services/Batch/batchAccounts/alerts.yaml (107 lines of code) (raw):
- name: UnusableNodeCount
description: Number of unusable nodes
type: Metric
verified: false
visible: true
tags:
- auto-generated
- agc-520
- hpc
properties:
metricName: UnusableNodeCount
metricNamespace: Microsoft.Batch/batchAccounts
severity: 2
windowSize: PT5M
evaluationFrequency: PT1M
timeAggregation: Total
operator: GreaterThan
criterionType: StaticThresholdCriterion
threshold: 2.5
autoMitigate: false
enabled: true
guid: 6c9857e4-7d6b-4384-80da-b88a2e6858ac
- name: OfflineNodeCount
description: Number of offline nodes
type: Metric
verified: false
visible: true
tags:
- auto-generated
- agc-416
- hpc
properties:
metricName: OfflineNodeCount
metricNamespace: Microsoft.Batch/batchAccounts
severity: 3
windowSize: PT5M
evaluationFrequency: PT1M
timeAggregation: Total
operator: GreaterThan
criterionType: StaticThresholdCriterion
threshold: 0.0
autoMitigate: false
enabled: true
guid: b40fdb04-cada-4870-80f3-317afc57e5fb
- name: TaskFailEvent
description: Total number of tasks that have completed in a failed state
type: Metric
verified: false
visible: true
tags:
- auto-generated
- agc-329
- hpc
- agc-371
properties:
metricName: TaskFailEvent
metricNamespace: Microsoft.Batch/batchAccounts
severity: 3
windowSize: PT5M
evaluationFrequency: PT1M
timeAggregation: Total
operator: GreaterThan
criterionType: StaticThresholdCriterion
threshold: 0.0
autoMitigate: false
enabled: true
guid: 70b8ce6d-0d28-4997-84df-957791877eec
- name: RebootingNodeCount
description: Number of rebooting nodes
type: Metric
verified: false
visible: true
tags:
- hpc
properties:
metricName: RebootingNodeCount
metricNamespace: Microsoft.Batch/batchAccounts
severity: 1
windowSize: PT5M
evaluationFrequency: PT1M
timeAggregation: Total
operator: GreaterThan
criterionType: StaticThresholdCriterion
threshold: 0.0
autoMitigate: false
enabled: true
guid: f49539ff-35b1-4d83-8541-e3cf49b383e5
- name: PreemptedNodeCount
description: Number of preempted nodes
type: Metric
verified: false
visible: true
tags:
- hpc
properties:
metricName: PreemptedNodeCount
metricNamespace: Microsoft.Batch/batchAccounts
severity: 1
windowSize: PT5M
evaluationFrequency: PT1M
timeAggregation: Total
operator: GreaterThan
criterionType: StaticThresholdCriterion
threshold: 0.0
autoMitigate: false
enabled: true
guid: 8ce7d791-41a5-4d6a-9516-b009eabbd8f7