Increasing resources for partition to compensate for input/output (I/O) recovery event

Patent metadata

Field	Value
Publication number	US-11327767-B2
Application number	US-201916376013-A
Country	US
Kind code	B2
Filing date	Apr 5, 2019
Priority date	Apr 5, 2019
Publication date	May 10, 2022
Grant date	May 10, 2022

Abstract

Embodiments of dynamically increasing the resources for a partition to compensate for an input/output (I/O) recovery event are provided. An aspect includes allocating a first set of resources to a partition that is hosted on a data processing system. Another aspect includes operating the partition on the data processing system using the first set of resources. Another aspect includes, based on detection of an input/output (I/O) recovery event associated with operation of the partition, determining a compensation for the I/O recovery event. Another aspect includes allocating a second set of resources in addition to the first set of resources to the partition, the second set of resources corresponding to the compensation for the I/O recovery event. Another aspect includes operating the partition on the data processing system using the first set of resources and the second set of resources.

First claim

What is claimed is:

1. A computer-implemented method comprising:
allocating a first set of resources comprising a set of processors to a partition that is hosted on a data processing system;
operating the partition on the data processing system using the first set of resources by operating the first set of processors at a steady state frequency;
detecting a non-catastrophic input/output (I/O) recovery event during operation of the partition using the first set of resources;
based on the detecting of the I/O recovery event during operation of the partition using the first set of resources, determining a compensation for the I/O recovery event, wherein the determined compensation comprises a time interval;
allocating a second set of resources in addition to the first set of resources to the partition, the second set of resources corresponding to the compensation for the I/O recovery event, wherein the second set of resources comprises a boosted frequency that is higher than the steady state frequency;
continuing operation of the partition on the data processing system using the first set of resources and the second set of resources by operating the set of processors at the boosted frequency for a duration of the time interval;
detecting a subsequent I/O recovery event during operation of the partition on the data processing system using the first set of resources and the second set of resources; and
allocating a third set of resources in addition to the first set of resources to the partition, the third set of resources corresponding to the compensation for the subsequent I/O recovery event, wherein an amount of the third set of resources is greater than an amount of the second set of resources; and
based on an elapsing of the time interval, removing the second set of resources and the third set of resources from the partition by resuming operation of the set of processors at the steady state frequency.

2. The method of claim 1 , further comprising:
determining a recovery delay based on the I/O recovery event;
determining whether the recovery delay is greater than a predetermined threshold; and
allocating the second set of resources to the partition based on the recovery delay being greater than the predetermined threshold.

3. The method of claim 2 , wherein the recovery delay is determined based on a type of the I/O recovery event.

4. The method of claim 2 , wherein the I/O recovery event comprises one of: a storage system warm start, a storage system failure, a missing interrupt, a channel path recovery, an I/O device timeout, an I/O link timeout, and an I/O storage system timeout; and
wherein the recovery delay is determined based on a measured duration of the I/O recovery event.

5. The method of claim 1 , further comprising:
adjusting billing information for the partition to exclude billing for the second set of resources that were allocated based on the compensation for the I/O recovery event.

6. The method of claim 1 , further comprising removing the second set of resources from the partition based on usage of a fixed amount of resources by the partition.

7. A system comprising:
a plurality of computing resources;
a plurality of partitions; and
a resource management module coupled with the plurality of partitions and the plurality of computing resources, the resource management module configured to:
allocate a first set of resources comprising a set of processors to a partition that is hosted on a data processing system;
operate the partition on the data processing system using the first set of resources by operating the first set of processors at a steady state frequency;
detect a non-catastrophic input/output (I/O) recovery event during operation of the partition using the first set of resources;
based on the detecting of the I/O recovery event during operation of the partition using the first set of resources, determine a compensation for the I/O recovery event, wherein the determined compensation comprises a time interval;
allocate a second set of resources in addition to the first set of resources to the partition, the second set of resources corresponding to the compensation for the I/O recovery event, wherein the second set of resources comprises a boosted frequency that is higher than the steady state frequency;
continue operation of the partition on the data processing system using the first set of resources and the second set of resources by operating the set of processors at the boosted frequency for a duration of the time interval;
detect a subsequent I/O recovery event during operation of the partition on the data processing system using the first set of resources and the second set of resources; and
allocate a third set of resources in addition to the first set of resources to the partition, the third set of resources corresponding to the compensation for the subsequent I/O recovery event, wherein an amount of the third set of resources is greater than an amount of the second set of resources; and
based on an elapsing of the time interval, remove the second set of resources and the third set of resources from the partition by resuming operation of the set of processors at the steady state frequency.

8. The system of claim 7 , wherein the resource management module is configured to:
determine a recovery delay based on the I/O recovery event;
determine whether the recovery delay is greater than a predetermined threshold; and
allocate the second set of resources to the partition based on the recovery delay being greater than the predetermined threshold.

9. The system of claim 8 , wherein the I/O recovery event comprises one of: a storage system warm start, a storage system failure, a missing interrupt, a channel path recovery, an I/O device timeout, an I/O link timeout, and an I/O storage system timeout; and
wherein the recovery delay is determined based on a type of the I/O recovery event.

10. The system of claim 8 , wherein the recovery delay is determined based on a measured duration of the I/O recovery event.

11. The system of claim 7 , wherein the system is configured to:
adjust billing information for the partition to exclude billing for the second set of resources that were allocated based on the compensation for the I/O recovery event.

12. The system of claim 7 , further comprising removing the second set of resources from the partition based on usage of a fixed amount of resources by the partition.

13. A computer program product comprising a computer readable storage medium having stored thereon program instructions executable by one or more processing devices to perform a method of comprising:
allocating a first set of resources comprising a set of processors to a partition that is hosted on a data processing system;
operating the partition on the data processing system using the first set of resources by operating the first set of processors at a steady state frequency;
detecting a non-catastrophic input/output (I/O) recovery event during operation of the partition using the first set of resources;
based on the detecting of the I/O recovery event during operation of the partition using the first set of resources, determining a compensation for the I/O recovery event, wherein the determined compensation comprises a time interval;
allocating a second set of resources in addition to the first set of resources to the partition, the second set of resources corresponding to the compensation for the I/O recovery event, wherein the second set of resources comprises a boosted frequency that is higher than the steady state frequency;
continuing operation of the partition on the data processing

Assignees

• IBM

Inventors

• Compton Scott B
• Sutton Peter
• Yudenfriend Harry M
• Riedy Dale F

Classifications

• G06F9/3861 Primary

  Recovery, e.g. branch miss-prediction, exception handling (error detection or correction G06F11/00) · CPC title

• G06F9/5061

  Partitioning or combining of resources · CPC title

• G06F2201/81

  Threshold · CPC title

• G06F11/3409 Primary

  for performance assessment · CPC title

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title