Monitoring

# There is no GA gcloud command to list or read metrics — use the REST API
# (or Metrics Explorer in the Console).

# List metric descriptors
curl -s -G -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  "https://monitoring.googleapis.com/v3/projects/my-project/metricDescriptors" \
  --data-urlencode 'filter=metric.type = starts_with("compute.googleapis.com")'

# Read time series (CPU utilization for one VM, 5-minute window)
curl -s -G -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  "https://monitoring.googleapis.com/v3/projects/my-project/timeSeries" \
  --data-urlencode 'filter=metric.type="compute.googleapis.com/instance/cpu/utilization" AND resource.labels.instance_id="INSTANCE_ID"' \
  --data-urlencode 'interval.startTime=2025-06-13T10:00:00Z' \
  --data-urlencode 'interval.endTime=2025-06-13T10:05:00Z'

# GA gcloud surface covers dashboards, uptime checks, and snoozes
gcloud monitoring dashboards list

# Read recent log entries
gcloud logging read "resource.type=gce_instance" --limit=50

# Read logs for a specific VM
gcloud logging read \
  'resource.type="gce_instance" AND resource.labels.instance_id="INSTANCE_ID"' \
  --limit=100 \
  --format=json

# Tail logs in real time
gcloud logging tail 'resource.type="cloud_run_revision"'

# Read App Engine logs
gcloud logging read 'resource.type="gae_app"' --limit=20

# Read logs by severity
gcloud logging read 'severity>=ERROR' --limit=50 --freshness=1h

# Write a log entry (useful for testing)
gcloud logging write my-log "Test message" --severity=INFO

# Errors in Cloud Run service
resource.type="cloud_run_revision"
resource.labels.service_name="my-service"
severity>=ERROR

# HTTP 5xx on a load balancer
resource.type="http_load_balancer"
httpRequest.status>=500

# Cloud SQL slow queries
resource.type="cloudsql_database"
textPayload:"duration"

# Specific user activity (Admin Activity audit log)
logName="projects/my-project/logs/cloudaudit.googleapis.com%2Factivity"
protoPayload.authenticationInfo.principalEmail="alice@example.com"

# Export logs to Cloud Storage
gcloud logging sinks create my-gcs-sink \
  storage.googleapis.com/my-log-bucket \
  --log-filter='severity>=WARNING'

# Export to BigQuery
gcloud logging sinks create my-bq-sink \
  bigquery.googleapis.com/projects/my-project/datasets/logs_dataset \
  --log-filter='resource.type="cloud_run_revision"'

# Export to Pub/Sub
gcloud logging sinks create my-pubsub-sink \
  pubsub.googleapis.com/projects/my-project/topics/log-topic

# List sinks
gcloud logging sinks list

# Update a sink filter
gcloud logging sinks update my-gcs-sink \
  --log-filter='severity>=ERROR'

# Delete a sink
gcloud logging sinks delete my-gcs-sink

# Create a counter metric from log entries
gcloud logging metrics create error-count \
  --description="Count of ERROR log entries" \
  --log-filter='severity>=ERROR'

# Create a distribution metric (e.g., request latency from logs)
gcloud logging metrics create request-latency \
  --description="Request latency distribution" \
  --log-filter='resource.type="cloud_run_revision"' \
  --value-extractor='EXTRACT(jsonPayload.latency_ms)'

# List metrics
gcloud logging metrics list

# Policy management via gcloud is still alpha (Console/Terraform are the GA paths)
gcloud alpha monitoring policies create --policy-from-file=alert-policy.json

# List alert policies
gcloud alpha monitoring policies list

# Delete a policy
gcloud alpha monitoring policies delete POLICY_ID

{
  "displayName": "High CPU",
  "conditions": [{
    "displayName": "CPU utilization > 80%",
    "conditionThreshold": {
      "filter": "resource.type=\"gce_instance\" metric.type=\"compute.googleapis.com/instance/cpu/utilization\"",
      "comparison": "COMPARISON_GT",
      "thresholdValue": 0.8,
      "duration": "300s",
      "aggregations": [{"alignmentPeriod": "60s", "perSeriesAligner": "ALIGN_MEAN"}]
    }
  }],
  "combiner": "OR",
  "alertStrategy": {"autoClose": "1800s"},
  "notificationChannels": ["projects/my-project/notificationChannels/CHANNEL_ID"]
}

# Channel management via gcloud is beta
gcloud beta monitoring channels list

# Create an email notification channel
gcloud beta monitoring channels create \
  --display-name="Ops Team" \
  --type=email \
  --channel-labels=email_address=ops@example.com

# Or create from a full JSON definition
gcloud beta monitoring channels create --channel-content-from-file=channel.json

# Slack/PagerDuty channels need OAuth setup — create them in the Console first

# Create an HTTPS uptime check (GA)
gcloud monitoring uptime create my-service-uptime \
  --resource-type=uptime-url \
  --resource-labels=host=api.example.com,project_id=my-project \
  --protocol=https \
  --port=443 \
  --path=/health \
  --period=1 \
  --timeout=10

# List / describe / delete uptime checks
gcloud monitoring uptime list-configs
gcloud monitoring uptime describe CHECK_ID
gcloud monitoring uptime delete CHECK_ID

# View traces (use Console or API — CLI is limited)
# Enable the API
gcloud services enable cloudtrace.googleapis.com

# In code: use OpenTelemetry or the Cloud Trace SDK
# Node.js auto-instrumentation
npm install @google-cloud/trace-agent
# Add at the very top of main file:
# require('@google-cloud/trace-agent').start();

# Enable
gcloud services enable cloudprofiler.googleapis.com

# Node.js agent
npm install @google-cloud/profiler
# require('@google-cloud/profiler').start({ serviceContext: { service: 'my-service', version: '1.0' } });

# Enable
gcloud services enable clouderrorreporting.googleapis.com

# List error groups
gcloud beta error-reporting events list --service=my-service --version=v1.0

# Errors are auto-ingested from Cloud Logging for supported runtimes.
# To report manually (REST):
curl -X POST \
  "https://clouderrorreporting.googleapis.com/v1beta1/projects/my-project/events:report?key=API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message":"Error: something failed","serviceContext":{"service":"my-service","version":"1.0"}}'