Migration between CPU cores

Patent metadata

Field	Value
Publication number	US-11182202-B2
Application number	US-201916653079-A
Country	US
Kind code	B2
Filing date	Oct 15, 2019
Priority date	Aug 26, 2015
Publication date	Nov 23, 2021
Grant date	Nov 23, 2021

Abstract

Methods, non-transitory machine-readable media, and computing devices for transitioning tasks and interrupt service routines are provided. An example method includes processing, by a plurality of processor cores of a storage controller, tasks and interrupt service routines. A performance statistic is determined corresponding to the plurality of processor cores. Based on detecting that the performance statistic passes a threshold, a number of the plurality of processor cores that are assigned to the tasks and the interrupt service routines are reduced.

First claim

What is claimed is:

1. A method comprising:
processing, by a first processor core of a storage controller in a single-core configuration, one or more operations for an initialization sequence;
executing, by the storage controller, an application configured to manage migration from the single-core configuration to a multi-core configuration upon completion of the initialization sequence, the executing the application being a trigger;
determining, by the storage controller, to transition from the single-core configuration to the multi-core configuration in response to the trigger; and
expanding, by the storage controller, from the first processor core assigned to process at least one remaining operation from among the one or more operations to a plurality of processor cores in the multi-core configuration that are assigned to process the at least one remaining operation.

2. The method of claim 1 , further comprising:
rebalancing, by the storage controller, the at least one remaining operation among the plurality of processor cores in response to a performance metric meeting a threshold.

3. The method of claim 1 , wherein the expanding further comprises:
migrating, by the storage controller, at least one operation from the at least one remaining operation to a target processor core from among the plurality of processor cores based on a mapping.

4. The method of claim 1 , wherein the expanding further comprises:
preventing, by the storage controller, processing of at least one operation from the at least one remaining operation by the first processor core while the at least one remaining operation is migrated to a target processor core from among the plurality of processor cores.

5. The method of claim 1 , wherein the expanding further comprises:
determining, dynamically by the storage controller, a target processor core from among the plurality of processor cores.

6. The method of claim 1 , further comprising:
determining, by the storage controller dynamically before the expanding, a mapping of each of the at least one remaining operation to the plurality of processor cores based on a latency metric and a workload metric.

7. The method of claim 1 , further comprising:
remapping, by the storage controller, the at least one remaining operation among the plurality of processor cores in response to a change in component configuration of the storage controller.

8. A computing device comprising:
a memory having stored thereon instructions for performing a method of transitioning tasks and interrupt service routines between core configurations; and
a processor coupled to the memory, the processor configured to execute the instructions to:
execute, by a first core of the processor in a single-core configuration, one or more of the tasks and one or more of the interrupt service routines for an initialization sequence;
execute an application configured to manage migration from the single-core configuration to a multi-core configuration upon completion of the initialization sequence, the execution of the application being a trigger;
determine to transition from the single-core configuration to the multi-core configuration in response to of the trigger; and
migrate execution of a remaining plurality of tasks from the tasks and a remaining plurality of interrupt service routines from the first core of the processor to a second core of the processor in the multi-core configuration.

9. The computing device of claim 8 , the processor is further configured to execute the instructions to:
rebalance the remaining plurality of tasks and the remaining plurality of interrupt service routines among a plurality of cores including the first core and the second core in response to a performance metric meeting a threshold.

10. The computing device of claim 8 , the the processor is further configured to execute the instructions to:
migrate the remaining plurality of tasks and the remaining plurality of interrupt service routines to the second core of the processor based on a mapping.

11. The computing device of claim 8 , the processor is further configured to execute the instructions to:
prevent execution of the remaining plurality of tasks by the first core while the remaining plurality of tasks are migrated to the second core.

12. The computing device of claim 8 , the processor is further configured to execute the instructions to:
disable execution of the remaining plurality of interrupt service routines by the first core while the remaining plurality of interrupt service routines are migrated to the second core.

13. The computing device of claim 8 , the processor is further configured to execute the instructions to:
determine, dynamically before the migration, a mapping of each of the remaining plurality of tasks and the remaining plurality of interrupt service routines to a plurality of cores including the first core and the second core based on a latency metric and a workload metric.

14. The computing device of claim 8 , the processor is further configured to execute the instructions to:
remap the remaining plurality of tasks and the remaining plurality of interrupt service routines among a plurality of cores including the first core and the second core in response to a change in component configuration of the computing device.

15. A non-transitory machine-readable medium having stored thereon instructions for performing a method which when executed by at least one machine, causes the at least one machine to:
process, by a first processor core of the at least one machine in a single-core configuration, a first subset of a plurality of tasks and a first subset of a plurality of interrupt service routines that comprise operations for an initialization sequence;
execute an application configured to manage migration from the single-core configuration to a multi-core configuration upon completion of the initialization sequence, the executing the application being a trigger;
determine to transition from the single-core configuration to the multi-core configuration in response to the trigger; and
expand, from the first processor core, processing of a second subset of the plurality of tasks and a second subset of the plurality of interrupt service routines to a plurality of processor cores in the multi-core configuration.

16. The non-transitory machine-readable medium of claim 15 , wherein the instructions when executed further cause the at least one machine to:
rebalance the second subset of the plurality of tasks and the second subset of the plurality of interrupt service routines among the plurality of processor cores in response to a performance metric meeting a threshold.

17. The non-transitory machine-readable medium of claim 15 , wherein the instructions when executed further cause the at least one machine to:
prevent processing of the second subset of the plurality of tasks by the first processor core while the second subset of the plurality of tasks is migrated to at least one of the plurality of processor cores.

18. The non-transitory machine-readable medium of claim 15 , wherein the instructions when executed further cause the at least one machine to:
disable processing of the second subset of the plurality of interrupt service routines by the first processor core while the second subset of the plurality of interrupt service routines is migrated to at least one of the plurality of processor cores.

19. The non-transitory machine-readable medium of claim 15 , wherein the instructions when executed further cause the

Assignees

• Netapp Inc

Inventors

• Prosch Kent
• Weber Matthew
• Banerjee Arindam
• Mcdavitt Ben

Classifications

• G06F15/16 Primary

  Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs {(coordinating program control therefor G06F9/52; in regulating and control system G05B)} · CPC title

• G06F9/5083

  Techniques for rebalancing the load in a distributed system · CPC title

• G06F2209/482

  Application · CPC title

• G06F9/5061

  Partitioning or combining of resources · CPC title

• G06F9/4856 Primary

  resumption being on a different machine, e.g. task migration, virtual machine migration (G06F9/5088 takes precedence) · CPC title