@InterfaceAudience.Public @InterfaceStability.Evolving public abstract class PreemptionMessage extends Object
PreemptionMessageis part of the RM-AM protocol, and it is used by the RM to specify resources that the RM wants to reclaim from this
ApplicationMaster(AM). The AM receives a
StrictPreemptionContractmessage encoding which containers the platform may forcibly kill, granting it an opportunity to checkpoint state or adjust its execution plan. The message may also include a
PreemptionContractgranting the AM more latitude in selecting which resources to return to the cluster.
The AM should decode both parts of the message. The
StrictPreemptionContract specifies particular allocations that the RM
requires back. The AM can checkpoint containers' state, adjust its execution
plan to move the computation, or take no action and hope that conditions that
caused the RM to ask for the container will change.
In contrast, the
PreemptionContract also includes a description of
resources with a set of containers. If the AM releases containers matching
that profile, then the containers enumerated in
PreemptionContract.getContainers() may not be killed.
Each preemption message reflects the RM's current understanding of the cluster state, so a request to return N containers may not reflect containers the AM is releasing, recently exited containers the RM has yet to learn about, or new containers allocated before the message was generated. Conversely, an RM may request a different profile of containers in subsequent requests.
The policy enforced by the RM is part of the scheduler. Generally, only containers that have been requested consistently should be killed, but the details are not specified.
|Constructor and Description|
@InterfaceAudience.Public @InterfaceStability.Evolving public abstract StrictPreemptionContract getStrictContract()
Copyright © 2016 Apache Software Foundation. All rights reserved.