Skip to content

config: update the self metrics after we switched to exporting using OTLP #73

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.

Sign up for GitHub

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

Open
ridwanmsharif wants to merge 1 commit into
base: main
Choose a base branch
from
Open

config: update the self metrics after we switched to exporting using OTLP #73

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
202 changes: 100 additions & 102 deletions config/collector.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,23 +28,21 @@ exporters:
auth:
authenticator: googleclientauth


extensions:
health_check:
endpoint: ${env:MY_POD_IP}:13133
googleclientauth:


processors:
filter/self-metrics:
metrics:
include:
match_type: strict
metric_names:
- otelcol_process_uptime
- otelcol_process_memory_rss
- otelcol_grpc_io_client_completed_rpcs
- otelcol_googlecloudmonitoring_point_count
- otelcol_process_uptime
- otelcol_process_memory_rss
- grpc.client.attempt.duration
- googlecloudmonitoring/point_count
batch:
send_batch_max_size: 200
send_batch_size: 200
Expand All @@ -53,27 +51,27 @@ processors:
k8sattributes:
extract:
metadata:
- k8s.namespace.name
- k8s.deployment.name
- k8s.statefulset.name
- k8s.daemonset.name
- k8s.cronjob.name
- k8s.job.name
- k8s.replicaset.name
- k8s.node.name
- k8s.pod.name
- k8s.pod.uid
- k8s.pod.start_time
- k8s.namespace.name
- k8s.deployment.name
- k8s.statefulset.name
- k8s.daemonset.name
- k8s.cronjob.name
- k8s.job.name
- k8s.replicaset.name
- k8s.node.name
- k8s.pod.name
- k8s.pod.uid
- k8s.pod.start_time
passthrough: false
pod_association:
- sources:
- from: resource_attribute
name: k8s.pod.ip
- sources:
- from: resource_attribute
name: k8s.pod.uid
- sources:
- from: connection
- sources:
- from: resource_attribute
name: k8s.pod.ip
- sources:
- from: resource_attribute
name: k8s.pod.uid
- sources:
- from: connection

memory_limiter:
check_interval: 1s
Expand All @@ -82,33 +80,33 @@ processors:

metricstransform/self-metrics:
transforms:
- action: update
include: otelcol_process_uptime
operations:
- action: add_label
new_label: version
new_value: Google-Cloud-OTLP manifests:0.4.0 OpenTelemetry Collector Built By Google/0.128.0 (linux/amd64)
- action: update
include: otelcol_process_uptime
operations:
- action: add_label
new_label: version
new_value: Google-Cloud-OTLP manifests:0.4.0 OpenTelemetry Collector Built By Google/0.128.0 (linux/amd64)

resourcedetection:
detectors: [gcp]
timeout: 10s

transform/collision:
metric_statements:
- context: datapoint
statements:
- set(attributes["exported_location"], attributes["location"])
- delete_key(attributes, "location")
- set(attributes["exported_cluster"], attributes["cluster"])
- delete_key(attributes, "cluster")
- set(attributes["exported_namespace"], attributes["namespace"])
- delete_key(attributes, "namespace")
- set(attributes["exported_job"], attributes["job"])
- delete_key(attributes, "job")
- set(attributes["exported_instance"], attributes["instance"])
- delete_key(attributes, "instance")
- set(attributes["exported_project_id"], attributes["project_id"])
- delete_key(attributes, "project_id")
- context: datapoint
statements:
- set(attributes["exported_location"], attributes["location"])
- delete_key(attributes, "location")
- set(attributes["exported_cluster"], attributes["cluster"])
- delete_key(attributes, "cluster")
- set(attributes["exported_namespace"], attributes["namespace"])
- delete_key(attributes, "namespace")
- set(attributes["exported_job"], attributes["job"])
- delete_key(attributes, "job")
- set(attributes["exported_instance"], attributes["instance"])
- delete_key(attributes, "instance")
- set(attributes["exported_project_id"], attributes["project_id"])
- delete_key(attributes, "project_id")

# The relative ordering of statements between ReplicaSet & Deployment and Job & CronJob are important.
# The ordering of these controllers is decided based on the k8s controller documentation available at
Expand All @@ -117,28 +115,28 @@ processors:
# create pods.
transform/aco-gke:
metric_statements:
- context: datapoint
statements:
- set(attributes["top_level_controller_type"], "ReplicaSet") where resource.attributes["k8s.replicaset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.replicaset.name"]) where resource.attributes["k8s.replicaset.name"] != nil
- set(attributes["top_level_controller_type"], "Deployment") where resource.attributes["k8s.deployment.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.deployment.name"]) where resource.attributes["k8s.deployment.name"] != nil
- set(attributes["top_level_controller_type"], "DaemonSet") where resource.attributes["k8s.daemonset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.daemonset.name"]) where resource.attributes["k8s.daemonset.name"] != nil
- set(attributes["top_level_controller_type"], "StatefulSet") where resource.attributes["k8s.statefulset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.statefulset.name"]) where resource.attributes["k8s.statefulset.name"] != nil
- set(attributes["top_level_controller_type"], "Job") where resource.attributes["k8s.job.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.job.name"]) where resource.attributes["k8s.job.name"] != nil
- set(attributes["top_level_controller_type"], "CronJob") where resource.attributes["k8s.cronjob.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.cronjob.name"]) where resource.attributes["k8s.cronjob.name"] != nil
- context: datapoint
statements:
- set(attributes["top_level_controller_type"], "ReplicaSet") where resource.attributes["k8s.replicaset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.replicaset.name"]) where resource.attributes["k8s.replicaset.name"] != nil
- set(attributes["top_level_controller_type"], "Deployment") where resource.attributes["k8s.deployment.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.deployment.name"]) where resource.attributes["k8s.deployment.name"] != nil
- set(attributes["top_level_controller_type"], "DaemonSet") where resource.attributes["k8s.daemonset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.daemonset.name"]) where resource.attributes["k8s.daemonset.name"] != nil
- set(attributes["top_level_controller_type"], "StatefulSet") where resource.attributes["k8s.statefulset.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.statefulset.name"]) where resource.attributes["k8s.statefulset.name"] != nil
- set(attributes["top_level_controller_type"], "Job") where resource.attributes["k8s.job.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.job.name"]) where resource.attributes["k8s.job.name"] != nil
- set(attributes["top_level_controller_type"], "CronJob") where resource.attributes["k8s.cronjob.name"] != nil
- set(attributes["top_level_controller_name"], resource.attributes["k8s.cronjob.name"]) where resource.attributes["k8s.cronjob.name"] != nil

# When sending telemetry to the GCP OTLP endpoint, the gcp.project_id resource attribute is required to be set to your project ID.
resource/gcp_project_id:
attributes:
- key: gcp.project_id
# MAKE SURE YOU REPLACE THIS WITH YOUR PROJECT ID
value: ${GOOGLE_CLOUD_PROJECT}
action: insert
- key: gcp.project_id
# MAKE SURE YOU REPLACE THIS WITH YOUR PROJECT ID
value: ${GOOGLE_CLOUD_PROJECT}
action: insert
# The metricstarttime processor is important to include if you are using the prometheus receiver to ensure the start time is set properly.
# It is a no-op otherwise.
metricstarttime:
Expand All @@ -153,8 +151,8 @@ receivers:
http:
cors:
allowed_origins:
- http://*
- https://*
- http://*
- https://*
endpoint: ${env:MY_POD_IP}:4318
otlp/self-metrics:
protocols:
Expand All @@ -163,62 +161,62 @@ receivers:

service:
extensions:
- health_check
- googleclientauth
- health_check
- googleclientauth
pipelines:
logs:
exporters:
- googlecloud
- googlecloud
processors:
- k8sattributes
- resourcedetection
- memory_limiter
- batch
- k8sattributes
- resourcedetection
- memory_limiter
- batch
receivers:
- otlp
- otlp
metrics/otlp:
exporters:
- googlemanagedprometheus
- googlemanagedprometheus
processors:
- k8sattributes
- memory_limiter
- metricstarttime
- resourcedetection
- transform/collision
- transform/aco-gke
- batch
- k8sattributes
- memory_limiter
- metricstarttime
- resourcedetection
- transform/collision
- transform/aco-gke
- batch
receivers:
- otlp
- otlp
metrics/self-metrics:
exporters:
- googlemanagedprometheus
- googlemanagedprometheus
processors:
- filter/self-metrics
- metricstransform/self-metrics
- k8sattributes
- memory_limiter
- resourcedetection
- batch
- filter/self-metrics
- metricstransform/self-metrics
- k8sattributes
- memory_limiter
- resourcedetection
- batch
receivers:
- otlp/self-metrics
- otlp/self-metrics
traces:
exporters:
- otlphttp
- otlphttp
processors:
- k8sattributes
- memory_limiter
- resource/gcp_project_id
- resourcedetection
- batch
- k8sattributes
- memory_limiter
- resource/gcp_project_id
- resourcedetection
- batch
receivers:
- otlp
- otlp
telemetry:
logs:
encoding: json
metrics:
readers:
- periodic:
exporter:
otlp:
protocol: grpc
endpoint: ${env:MY_POD_IP}:14317
- periodic:
exporter:
otlp:
protocol: grpc
endpoint: ${env:MY_POD_IP}:14317
Loading