최신 스냅샷에서 루트 볼륨 복원

루트 볼륨의 운영 체제는 여러 가지 이유로 손상될 수 있습니다. 예를 들어 패치 작업 후 손상된 커널 또는 레지스트리로 인해 인스턴스가 성공적으로 부팅되지 않을 수 있습니다. 패치 작업 전에 생성된 최신 스냅샷에서 루트 볼륨을 복원하는 것과 같은 일반적인 문제 해결 태스크를 자동화하면 가동 중지 시간을 줄이고 문제 해결 작업을 신속하게 수행할 수 있습니다. AWS Systems Manager 이러한 경우 Automation 작업이 도움이 될 수 있습니다. Automation은 AWS Systems Manager의 기능입니다.

다음 예제 AWS Systems Manager 런북은 다음과 같은 작업을 수행합니다.

• aws:executeAwsApi 자동화 작업을 사용하여 인스턴스의 루트 볼륨에서 세부 정보를 검색합니다.

• aws:executeScript 자동화 작업을 사용하여 루트 볼륨의 최신 스냅샷을 검색합니다.

• 루트 볼륨에 대한 스냅샷이 발견되면 aws:branch 자동화 작업을 사용하여 자동화를 계속합니다.

YAML

    ---
    description: Custom Automation Troubleshooting Example
    schemaVersion: '0.3'
    assumeRole: "{{ AutomationAssumeRole }}"
    parameters:
      AutomationAssumeRole:
        type: String
        description: "(Required) The ARN of the role that allows Automation to perform
          the actions on your behalf. If no role is specified, Systems Manager Automation
          uses your IAM permissions to use this runbook."
        default: ''
      InstanceId:
          type: String
          description: "(Required) The Instance Id whose root EBS volume you want to restore the latest Snapshot."
          default: ''
    mainSteps:
    - name: getInstanceDetails
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: DescribeInstances
        InstanceIds:
        - "{{ InstanceId }}"
      outputs:
        - Name: availabilityZone
          Selector: "$.Reservations[0].Instances[0].Placement.AvailabilityZone"
          Type: String
        - Name: rootDeviceName
          Selector: "$.Reservations[0].Instances[0].RootDeviceName"
          Type: String
      nextStep: getRootVolumeId
    - name: getRootVolumeId
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: DescribeVolumes
        Filters:
        -  Name: attachment.device
           Values: ["{{ getInstanceDetails.rootDeviceName }}"]
        -  Name: attachment.instance-id
           Values: ["{{ InstanceId }}"]
      outputs:
        - Name: rootVolumeId
          Selector: "$.Volumes[0].VolumeId"
          Type: String
      nextStep: getSnapshotsByStartTime
    - name: getSnapshotsByStartTime
      action: aws:executeScript
      timeoutSeconds: 45
      onFailure: Abort
      inputs:
        Runtime: python3.8
        Handler: getSnapshotsByStartTime
        InputPayload:
          rootVolumeId : "{{ getRootVolumeId.rootVolumeId }}"
        Script: |-
          def getSnapshotsByStartTime(events,context):
            import boto3
    
            #Initialize client
            ec2 = boto3.client('ec2')
            rootVolumeId = events['rootVolumeId']
            snapshotsQuery = ec2.describe_snapshots(
              Filters=[
                {
                  "Name": "volume-id",
                  "Values": [rootVolumeId]
                }
              ]
            )
            if not snapshotsQuery['Snapshots']:
              noSnapshotFoundString = "NoSnapshotFound"
              return { 'noSnapshotFound' : noSnapshotFoundString }
            else:
              jsonSnapshots = snapshotsQuery['Snapshots']
              sortedSnapshots = sorted(jsonSnapshots, key=lambda k: k['StartTime'], reverse=True)
              latestSortedSnapshotId = sortedSnapshots[0]['SnapshotId']
              return { 'latestSnapshotId' : latestSortedSnapshotId }
      outputs:
      - Name: Payload
        Selector: $.Payload
        Type: StringMap
      - Name: latestSnapshotId
        Selector: $.Payload.latestSnapshotId
        Type: String
      - Name: noSnapshotFound
        Selector: $.Payload.noSnapshotFound
        Type: String 
      nextStep: branchFromResults
    - name: branchFromResults
      action: aws:branch
      onFailure: Abort
      inputs:
        Choices:
        - NextStep: createNewRootVolumeFromSnapshot
          Not:
            Variable: "{{ getSnapshotsByStartTime.noSnapshotFound }}"
            StringEquals: "NoSnapshotFound"
      isEnd: true
    - name: createNewRootVolumeFromSnapshot
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: CreateVolume
        AvailabilityZone: "{{ getInstanceDetails.availabilityZone }}"
        SnapshotId: "{{ getSnapshotsByStartTime.latestSnapshotId }}"
      outputs:
        - Name: newRootVolumeId
          Selector: "$.VolumeId"
          Type: String
      nextStep: stopInstance
    - name: stopInstance
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: StopInstances
        InstanceIds:
        - "{{ InstanceId }}"
      nextStep: verifyVolumeAvailability
    - name: verifyVolumeAvailability
      action: aws:waitForAwsResourceProperty
      timeoutSeconds: 120
      inputs:
        Service: ec2
        Api: DescribeVolumes
        VolumeIds:
        - "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
        PropertySelector: "$.Volumes[0].State"
        DesiredValues:
        - "available"
      nextStep: verifyInstanceStopped
    - name: verifyInstanceStopped
      action: aws:waitForAwsResourceProperty
      timeoutSeconds: 120
      inputs:
        Service: ec2
        Api: DescribeInstances
        InstanceIds:
        - "{{ InstanceId }}"
        PropertySelector: "$.Reservations[0].Instances[0].State.Name"
        DesiredValues:
        - "stopped"
      nextStep: detachRootVolume
    - name: detachRootVolume
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: DetachVolume
        VolumeId: "{{ getRootVolumeId.rootVolumeId }}"
      nextStep: verifyRootVolumeDetached
    - name: verifyRootVolumeDetached
      action: aws:waitForAwsResourceProperty
      timeoutSeconds: 30
      inputs:
        Service: ec2
        Api: DescribeVolumes
        VolumeIds:
        - "{{ getRootVolumeId.rootVolumeId }}"
        PropertySelector: "$.Volumes[0].State"
        DesiredValues:
        - "available"
      nextStep: attachNewRootVolume
    - name: attachNewRootVolume
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: AttachVolume
        Device: "{{ getInstanceDetails.rootDeviceName }}"
        InstanceId: "{{ InstanceId }}"
        VolumeId: "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
      nextStep: verifyNewRootVolumeAttached
    - name: verifyNewRootVolumeAttached
      action: aws:waitForAwsResourceProperty
      timeoutSeconds: 30
      inputs:
        Service: ec2
        Api: DescribeVolumes
        VolumeIds:
        - "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
        PropertySelector: "$.Volumes[0].Attachments[0].State"
        DesiredValues:
        - "attached"
      nextStep: startInstance
    - name: startInstance
      action: aws:executeAwsApi
      onFailure: Abort
      inputs:
        Service: ec2
        Api: StartInstances
        InstanceIds:
        - "{{ InstanceId }}"

JSON

    {
       "description": "Custom Automation Troubleshooting Example",
       "schemaVersion": "0.3",
       "assumeRole": "{{ AutomationAssumeRole }}",
       "parameters": {
          "AutomationAssumeRole": {
             "type": "String",
             "description": "(Required) The ARN of the role that allows Automation to perform the actions on your behalf. If no role is specified, Systems Manager Automation uses your IAM permissions to run this runbook.",
             "default": ""
          },
          "InstanceId": {
             "type": "String",
             "description": "(Required) The Instance Id whose root EBS volume you want to restore the latest Snapshot.",
             "default": ""
          }
       },
       "mainSteps": [
          {
             "name": "getInstanceDetails",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeInstances",
                "InstanceIds": [
                   "{{ InstanceId }}"
                ]
             },
             "outputs": [
                {
                   "Name": "availabilityZone",
                   "Selector": "$.Reservations[0].Instances[0].Placement.AvailabilityZone",
                   "Type": "String"
                },
                {
                   "Name": "rootDeviceName",
                   "Selector": "$.Reservations[0].Instances[0].RootDeviceName",
                   "Type": "String"
                }
             ],
             "nextStep": "getRootVolumeId"
          },
          {
             "name": "getRootVolumeId",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeVolumes",
                "Filters": [
                   {
                      "Name": "attachment.device",
                      "Values": [
                         "{{ getInstanceDetails.rootDeviceName }}"
                      ]
                   },
                   {
                      "Name": "attachment.instance-id",
                      "Values": [
                         "{{ InstanceId }}"
                      ]
                   }
                ]
             },
             "outputs": [
                {
                   "Name": "rootVolumeId",
                   "Selector": "$.Volumes[0].VolumeId",
                   "Type": "String"
                }
             ],
             "nextStep": "getSnapshotsByStartTime"
          },
          {
             "name": "getSnapshotsByStartTime",
             "action": "aws:executeScript",
             "timeoutSeconds": 45,
             "onFailure": "Continue",
             "inputs": {
                "Runtime": "python3.8",
                "Handler": "getSnapshotsByStartTime",
                "InputPayload": {
                   "rootVolumeId": "{{ getRootVolumeId.rootVolumeId }}"
                },
                "Attachment": "getSnapshotsByStartTime.py"
             },
             "outputs": [
                {
                   "Name": "Payload",
                   "Selector": "$.Payload",
                   "Type": "StringMap"
                },
                {
                   "Name": "latestSnapshotId",
                   "Selector": "$.Payload.latestSnapshotId",
                   "Type": "String"
                },
                {
                   "Name": "noSnapshotFound",
                   "Selector": "$.Payload.noSnapshotFound",
                   "Type": "String"
                }
             ],
             "nextStep": "branchFromResults"
          },
          {
             "name": "branchFromResults",
             "action": "aws:branch",
             "onFailure": "Abort",
             "inputs": {
                "Choices": [
                   {
                      "NextStep": "createNewRootVolumeFromSnapshot",
                      "Not": {
                         "Variable": "{{ getSnapshotsByStartTime.noSnapshotFound }}",
                         "StringEquals": "NoSnapshotFound"
                      }
                   }
                ]
             },
             "isEnd": true
          },
          {
             "name": "createNewRootVolumeFromSnapshot",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "CreateVolume",
                "AvailabilityZone": "{{ getInstanceDetails.availabilityZone }}",
                "SnapshotId": "{{ getSnapshotsByStartTime.latestSnapshotId }}"
             },
             "outputs": [
                {
                   "Name": "newRootVolumeId",
                   "Selector": "$.VolumeId",
                   "Type": "String"
                }
             ],
             "nextStep": "stopInstance"
          },
          {
             "name": "stopInstance",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "StopInstances",
                "InstanceIds": [
                   "{{ InstanceId }}"
                ]
             },
             "nextStep": "verifyVolumeAvailability"
          },
          {
             "name": "verifyVolumeAvailability",
             "action": "aws:waitForAwsResourceProperty",
             "timeoutSeconds": 120,
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeVolumes",
                "VolumeIds": [
                   "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
                ],
                "PropertySelector": "$.Volumes[0].State",
                "DesiredValues": [
                   "available"
                ]
             },
             "nextStep": "verifyInstanceStopped"
          },
          {
             "name": "verifyInstanceStopped",
             "action": "aws:waitForAwsResourceProperty",
             "timeoutSeconds": 120,
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeInstances",
                "InstanceIds": [
                   "{{ InstanceId }}"
                ],
                "PropertySelector": "$.Reservations[0].Instances[0].State.Name",
                "DesiredValues": [
                   "stopped"
                ]
             },
             "nextStep": "detachRootVolume"
          },
          {
             "name": "detachRootVolume",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "DetachVolume",
                "VolumeId": "{{ getRootVolumeId.rootVolumeId }}"
             },
             "nextStep": "verifyRootVolumeDetached"
          },
          {
             "name": "verifyRootVolumeDetached",
             "action": "aws:waitForAwsResourceProperty",
             "timeoutSeconds": 30,
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeVolumes",
                "VolumeIds": [
                   "{{ getRootVolumeId.rootVolumeId }}"
                ],
                "PropertySelector": "$.Volumes[0].State",
                "DesiredValues": [
                   "available"
                ]
             },
             "nextStep": "attachNewRootVolume"
          },
          {
             "name": "attachNewRootVolume",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "AttachVolume",
                "Device": "{{ getInstanceDetails.rootDeviceName }}",
                "InstanceId": "{{ InstanceId }}",
                "VolumeId": "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
             },
             "nextStep": "verifyNewRootVolumeAttached"
          },
          {
             "name": "verifyNewRootVolumeAttached",
             "action": "aws:waitForAwsResourceProperty",
             "timeoutSeconds": 30,
             "inputs": {
                "Service": "ec2",
                "Api": "DescribeVolumes",
                "VolumeIds": [
                   "{{ createNewRootVolumeFromSnapshot.newRootVolumeId }}"
                ],
                "PropertySelector": "$.Volumes[0].Attachments[0].State",
                "DesiredValues": [
                   "attached"
                ]
             },
             "nextStep": "startInstance"
          },
          {
             "name": "startInstance",
             "action": "aws:executeAwsApi",
             "onFailure": "Abort",
             "inputs": {
                "Service": "ec2",
                "Api": "StartInstances",
                "InstanceIds": [
                   "{{ InstanceId }}"
                ]
             }
          }
       ],
       "files": {
            "getSnapshotsByStartTime.py": {
                "checksums": {
                    "sha256": "sampleETagValue"
                }
            }
        }
    }