# US 2021/0342205 A1 · Method and apparatus for predicting hard drive failure

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0342205 A1
- Document ID: US20210342205A1
- Status: Published application
- Kind: A1
- Application number: 16/864,766
- Filed: 2020-05-01
- Published: 2021-11-04
- Earliest claimed: 2020-05-01
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Patrick Mcguinness; Nagendra-Vikas Kamath; Elmira M. Bonab; WeiTa Chen; Joe Ray
- Web page: https://patentgrep.com/patent/US20210342205A1

## CPC

- G06F 11/008: {Reliability or availability analysis}
- G06F 3/0616: {in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]}
- G06F 3/0653: {Monitoring storage devices or systems}
- G06F 3/0683: {Plurality of storage devices}
- G06F 11/0772: {Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers}
- G06F 11/3034: {where the computing system component is a storage system, e.g. DASD based or network based (digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097)}
- G06F 11/3058: {Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations (thermal management in cooling arrangements of a computing system G06F1/206)}
- G06F 11/3409: {for performance assessment}
- G06F 11/3457: {Performance evaluation by simulation}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method is provided, comprising: retrieving telemetry data from a first storage device; generating a failure risk score for the first storage device, the failure risk score being generated by using a failure inference engine, the failure inference engine being arranged to execute a predictive failure model for calculating the failure risk score; and outputting the failure risk score for use in servicing the first storage device.

## Claims

### Claim 1

A method comprising:
retrieving telemetry data from a first storage device;
generating a failure risk score for the first storage device, the failure risk score being generated by using a failure inference engine, the failure inference engine being arranged to execute a predictive failure model for calculating the failure risk score; and
outputting the failure risk score for use in servicing the first storage device.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the telemetry data includes manufacturer-specific data and standard telemetry data;
the manufacturer-specific data is obtained by using a first collector, the first collector being arranged to provide, to the first storage device, a key for unlocking manufacturer-specific logs that are maintained by the controller; and
the standard telemetry data is obtained by using a second collector.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
providing, to a management system, an identifier corresponding to the first storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is selected, by the management system, based on the identifier corresponding to the first storage device.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
providing, to a management system, an identifier corresponding to the first storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is trained, by the management system, based on training data that is selected based on the identifier corresponding to the first storage device.

### Claim 5 (depends on 1)

The method of claim 1, wherein the telemetry data identifies one or more of fly height, temperature, duty cycle, and vibration of the first storage device.

### Claim 6 (depends on 1)

The method of claim 1, wherein outputting the failure risk score include providing the failure risk score to a management system.

### Claim 7 (depends on 1)

The method of claim 1, wherein outputting the failure risk score includes providing the failure risk score to a risk score analyzer, the risk score analyzer including logic that is arranged to execute a preemptive maintenance action for the first storage device when the failure risk score satisfies a predetermined condition.

### Claim 8

A system comprising:
a storage device; and
at least one processor operatively coupled to the storage device, the at least one processor being configured to perform the operations of:
retrieving telemetry data from a storage device;
generating a failure risk score for the storage device, the failure risk score being generated by using a failure inference engine, the failure inference engine being arranged to execute a predictive failure model for calculating the failure risk score; and
outputting the failure risk score for use in servicing the storage device.

### Claim 9 (depends on 8)

The system of claim 8, wherein:
the telemetry data includes manufacturer-specific data and standard telemetry data;
the manufacturer-specific data is obtained by using a first collector, the first collector being arranged to provide, to a controller of the storage device, a key for unlocking manufacturer-specific logs that are maintained by the controller; and
the standard telemetry data is obtained by using a second collector.

### Claim 10 (depends on 8)

The system of claim 8, wherein the at least one processor is further configured to perform the operations of:
providing, to a management system, an identifier corresponding to the storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is selected, by the management system, based on the identifier corresponding to the storage device.

### Claim 11 (depends on 8)

The system of claim 8, wherein the at least one processor is further configured to perform the operations of:
providing, to a management system, an identifier corresponding to the storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is trained, by the management system, based on training data that is selected based on the identifier corresponding to the storage device.

### Claim 12 (depends on 8)

The system of claim 8, wherein the telemetry data identifies one or more of fly height, temperature, duty cycle, and vibration of the storage device.

### Claim 13 (depends on 8)

The system of claim 8, wherein outputting the failure risk score include providing the failure risk score to a management system.

### Claim 14 (depends on 8)

The system of claim 8, wherein outputting the failure risk score includes providing the failure risk score to a risk score analyzer, the risk score analyzer including logic that is arranged to execute a preemptive maintenance action for the storage device when the failure risk score satisfies a predetermined condition.

### Claim 15

A non-transitory, computer-readable medium storing one or more processor-executable instructions, which when executed by at least one processor further cause the at least one processor to perform the operations of:
retrieving telemetry data from a first storage device;
generating a failure risk score for the first storage device, the failure risk score being generated by using a failure inference engine, the failure inference engine being arranged to execute a predictive failure model for calculating the failure risk score; and
outputting the failure risk score for use in servicing the first storage device.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein:
the telemetry data includes manufacturer-specific data and standard telemetry data;
the manufacturer-specific data is obtained by using a first collector, the first collector being arranged to provide, to the first storage device, a key for unlocking manufacturer-specific logs that are maintained by the controller; and
the standard telemetry data is obtained by using a second collector.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more processor-executable instructions, when executed by the at least one processor, further cause the at least one processor to perform the operations of:
providing, to a management system, an identifier corresponding to the first storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is selected, by the management system, based on the identifier corresponding to the first storage device.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more processor-executable instructions, when executed by the at least one processor, further cause the at least one processor to perform the operations of:
providing, to a management system, an identifier corresponding to the first storage device;
receiving the predictive failure model from the management system; and
causing the failure inference engine to execute the predictive failure model,
wherein the predictive failure model is trained, by the management system, based on training data that is selected based on the identifier corresponding to the first storage device.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the telemetry data identifies one or more of fly height, temperature, duty cycle, and vibration of the first storage device.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein outputting the failure risk score include providing the failure risk score to a management system.
