Using managed scaling in Amazon EMR - Amazon EMR
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China.

Using managed scaling in Amazon EMR

Important

We strongly recommend that you use the latest Amazon EMR release for managed scaling. In earlier Amazon EMR releases, you could experience intermittent application failures or delay in scaling. Amazon EMR resolved this issue in releases 5.30.2, 5.31.1, 5.32.1, 5.33.1 and 6.0.1, 6.1.1, 6.2.1, 6.3.1.

With Amazon EMR versions 5.30.0 and later (except for Amazon EMR 6.0.0), you can enable Amazon EMR managed scaling. Managed scaling lets you automatically increase or decrease the number of instances or units in your cluster based on workload. EMR continuously evaluates cluster metrics to make scaling decisions that optimize your clusters for cost and speed. Managed scaling is available for clusters composed of either instance groups or instance fleets.

Managed scaling parameters

You must configure the following parameters for managed scaling. The limit only applies to the core and task nodes. You cannot scale the primary node after initial configuration.

  • Minimum (MinimumCapacityUnits) – The lower boundary of allowed EC2 capacity in a cluster. It is measured through virtual central processing unit (vCPU) cores or instances for instance groups. It is measured through units for instance fleets.

  • Maximum (MaximumCapacityUnits) – The upper boundary of allowed EC2 capacity in a cluster. It is measured through virtual central processing unit (vCPU) cores or instances for instance groups. It is measured through units for instance fleets.

  • On-Demand limit (MaximumOnDemandCapacityUnits) (Optional) – The upper boundary of allowed EC2 capacity for On-Demand market type in a cluster. If this parameter is not specified, it defaults to the value of MaximumCapacityUnits.

    • This parameter is used to split capacity allocation between On-Demand and Spot Instances. For example, if you set the minimum parameter as 2 instances, the maximum parameter as 100 instances, the On-Demand limit as 10 instances, then Amazon EMR managed scaling scales up to 10 On-Demand Instances and allocates the remaining capacity to Spot Instances. For more information, see Node allocation scenarios.

  • Maximum core nodes (MaximumCoreCapacityUnits) (Optional) – The upper boundary of allowed EC2 capacity for core node type in a cluster. If this parameter is not specified, it defaults to the value of MaximumCapacityUnits.

    • This parameter is used to split capacity allocation between core and task nodes. For example, if you set the minimum parameter as 2 instances, the maximum as 100 instances, the maximum core node as 17 instances, then Amazon EMR managed scaling scales up to 17 core nodes and allocates the remaining 83 instances to task nodes. For more information, see Node allocation scenarios.

For more information about managed scaling parameters, see ComputeLimits.

Considerations and limitations

Availability

  • Amazon EMR managed scaling is currently available in the following Amazon Regions: US East (N. Virginia and Ohio), US West (Oregon and N. California), South America (São Paulo), Europe (Frankfurt, Ireland, London, Milan, Paris, and Stockholm), Canada (Central), Asia Pacific (Hong Kong, Mumbai, Seoul, Singapore, Sydney, and Tokyo), Middle East (Bahrain), Africa (Cape Town), Amazon GovCloud (US-East), Amazon GovCloud (US-West), China (Beijing) operated by Sinnet, and China (Ningxia) operated by NWCD.

  • Amazon EMR managed scaling only works with YARN applications, such as Spark, Hadoop, Hive, and Flink. It currently does not support applications that are not based on YARN, such as Presto and HBase.

  • You must configure the required parameters for Amazon EMR managed scaling. For more information, see Managed scaling parameters.

  • To use managed scaling, the metrics-collector process must be able to connect to the public API endpoint for managed scaling in API Gateway. If you use a private DNS name with Amazon Virtual Private Cloud, managed scaling won't function properly. To ensure that managed scaling works, we recommend that you take one of the following actions:

Other considerations

  • If your YARN jobs are intermittently slow during scale down and YARN Resource Manager logs show that most of your nodes were deny listed during that time, you can adjust the decommissioning timeout threshold.

    Reduce the spark.blacklist.decommissioning.timeout from one hour to one minute to make the node available for other pending containers to continue task processing.

    You should also set YARN.resourcemanager.nodemanager-graceful-decommission-timeout-secs to a larger value to ensure Amazon EMR doesn’t force terminate the node while the longest “Spark Task” is still running on the node. The current default is 60 minutes, which means YARN force-terminates the container after 60 minutes once the node enters the decomissioning state.

    The following example YARN Resource Manager Log line shows nodes added to the decomissioning state:

    2021-10-20 15:55:26,994 INFO org.apache.hadoop.YARN.server.resourcemanager.DefaultAMSProcessor (IPC Server handler 37 on default port 8030): blacklist are updated in Scheduler.blacklistAdditions: [ip-10-10-27-207.us-west-2.compute.internal, ip-10-10-29-216.us-west-2.compute.internal, ip-10-10-31-13.us-west-2.compute.internal, ... , ip-10-10-30-77.us-west-2.compute.internal], blacklistRemovals: []

    See more details on how Amazon EMR integrates with YARN deny listing during decommissioning of nodes, cases when nodes in Amazon EMR can be deny listed, and configuring Spark node-decommissioning behavior.

  • Over-utilization of EBS volumes can cause Managed Scaling issues. We recommend that you maintain EBS volume below 90% utilization. For more information, see Specifying additional EBS storage volumes.

  • Amazon CloudWatch metrics are critical for Amazon EMR managed scaling to operate. We recommend that you closely monitor Amazon CloudWatch metrics to make sure data is not missing. For more information about how you can configure CloudWatch alarms to detect missing metrics, see Using Amazon CloudWatch alarms.

  • Managed scaling operations on 5.30.0 and 5.30.1 clusters without Presto installed may cause application failures or cause a uniform instance group or instance fleet to stay in the ARRESTED state, particularly when a scale down operation is followed quickly by a scale up operation.

    As a workaround, choose Presto as an application to install when you create a cluster with Amazon EMR releases 5.30.0 and 5.30.1, even if your job does not require Presto.

  • When you set the maximum core node and the On-Demand limit for Amazon EMR managed scaling, consider the differences between instance groups and instance fleets. Each instance group consists of the same instance type and the same purchasing option for instances: On-Demand or Spot. For each instance fleet, you can specify up to five instance types, which can be provisioned as On-Demand and Spot Instances. For more information, see Create a cluster with instance fleets or uniform instance groups, Instance fleet options, and Node allocation scenarios.

  • With Amazon EMR 5.30.0 and later, if you remove the default Allow All outbound rule to 0.0.0.0/ for the master security group, you must add a rule that allows outbound TCP connectivity to your security group for service access on port 9443. Your security group for service access must also allow inbound TCP traffic on port 9443 from the master security group. For more information about configuring security groups, see Amazon EMR-managed security group for the primary instance (private subnets).

  • Managed scaling doesn’t support the YARN node labels feature. Avoid using node labels on clusters with managed scaling. For example, don't allow executors to run only on task nodes. When you use node labels in your Amazon EMR clusters, you may find that your cluster isn't scaling up, which can lead to a slow-down of your application.

  • You can use Amazon CloudFormation to configure Amazon EMR managed scaling. For more information, see AWS::EMR::Cluster in the Amazon CloudFormation User Guide.

Feature history

This table lists updates to the Amazon EMR managed scaling capability.

Release date Capability Amazon EMR versions
March 21, 2022 Added Spark shuffle data awareness used when scaling-down clusters. For Amazon EMR clusters with Apache Spark and the managed scaling feature enabled, Amazon EMR continuously monitors Spark executors and intermediate shuffle data locations. Using this information, Amazon EMR scales-down only under-utilized instances which don't contain actively used shuffle data. This prevents recomputation of lost shuffle data, helping to lower cost and improve job performance. For more information, see the Spark Programming Guide. 5.34.0 and later, 6.4.0 and later