System and Method for a Self-Optimizing Reservation in Time of Compute Resources

Patent metadata

Field	Value
Publication number	US-2022222119-A1
Application number	US-202217711214-A
Country	US
Kind code	A1
Filing date	Apr 1, 2022
Priority date	Mar 13, 2004
Publication date	Jul 14, 2022
Grant date	—

Abstract

A system and method of dynamically controlling a reservation of resources within a cluster environment to maximize a response time are disclosed. The method embodiment of the invention comprises receiving from a requestor a request for a reservation of resources in the cluster environment, reserving a first group of resources, evaluating resources within the cluster environment to determine if the response time can be improved and if the response time can be improved, then canceling the reservation for the first group of resources and reserving a second group of resources to process the request at the improved response time.

First claim

1 - 20 . (canceled)

21 . A method of operating a compute environment comprising a plurality of resources, the method comprising:
causing, using at least one of a computerized workload manager process or a computerized scheduler process, at least a portion of the plurality of resources to be put into a reserved state, the reserved state associated with at least one compute job to be processed by the compute environment; attaching at least one trigger to the at least one compute job; and firing the at least one trigger based at least on at least one trigger attribute; wherein the compute environment is modified by at least one action that is initiated when the at least one trigger is fired; and wherein the at least one job utilizes the at least portion of the plurality of resources put into a reserved state during processing of the at least one compute job.

22 . The method of claim 21 , wherein:
the causing the at least a portion of the plurality of resources to be put into a reserved state occurs prior to the processing of the at least one compute job; and the processing of the compute job comprises processing the compute job using the compute environment after it has been modified by the at least one action.

23 . The method of claim 22 , wherein the modification of the compute environment by the at least one action comprises modification to the at least portion of the plurality of resources put into a reserved state.

24 . The method of claim 21 , wherein:
the compute environment comprises a plurality of compute nodes; the modification of the compute environment by the at least one action comprises causing performance of an operating system (OS) setup process for one or more of the plurality of compute node; and the method further comprises performing at least one monitoring process of the one of the plurality of compute nodes to determine whether the OS setup process was successfully completed.

25 . The method of claim 21 , further comprising receiving a request for processing the job, the receiving the request comprising receiving at least one configuration file via at least one of (i) the computerized resource manager process, or (ii) the computerized scheduler process.

26 . The method of claim 21 , further comprising receiving a request for processing the job, the receiving the request comprising receiving a request comprising at least one QoS (quality of service) requirement; and
the causing at least a portion of the plurality of resources to be put into a reserved state comprises causing resources necessary to meet the at least one QoS requirement to be put in the reserved state.

27 . The method of claim 21 , wherein the at least one action comprises performance of an internetwork access operation, the internetwork in data communication with the compute environment.

28 . The method of claim 21 , wherein the at least one action comprises performance of a database update operation.

29 . The method of claim 21 , wherein the at least one action comprises performance of both (i) a data storage system access operation, and (ii) a transfer operation which transfers data accessed from the storage system to a local file or storage system in data communication with at least one compute node of the compute environment.

30 . The method of claim 21 , wherein the attaching the at least one trigger comprises:
causing creation of at least one software object which comprises at least a portion of the at least one trigger, the at least one software object created responsive to a user input via a graphical user interface (GUI) of a computer software process; and causing association of the at least one software object with the at least one compute job.

31 . The method of claim 21 , wherein the at least one trigger is further configured to cause the at least one action only after expiry of a prescribed time period.

32 . The method of claim 31 , wherein the prescribed time period includes a time period measured from when the at least portion of the plurality of resources are put in the reserved state.

33 . The method of claim 21 , wherein:
the at least one trigger further comprises a timeout value associated therewith; and the method further comprises using the timeout value at least to determine whether the at least one action has completed successfully.

34 . A method of operating a compute environment comprising a plurality of compute nodes under common administrative control, the method comprising:
receiving a request for processing one or more workload items; causing resources of the compute environment to be put in a reserved state to support processing of at least one of the one or more workload items; causing creation of one or more triggers, the one or more triggers adapted to cause initiation of configuration of at least a portion of the resources in support of processing the workload; triggering at least one of the one or more triggers based at least on an occurrence of a prescribed condition, the triggering causing the initiation of the configuration of the at least portion of the resources; monitoring one or more events after causing the initiation of the configuration; and based at least on the monitored one or more events, causing at least one of (i) cancellation of the reserved state, or (ii) retry of the initiation of the configuration of the at least portion of the resources.

35 . The method of claim 34 , wherein:
the causing the initiation of the configuration of the at least portion of the resources comprises causing initiation of an operating system (OS) setup process for one or more of the compute nodes; and the monitoring of the one or more events after causing the initiation of the configuration comprises monitoring whether the OS setup process was completed.

36 . The method of claim 34 , wherein the monitoring of the one or more events after causing the initiation of the configuration comprises performance of a health check process.

37 . The method of claim 34 , wherein the receiving a request for processing one or more workload items comprises receiving at least one configuration file via at least one of (i) a computerized resource manager process, or (ii) a computerized scheduler process, of the compute environment.

38 . The method of claim 34 , wherein:
the receiving a request for processing one or more workload items comprises receiving a request comprising at least one QoS (quality of service) requirement; and the causing resources of the compute environment to be put in a reserved state to support processing of at least one of the one or more workload items comprises causing resources necessary to meet the at least one QoS requirement to be put in the reserved state.

39 . The method of claim 34 , wherein the causing the initiation of the configuration of the at least portion of the resources comprises causing initiation of at least one of (i) a data storage system access operation, or (ii) a transfer operation which transfers data accessed from a storage system to a local file or storage system.

40 . The method of claim 39 , wherein the causing initiation of at least one of (i) a data storage system access operation, or (ii) a transfer operation which transfers data accessed from a storage system to a local file or storage system, comprises initiation of both (i) the data storage system access operation, and (ii) a transfer operation which transfers the data accessed from the storage system to a local file or storage system in d

Assignees

• Iii Holdings 12 Llc

Inventors

• Jackson David B

Classifications

• G06F9/505 Primary

  considering the load · CPC title

• G06F9/5072

  Grid computing · CPC title

• G06F9/5011

  the resources being hardware resources other than CPUs, Servers and Terminals · CPC title

• G06F2209/503

  Resource availability · CPC title

• G06F2209/506

  Constraint · CPC title