Add timeout to Batch jobs

R builds can hang forever; for example, the Ubuntu 20.04 builds
with OpenBLAS present.
This commit is contained in:
Greg Lin 2020-05-04 11:28:27 -05:00
commit 034b3712d7

View file

@ -143,6 +143,8 @@ rBuildsBatchJobDefinitionUbuntu1604:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-1604" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-1604"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionUbuntu1804: rBuildsBatchJobDefinitionUbuntu1804:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -155,6 +157,8 @@ rBuildsBatchJobDefinitionUbuntu1804:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-1804" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-1804"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionUbuntu2004: rBuildsBatchJobDefinitionUbuntu2004:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -167,6 +171,8 @@ rBuildsBatchJobDefinitionUbuntu2004:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-2004" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:ubuntu-2004"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionDebian9: rBuildsBatchJobDefinitionDebian9:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -179,6 +185,8 @@ rBuildsBatchJobDefinitionDebian9:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:debian-9" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:debian-9"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionCentos6: rBuildsBatchJobDefinitionCentos6:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -191,6 +199,8 @@ rBuildsBatchJobDefinitionCentos6:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-6" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-6"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionCentos7: rBuildsBatchJobDefinitionCentos7:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -203,6 +213,8 @@ rBuildsBatchJobDefinitionCentos7:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-7" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-7"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionCentos8: rBuildsBatchJobDefinitionCentos8:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -215,6 +227,8 @@ rBuildsBatchJobDefinitionCentos8:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-8" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:centos-8"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionOpensuse42: rBuildsBatchJobDefinitionOpensuse42:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -227,6 +241,8 @@ rBuildsBatchJobDefinitionOpensuse42:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:opensuse-42" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:opensuse-42"
Timeout:
AttemptDurationSeconds: 7200
rBuildsBatchJobDefinitionOpensuse15: rBuildsBatchJobDefinitionOpensuse15:
Type: AWS::Batch::JobDefinition Type: AWS::Batch::JobDefinition
Properties: Properties:
@ -239,6 +255,8 @@ rBuildsBatchJobDefinitionOpensuse15:
JobRoleArn: JobRoleArn:
"Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ] "Fn::GetAtt": [ rBuildsEcsTaskIamRole, Arn ]
Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:opensuse-15" Image: "#{AWS::AccountId}.dkr.ecr.#{AWS::Region}.amazonaws.com/r-builds:opensuse-15"
Timeout:
AttemptDurationSeconds: 7200
# step function cloudwatch event trigger resources # step function cloudwatch event trigger resources
rBuildsEventRuleIamRole: rBuildsEventRuleIamRole: