operator.ec2nodeclass.status_condition_count',
+    'karpenter.operator.node.status_condition.current_status.seconds',
+    'karpenter.operator.node.status_condition.transitions.count',
+    'karpenter.operator.node.status_condition.transitions.seconds.bucket',
+    'karpenter.operator.node.status_condition_count',
+    'karpenter.operator.node.termination.duration_seconds.bucket',
+    'karpenter.operator.nodeclaim.status_condition.current_status.seconds',
+    'karpenter.operator.nodeclaim.status_condition.transitions.count',
+    'karpenter.operator.nodeclaim.status_condition.transitions.seconds.bucket',
+    'karpenter.operator.nodeclaim.status_condition_count',
+    'karpenter.operator.nodeclaim.termination.duration_seconds.bucket',
+    'karpenter.operator.nodepool.status_condition.current_status.seconds',
+    'karpenter.operator.nodepool.status_condition.transitions.count',
+    'karpenter.operator.nodepool.status_condition_count',
 ]
 RENAMED_LABELS = [
     'go_version:go1.20.6',