Skip to content
Open
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
5 changes: 3 additions & 2 deletions codebundles/azure-adf-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -340,12 +340,13 @@ Suite Initialization
... type=string
... description=Azure resource group.
... pattern=\w*
${LOOKBACK_PERIOD}= RW.Core.Import User Variable LOOKBACK_PERIOD
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The lookback period for querying failed pipelines (e.g., 1d, 7d, 30d).
... description=The lookback window for querying failed pipelines (e.g., 1d, 7d, 30d).
... pattern=\w*
... default=7d
... example=1d
${LOOKBACK_PERIOD}= Set Variable ${LOOKBACK_WINDOW}
${THRESHOLD_MB}= RW.Core.Import User Variable THRESHOLD_MB
... type=string
... description=The threshold for data volume in MB.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-aks-triage/runbook.robot
lookbackWindow: 60m
configProvided:
- name: AZ_RESOURCE_GROUP
value: {{resource_group.name}}
- name: AKS_CLUSTER
value: {{match_resource.resource.name}}
- name: TIME_PERIOD_MINUTES
value: "60"
- name: AZURE_RESOURCE_SUBSCRIPTION_ID
value: "{{ subscription_id }}"
- name: AZURE_SUBSCRIPTION_NAME
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-aks-triage/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -130,11 +130,12 @@ Suite Initialization
... type=string
... description=The Azure AKS cluster to triage.
... pattern=\w*
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=60
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW}
${AZURE_RESOURCE_SUBSCRIPTION_ID}= RW.Core.Import User Variable AZURE_RESOURCE_SUBSCRIPTION_ID
... type=string
... description=The Azure Subscription ID for the resource.
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-apim-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -505,11 +505,12 @@ Suite Initialization
... type=string
... description=The APIM Instance Name
... pattern=\w*
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=60
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${AZURE_RESOURCE_SUBSCRIPTION_ID}= RW.Core.Import User Variable AZURE_RESOURCE_SUBSCRIPTION_ID
... type=string
... description=The Azure Subscription ID for the resource.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-appservice-functionapp-health/runbook.robot
lookbackWindow: 10m
configProvided:
- name: AZ_RESOURCE_GROUP
value: {{resource_group.name}}
- name: FUNCTION_APP_NAME
value: {{match_resource.resource.name}}
- name: TIME_PERIOD_MINUTES
value: "10"
- name: AZURE_RESOURCE_SUBSCRIPTION_ID
value: "{{ subscription_id }}"
- name: AZURE_SUBSCRIPTION_NAME
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -538,11 +538,12 @@ Suite Initialization
... description=The Azure Subscription ID for the resource.
... pattern=\w*
... default=""
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=10
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${TIME_PERIOD_DAYS}= RW.Core.Import User Variable TIME_PERIOD_DAYS
... type=string
... description=The time period, in days, to look back for recommendations and notifications.
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-appservice-plan-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -270,11 +270,12 @@ Suite Initialization
... description=Azure subscription name.
... pattern=\w*
... default=""
${AZURE_ACTIVITY_LOG_OFFSET}= RW.Core.Import User Variable AZURE_ACTIVITY_LOG_OFFSET
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=Time offset for activity log collection (e.g., 24h, 7d) (default: 24h)
... pattern=\w+
... default=24h
${AZURE_ACTIVITY_LOG_OFFSET}= Set Variable ${LOOKBACK_WINDOW}
${CPU_THRESHOLD}= RW.Core.Import User Variable CPU_THRESHOLD
... type=string
... description=CPU usage threshold percentage for high usage alerts (default: 80)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-appservice-webapp-health/runbook.robot
lookbackWindow: 10m
configProvided:
- name: AZ_RESOURCE_GROUP
value: {{resource_group.name}}
Expand All @@ -30,8 +31,6 @@ spec:
value: "{{ subscription_id }}"
- name: AZURE_SUBSCRIPTION_NAME
value: "{{ subscription_name }}"
- name: TIME_PERIOD_MINUTES
value: "10"
secretsProvided:
{% if wb_version %}
{% include "azure-auth.yaml" ignore missing %}
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-appservice-webapp-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -479,11 +479,12 @@ Suite Initialization
... description=The Azure Subscription ID for the resource.
... pattern=\w*
... default=""
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=10
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${CPU_THRESHOLD}= RW.Core.Import User Variable CPU_THRESHOLD
... type=string
... description=The CPU % threshold in which to generate an issue.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-appservice-webapp-ops/runbook.robot
lookbackWindow: 10m
configProvided:
- name: AZ_RESOURCE_GROUP
value: {{resource_group.name}}
- name: APP_SERVICE_NAME
value: {{match_resource.resource.name}}
- name: TIME_PERIOD_MINUTES
value: "10"
- name: SCALE_OUT_FACTOR
value: "2"
- name: SCALE_IN_FACTOR
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-appservice-webapp-ops/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -214,11 +214,12 @@ Suite Initialization
... description=The Azure Subscription ID for the resource.
... pattern=\w*
... default=""
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=10
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${SCALE_OUT_FACTOR}= RW.Core.Import User Variable SCALE_OUT_FACTOR
... type=string
... description=The factor by which to increase the amount of instances within the given App Service Plan.
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-kv-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -303,11 +303,12 @@ Suite Initialization
... description=Interval for latency metrics (format: PT1H, PT30M, PT5M, etc.)
... default=PT1H
... example=PT5M
${TIME_RANGE}= RW.Core.Import User Variable TIME_RANGE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=integer
... description=Time range in hours to look back for metrics
... default=24
... example=24
${TIME_RANGE}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${LOG_QUERY_DAYS}= RW.Core.Import User Variable LOG_QUERY_DAYS
... type=string
... description=Time range for log queries (format: 1d, 7d, 30d, etc.)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,8 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-loadbalancer-triage/runbook.robot
lookbackWindow: 24h
configProvided:
- name: AZ_HISTORY_RANGE
value: '24'
- name: AZ_LB_NAME
value: {{match_resource.resource.name}}
- name: AZ_LB_ID
Expand Down
5 changes: 3 additions & 2 deletions codebundles/azure-loadbalancer-triage/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -48,13 +48,14 @@ Suite Initialization
... type=string
... description=The secret containing AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET, AZURE_SUBSCRIPTION_ID
... pattern=\w*
${AZ_HISTORY_RANGE}= RW.Core.Import User Variable
... AZ_HISTORY_RANGE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable
... LOOKBACK_WINDOW
... type=string
... description=The range of history to check for incidents in the activity log, in hours.
... pattern=\w*
... default=24
... example=24
${AZ_HISTORY_RANGE}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${AZ_LB_NAME}= RW.Core.Import User Variable
... AZ_LB_NAME
... type=string
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/azure-vmss-triage/runbook.robot
lookbackWindow: 60m
configProvided:
- name: AZ_RESOURCE_GROUP
value: {{resource_group.name}}
- name: VMSCALESET
value: {{match_resource.resource.name}}
- name: TIME_PERIOD_MINUTES
value: "60"
- name: AZURE_RESOURCE_SUBSCRIPTION_ID
value: "{{ subscription_id }}"
- name: AZURE_SUBSCRIPTION_NAME
Expand Down
3 changes: 2 additions & 1 deletion codebundles/azure-vmss-triage/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -82,11 +82,12 @@ Suite Initialization
... type=string
... description=The Azure Virtual Machine Scale Set to triage.
... pattern=\w*
${TIME_PERIOD_MINUTES}= RW.Core.Import User Variable TIME_PERIOD_MINUTES
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time period, in minutes, to look back for activites/events.
... pattern=\w*
... default=60
${TIME_PERIOD_MINUTES}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${azure_credentials}= RW.Core.Import Secret
... azure_credentials
... type=string
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -143,12 +143,13 @@ Suite Initialization
... pattern=\w*
... example=5.* (matches any 500 error code)
... default=5.*
${TIME_SLICE}= RW.Core.Import User Variable TIME_SLICE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=Specify the window of time used to measure the rate.
... pattern=\w*
... example=1m
... default=1m
${TIME_SLICE}= Set Variable ${LOOKBACK_WINDOW}
${HTTP_ERROR_RATE_THRESHOLD}= RW.Core.Import User Variable HTTP_ERROR_RATE_THRESHOLD
... type=string
... description=Specify the error rate threshold that is considered unhealthy. Measured in errors/s.
Expand Down
5 changes: 3 additions & 2 deletions codebundles/curl-gmp-nginx-ingress-inspection/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -135,13 +135,13 @@ Suite Initialization
... description=The name of the ingress object in Kubernetes.
... pattern=\w*
... example=frontend-external
${TIME_SLICE}= RW.Core.Import User Variable TIME_SLICE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The amount of time to perform aggregations over.
... pattern=\w*
... example=60m
... default=60m
Set Suite Variable ${TIME_SLICE} ${TIME_SLICE}
${TIME_SLICE}= Set Variable ${LOOKBACK_WINDOW}
${ERROR_CODES}= RW.Core.Import User Variable ERROR_CODES
... type=string
... description=Which http status codes to look for and classify as errors.
Expand All @@ -159,6 +159,7 @@ Suite Initialization
Set Suite Variable ${INGRESS_HOST} ${INGRESS_HOST}
Set Suite Variable ${INGRESS_SERVICE} ${INGRESS_SERVICE}
Set Suite Variable ${INGRESS_OBJECT_NAME} ${INGRESS_OBJECT_NAME}
Set Suite Variable ${TIME_SLICE} ${TIME_SLICE}
Set Suite Variable
... ${env}
... {"CLOUDSDK_CORE_PROJECT":"${GCP_PROJECT_ID}","GOOGLE_APPLICATION_CREDENTIALS":"./${gcp_credentials_json.key}", "KUBECONFIG":"./${kubeconfig.key}","PATH":"$PATH:${OS_PATH}"}
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/gcloud-node-preempt/runbook.robot
lookbackWindow: 30m
intervalStrategy: intermezzo
intervalSeconds: 300
configProvided:
- name: GCP_PROJECT_ID
value: {{match_resource.resource.project_id}}
- name: AGE
value: '30'
secretsProvided:
- name: gcp_credentials_json
workspaceKey: {{custom.gcp_ops_suite_sa}}
3 changes: 2 additions & 1 deletion codebundles/gcloud-node-preempt/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -49,12 +49,13 @@ Suite Initialization
... description=The GCP Project ID to scope the API to.
... pattern=\w*
... example=myproject-ID
${AGE}= RW.Core.Import User Variable AGE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The age, in minutes, since the preempt event.
... pattern=\d+
... default=30
... example=30
${AGE}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${OS_PATH}= Get Environment Variable PATH
Set Suite Variable ${GCP_PROJECT_ID} ${GCP_PROJECT_ID}
Set Suite Variable ${gcp_credentials_json} ${gcp_credentials_json}
Expand Down
3 changes: 2 additions & 1 deletion codebundles/gh-actions-artifact-analysis/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -90,12 +90,13 @@ Suite Initialization
... description=The GitHub Token used to access the repository.
... pattern=\w*
... default=''
${PERIOD_HOURS}= RW.Core.Import User Variable PERIOD_HOURS
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The amount of hours to condider for a healthy last workflow run.
... pattern=\w*
... example=24
... default=24
${PERIOD_HOURS}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${ISSUE_SEARCH_STRING}= RW.Core.Import User Variable ISSUE_SEARCH_STRING
... type=string
... description=A string that, if found in the analysis output, will generate an Issue.
Expand Down
3 changes: 2 additions & 1 deletion codebundles/gh-actions-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -387,12 +387,13 @@ Suite Initialization
... pattern=^\d+$
... example=70
... default=70
${FAILURE_LOOKBACK_DAYS}= RW.Core.Import User Variable FAILURE_LOOKBACK_DAYS
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=Number of days to look back for workflow failures. Accepts partial numbers (e.g. 0.04 = 1h)
... pattern=^\d+$
... example=1
... default=1
${FAILURE_LOOKBACK_DAYS}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
${MAX_REPOS_TO_ANALYZE}= RW.Core.Import User Variable MAX_REPOS_TO_ANALYZE
... type=string
... description=Maximum number of repositories to analyze when GITHUB_REPOS is 'ALL' (0 for unlimited)
Expand Down
3 changes: 2 additions & 1 deletion codebundles/gke-cluster-health/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -58,12 +58,13 @@ Suite Initialization
... pattern=\w*
... default=2
... example=2
${NODE_HEALTH_LOOKBACK_HOURS}= RW.Core.Import User Variable NODE_HEALTH_LOOKBACK_HOURS
${LOOKBACK_WINDOW}= RW.Core.Import User Variable LOOKBACK_WINDOW
... type=string
... description=The time (in hours) to look back for node pool events and compute operations when checking node health.
... pattern=\w*
... default=24
... example=24
${NODE_HEALTH_LOOKBACK_HOURS}= RW.Core.Normalize Lookback Window Str ${LOOKBACK_WINDOW} 1
Set Suite Variable ${GCP_PROJECT_ID} ${GCP_PROJECT_ID}
Set Suite Variable ${gcp_credentials_json} ${gcp_credentials_json}
Set Suite Variable
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/k8s-app-troubleshoot/runbook.robot
lookbackWindow: 60m
configProvided:
- name: NAMESPACE
value: {{match_resource.resource.metadata.namespace}}
Expand All @@ -31,8 +32,6 @@ spec:
value: '10'
- name: CREATE_ISSUES
value: 'YES'
- name: LOGS_SINCE
value: 60m
- name: EXCLUDE_PATTERN
value: Placeholder
- name: MAX_LOG_LINES
Expand Down
5 changes: 3 additions & 2 deletions codebundles/k8s-app-troubleshoot/runbook.robot
Original file line number Diff line number Diff line change
Expand Up @@ -179,13 +179,14 @@ Suite Initialization
... enum=[YES,NO]
... example=YES
... default=YES
${LOGS_SINCE}= RW.Core.Import User Variable
... LOGS_SINCE
${LOOKBACK_WINDOW}= RW.Core.Import User Variable
... LOOKBACK_WINDOW
... type=string
... description=How far back to fetch logs from containers in Kubernetes. Making this too recent and running the codebundle often could cause adverse performance.
... pattern=\w*
... example=15m
... default=15m
${LOGS_SINCE}= Set Variable ${LOOKBACK_WINDOW}
${EXCLUDE_PATTERN}= RW.Core.Import User Variable
... EXCLUDE_PATTERN
... type=string
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,13 +20,12 @@ spec:
ref: main
{% endif %}
pathToRobot: codebundles/k8s-cluster-node-health/runbook.robot
lookbackWindow: 10m
configProvided:
- name: CONTEXT
value: "{{cluster.context}}"
- name: KUBERNETES_DISTRIBUTION_BINARY
value: {{custom.kubernetes_distribution_binary}}
- name: INTERVAL
value: "10 minutes"
secretsProvided:
{% if wb_version %}
{% include "kubernetes-auth.yaml" ignore missing %}
Expand Down
Loading