Skip to content
This repository was archived by the owner on Oct 17, 2024. It is now read-only.

Add manifests to enable metrics-collector running independently #36

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add manifests to enable metrics-collector running independently #36

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ad2dbd3
Add manifests to enable metrics-collector running independently
clyang82 Jun 11, 2021
43df1ed
submit template
clyang82 Jun 16, 2021
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
251 changes: 251 additions & 0 deletions manifests/metrics-collector-template.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,251 @@
---
apiVersion: v1
kind: Namespace
metadata:
name: standalone-metrics-collector
---
apiVersion: v1
kind: ConfigMap
metadata:
annotations:
service.alpha.openshift.io/inject-cabundle: "true"
name: metrics-collector-serving-certs-ca-bundle
namespace: standalone-metrics-collector
data:
service-ca.crt: ""
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: endpoint-observability-operator-sa
namespace: standalone-metrics-collector
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: standalone-metrics-collector
subjects:
- kind: ServiceAccount
name: endpoint-observability-operator-sa
namespace: standalone-metrics-collector
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: cluster-monitoring-view
---
apiVersion: v1
kind: Secret
metadata:
name: observability-managed-cluster-certs
namespace: standalone-metrics-collector
data:
ca.crt:
${CA_CRT}
tls.crt:
${TLS_CRT}
tls.key:
${TLS_KEY}
type: Opaque
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: standalone-metrics-collector
namespace: standalone-metrics-collector
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
component: standalone-metrics-collector
strategy:
rollingUpdate:
maxSurge: 25%
maxUnavailable: 25%
type: RollingUpdate
template:
metadata:
creationTimestamp: null
labels:
component: standalone-metrics-collector
spec:
containers:
- command:
- /usr/bin/telemeter-client
- --from=$(FROM)
- --to-upload=$(TO)
- --from-ca-file=/etc/serving-certs-ca-bundle/service-ca.crt
- --from-token-file=/var/run/secrets/kubernetes.io/serviceaccount/token
- --interval=60s
- --label="cluster=${CLUSTER_NAME}"
- --label="clusterID=${CLUSTER_ID}"
- --limit-bytes=1073741824
- --match={__name__=":node_memory_MemAvailable_bytes:sum"}
- --match={__name__="ALERTS"}
- --match={__name__="apiserver_request_count"}
- --match={__name__="apiserver_request_latencies_summary_count"}
- --match={__name__="apiserver_request_latencies_summary_sum"}
- --match={__name__="authenticated_user_requests"}
- --match={__name__="authentication_attempts"}
- --match={__name__="cluster:capacity_cpu_cores:sum"}
- --match={__name__="cluster:capacity_memory_bytes:sum"}
- --match={__name__="cluster:container_cpu_usage:ratio"}
- --match={__name__="cluster:container_spec_cpu_shares:ratio"}
- --match={__name__="cluster:cpu_usage_cores:sum"}
- --match={__name__="cluster:memory_usage:ratio"}
- --match={__name__="cluster:memory_usage_bytes:sum"}
- --match={__name__="cluster:usage:resources:sum"}
- --match={__name__="cluster_infrastructure_provider"}
- --match={__name__="cluster_version"}
- --match={__name__="cluster_version_payload"}
- --match={__name__="container_cpu_cfs_periods_total"}
- --match={__name__="container_cpu_cfs_throttled_periods_total"}
- --match={__name__="container_spec_cpu_quota"}
- --match={__name__="coredns_dns_request_count_total"}
- --match={__name__="coredns_dns_request_duration_seconds_sum"}
- --match={__name__="coredns_dns_request_type_count_total"}
- --match={__name__="coredns_dns_response_rcode_count_total"}
- --match={__name__="etcd_debugging_mvcc_db_total_size_in_bytes"}
- --match={__name__="etcd_debugging_snap_save_total_duration_seconds_sum"}
- --match={__name__="etcd_disk_backend_commit_duration_seconds_bucket"}
- --match={__name__="etcd_disk_backend_commit_duration_seconds_sum"}
- --match={__name__="etcd_disk_wal_fsync_duration_seconds_bucket"}
- --match={__name__="etcd_disk_wal_fsync_duration_seconds_sum"}
- --match={__name__="etcd_object_counts"}
- --match={__name__="etcd_network_client_grpc_received_bytes_total"}
- --match={__name__="etcd_network_client_grpc_sent_bytes_total"}
- --match={__name__="etcd_network_peer_received_bytes_total"}
- --match={__name__="etcd_network_peer_sent_bytes_total"}
- --match={__name__="etcd_server_client_requests_total"}
- --match={__name__="etcd_server_has_leader"}
- --match={__name__="etcd_server_health_failures"}
- --match={__name__="etcd_server_leader_changes_seen_total"}
- --match={__name__="etcd_server_proposals_failed_total"}
- --match={__name__="etcd_server_proposals_pending"}
- --match={__name__="etcd_server_proposals_committed_total"}
- --match={__name__="etcd_server_proposals_applied_total"}
- --match={__name__="etcd_server_quota_backend_bytes"}
- --match={__name__="grpc_server_started_total"}
- --match={__name__="haproxy_backend_connection_errors_total"}
- --match={__name__="haproxy_backend_connections_total"}
- --match={__name__="haproxy_backend_current_queue"}
- --match={__name__="haproxy_backend_http_average_response_latency_milliseconds"}
- --match={__name__="haproxy_backend_max_sessions"}
- --match={__name__="haproxy_backend_response_errors_total"}
- --match={__name__="haproxy_backend_up"}
- --match={__name__="http_requests_total"}
- --match={__name__="instance:node_filesystem_usage:sum"}
- --match={__name__="instance:node_cpu_utilisation:rate1m"}
- --match={__name__="instance:node_load1_per_cpu:ratio"}
- --match={__name__="instance:node_memory_utilisation:ratio"}
- --match={__name__="instance:node_network_receive_bytes_excluding_lo:rate1m"}
- --match={__name__="instance:node_network_receive_drop_excluding_lo:rate1m"}
- --match={__name__="instance:node_network_transmit_bytes_excluding_lo:rate1m"}
- --match={__name__="instance:node_network_transmit_drop_excluding_lo:rate1m"}
- --match={__name__="instance:node_num_cpu:sum"}
- --match={__name__="instance:node_vmstat_pgmajfault:rate1m"}
- --match={__name__="instance_device:node_disk_io_time_seconds:rate1m"}
- --match={__name__="instance_device:node_disk_io_time_weighted_seconds:rate1m"}
- --match={__name__="kube_daemonset_status_desired_number_scheduled"}
- --match={__name__="kube_daemonset_status_number_unavailable"}
- --match={__name__="kube_node_spec_unschedulable"}
- --match={__name__="kube_node_status_allocatable"}
- --match={__name__="kube_node_status_allocatable_cpu_cores"}
- --match={__name__="kube_node_status_allocatable_memory_bytes"}
- --match={__name__="kube_node_status_capacity"}
- --match={__name__="kube_node_status_capacity_pods"}
- --match={__name__="kube_node_status_capacity_cpu_cores"}
- --match={__name__="kube_node_status_condition"}
- --match={__name__="kube_pod_container_resource_limits"}
- --match={__name__="kube_pod_container_resource_limits_cpu_cores"}
- --match={__name__="kube_pod_container_resource_limits_memory_bytes"}
- --match={__name__="kube_pod_container_resource_requests"}
- --match={__name__="kube_pod_container_resource_requests_cpu_cores"}
- --match={__name__="kube_pod_container_resource_requests_memory_bytes"}
- --match={__name__="kube_pod_info"}
- --match={__name__="kube_pod_owner"}
- --match={__name__="kube_resourcequota"}
- --match={__name__="kubelet_running_container_count"}
- --match={__name__="kubelet_runtime_operations"}
- --match={__name__="kubelet_runtime_operations_latency_microseconds"}
- --match={__name__="kubelet_volume_stats_available_bytes"}
- --match={__name__="kubelet_volume_stats_capacity_bytes"}
- --match={__name__="kube_persistentvolume_status_phase"}
- --match={__name__="machine_cpu_cores"}
- --match={__name__="machine_memory_bytes"}
- --match={__name__="mixin_pod_workload"}
- --match={__name__="namespace:kube_pod_container_resource_requests_cpu_cores:sum"}
- --match={__name__="namespace:kube_pod_container_resource_requests_memory_bytes:sum"}
- --match={__name__="namespace:container_memory_usage_bytes:sum"}
- --match={__name__="namespace_cpu:kube_pod_container_resource_requests:sum"}
- --match={__name__="namespace_workload_pod:kube_pod_owner:relabel"}
- --match={__name__="node_cpu_seconds_total"}
- --match={__name__="node_filesystem_avail_bytes"}
- --match={__name__="node_filesystem_free_bytes"}
- --match={__name__="node_filesystem_size_bytes"}
- --match={__name__="node_memory_MemAvailable_bytes"}
- --match={__name__="node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate"}
- --match={__name__="node_netstat_Tcp_OutSegs"}
- --match={__name__="node_netstat_Tcp_RetransSegs"}
- --match={__name__="node_netstat_TcpExt_TCPSynRetrans"}
- --match={__name__="up"}
- --match={__name__="cluster_monitoring_operator_reconcile_errors_total"}
- --match={__name__="cluster_monitoring_operator_reconcile_attempts_total"}
- --match={__name__="cluster_operator_conditions"}
- --match={__name__="cluster_operator_up"}
- --match={__name__="workqueue_queue_duration_seconds_bucket",job="apiserver"}
- --match={__name__="workqueue_adds_total",job="apiserver"}
- --match={__name__="workqueue_depth",job="apiserver"}
- --match={__name__="go_goroutines",job="apiserver"}
- --match={__name__="process_cpu_seconds_total",job="apiserver"}
- --match={__name__="process_resident_memory_bytes",job="apiserver"}
- --match={__name__="container_memory_cache",container!=""}
- --match={__name__="container_memory_rss",container!=""}
- --match={__name__="container_memory_swap",container!=""}
- --match={__name__="container_memory_working_set_bytes",container!=""}
- --rename="mixin_pod_workload=namespace_workload_pod:kube_pod_owner:relabel"
- --rename="namespace:kube_pod_container_resource_requests_cpu_cores:sum=namespace_cpu:kube_pod_container_resource_requests:sum"
- --recordingrule={"name":"apiserver_request_duration_seconds:histogram_quantile_99","query":"histogram_quantile(0.99,sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", verb!=\"WATCH\"}[5m])) by (verb,le))"}
- --recordingrule={"name":"apiserver_request_duration_seconds:histogram_quantile_99:instance","query":"histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", verb!=\"WATCH\"}[5m])) by (le, instance))"}
- --recordingrule={"name":"sum:apiserver_request_total:1h","query":"sum(rate(apiserver_request_total{job=\"apiserver\"}[1h])) by(code, instance)"}
- --recordingrule={"name":"sum:apiserver_request_total:5m","query":"sum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by(code, instance)"}
- --recordingrule={"name":"rpc_rate:grpc_server_handled_total:sum_rate","query":"sum(rate(grpc_server_handled_total{job=\"etcd\",grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))"}
- --recordingrule={"name":"active_streams_watch:grpc_server_handled_total:sum","query":"sum(grpc_server_started_total{job=\"etcd\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"etcd\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})"}
- --recordingrule={"name":"active_streams_lease:grpc_server_handled_total:sum","query":"sum(grpc_server_started_total{job=\"etcd\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"etcd\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})"}
env:
- name: FROM
value: https://prometheus-k8s.openshift-monitoring.svc:9091
- name: TO
value: ${OBSERVATORIUM_RECEIVER_URL}
- name: STANDALONE
value: "true"
image: ${METRICS_COLLECTOR_IMAGE}
imagePullPolicy: Always
name: metrics-collector
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /tlscerts/ca
name: observability-managed-cluster-certs
- mountPath: /tlscerts/certs
name: observability-managed-cluster-certs
- mountPath: /etc/serving-certs-ca-bundle
name: serving-certs-ca-bundle
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
serviceAccount: endpoint-observability-operator-sa
serviceAccountName: endpoint-observability-operator-sa
terminationGracePeriodSeconds: 30
volumes:
- name: observability-managed-cluster-certs
secret:
defaultMode: 420
secretName: observability-managed-cluster-certs
- configMap:
defaultMode: 420
name: metrics-collector-serving-certs-ca-bundle
name: serving-certs-ca-bundle