Determining a device wear-rate

Patent metadata

Field	Value
Publication number	US-11429283-B2
Application number	US-202017083689-A
Country	US
Kind code	B2
Filing date	Oct 29, 2020
Priority date	Jul 8, 2016
Publication date	Aug 30, 2022
Grant date	Aug 30, 2022

Abstract

Example implementations relate to determining a device wear-rate. An example system for determining a device wear-rate can include a plurality of filter drivers to: monitor system requests for I/O associated with a device of the system and transmit information associated with the system requests to a filter manager. The system can also include the filter manager to catalog the information, a service to collate the information across a plurality of machine configurations and workloads, and a processor to determine a wear-rate of the device based on an analysis of the collated information.

First claim

What is claimed:

1. A device, comprising:
a processor resource; and
a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to:
tag input/output (I/O) system requests associated with a device;
catalog the tagged I/O system requests based on an application executing the I/O system requests;
compare the tagged I/O system requests to a data payload exercised against physical segments of the device; and
determine an impact of the application on the device based on the comparison of the tagged I/O system requests.

2. The device of claim 1 , wherein the processor resource is to monitor the I/O system requests from direct application programming interfaces.

3. The device of claim 1 , wherein the processor resource is to monitor the I/O system requests from a memory-mapped I/O.

4. The device of claim 1 , wherein the processor resource is to catalog the I/O system requests based on application context, amount of I/O, type of I/O, and time.

5. The device of claim 1 , wherein the processor resource is to analyze cataloged I/O system requests to determine groupings of commonality and determine an outlier within the tagged I/O system requests.

6. A method, comprising:
tagging information associated with input output (I/O) system requests from a plurality of applications on a plurality of devices within a system, wherein the plurality of applications utilize different I/O methods;
correlating the tagged information for the plurality of devices based on the plurality of applications associated with the tagged information;
determining outliers for the plurality of applications based on the correlation of the tagged information for the plurality of devices within the system, wherein the outliers are I/O system requests that have a higher failure probability than other I/O system requests that include similar behaviors;
correlating the outliers with other outliers exhibiting similar behavior on the plurality of devices within the system; and
determining failure probabilities for the plurality of devices within the system based on the correlation and the plurality of applications utilized by the plurality of devices in the system.

7. The method of claim 6 , wherein the outliers perform differently when devices have faster wear-rates as compared to other I/O system requests.

8. The method of claim 6 , further comprising creating a filtering subsystem of the system based on a wear-rate determination.

9. The method of claim 6 , further comprising comparing performances of each of the plurality of devices to one another based on an application load associated with each of the plurality of devices and an amount of time the application load was applied to each of the plurality of devices.

10. A non-transitory machine-readable medium storing instructions executable by a processing resource to cause a computing system to:
monitor interactions between a file system and an application layer of the computing system;
tag the interactions;
compare the tagged interactions to a data payload of the interactions exercised against physical segments of a plurality of system devices;
create device usage patterns based on the tagged interactions and data payload of the interactions against the physical segments;
collate the device usage patterns across a plurality of system devices using a network services layer and a database; and
determine an impact of the application layer on the plurality of system devices based on the device usage patterns of the plurality of system devices.

11. The non-transitory machine-readable medium of claim 10 , wherein the impact of the application layer includes modifications to I/O operations of a cache manager.

12. The non-transitory machine-readable medium of claim 10 , wherein the tag is monitored through an I/O process flow of interactions between the file system and the application layer of the computing system.

Assignees

• Hewlett Packard Development Co

Inventors

• Graham Christoph J
• Flynn Thomas J
• Herrera Virginia Quance

Classifications

• G06F11/3072 Primary

  where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting · CPC title

• G06F3/0653

  Monitoring storage devices or systems · CPC title

• G06F11/3055

  Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available (error or fault processing without redundancy G06F11/0703; error detection or correction by redundancy in data representation G06F11/08; error detection or correction of the data by redundancy in operations G06F11/14; error detection or correction by redundancy in hardware G06F11/16) · CPC title

• G06F11/3485

  for I/O devices · CPC title

• G06F11/3433

  for load management (allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029) · CPC title