# US 2021/0173792 A1 · Method and system for efficiently evicting data from memory slots in a storage system

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

- Number: US 2021/0173792 A1
- Document ID: US20210173792A1
- Status: Published application
- Kind: A1
- Application number: 16/705,323
- Filed: 2019-12-06
- Published: 2021-06-10
- Earliest claimed: 2019-12-06
- Assignees: EMC IP Holding Company LLC
- Applicants: EMC IP Holding Company LLC
- Inventors: Jonathan I. Krasner; Jason Jerome Duquette
- Web page: https://patentgrep.com/patent/US20210173792A1

## CPC

- G06F 12/0868: Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
- G06F 12/126: with special data handling, e.g. priority of data or instructions, handling errors or pinning
- G06F 3/0608: {Saving storage space on storage systems}
- G06F 3/0656: {Data buffering arrangements}
- G06F 3/0685: {Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays}
- G06N 5/04: Inference or reasoning models
- G06F 12/0238: {Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory}
- G06F 2212/1016: Performance improvement
- G06F 2212/152: Virtualized environment, e.g. logically partitioned system
- G06F 2212/214: Solid state disk
- G06F 2212/261: Storage comprising a plurality of storage devices
- G06F 2212/462: Track or segment
- G06F 2212/7204: Capacity control, e.g. partitioning, end-of-life degradation
- G06F 2212/7208: Multiple device management, e.g. distributing data over multiple flash devices
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for managing data includes generating, by an offload device, predicted active logical partition data using an active logical partition mapping obtained from a host computing device, generating logical partition correlation data using active memory track maps obtained from the host computing device, generating most probable tracks using the predicted active logical partition data and the logical partition correlation data, and sending the most probable tracks to the host computing device, wherein the host computing device evicts data from a memory device based on the most probable tracks.

## Claims

### Claim 1

A method for managing data, the method comprising:
generating, by an offload device, predicted active logical partition data using an active logical partition mapping obtained from a host computing device;
generating logical partition correlation data using active memory track maps obtained from the host computing device;
generating most probable tracks using the predicted active logical partition data and the logical partition correlation data; and
sending the most probable tracks to the host computing device,
wherein the host computing device evicts data from a memory device based on the most probable tracks.

### Claim 2 (depends on 1)

The method of claim 1, wherein the memory device comprises at least a plurality of memory slots.

### Claim 3 (depends on 1)

The method of claim 1, wherein the active logical partition mapping specifies a plurality of logical partitions, wherein each of the plurality of logical partitions is associated with a persistent storage device in the host computing device.

### Claim 4 (depends on 1)

The method of claim 1, wherein the method further comprises:
performing an error analysis on the most probable tracks to generate an error score; and
generating an error report based on the error score.

### Claim 5 (depends on 4)

The method of claim 4, wherein the error score is sent to the host computing device if the error score exceeds a significance of error.

### Claim 6 (depends on 1)

The method of claim 1, wherein the predicted active logical partition data is generated after an active logical partition predictor (ALPP) time interval.

### Claim 7 (depends on 1)

The method of claim 1,
wherein the active memory track maps specify a plurality of active tracks, and
wherein each active track in the plurality of active tracks is associated with at least one logical partition.

### Claim 8

A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for managing data the method comprising:
generating, by an offload device, predicted active logical partition data using an active logical partition mapping obtained from a host computing device;
generating logical partition correlation data using active memory track maps obtained from the host computing device;
generating most probable tracks using the predicted active logical partition data and the logical partition correlation data; and
sending the most probable tracks to the host computing device,
wherein the host computing device evicts data from one or more memory devices based on the most probable tracks.

### Claim 9 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein each memory device comprises at least a plurality of memory slots.

### Claim 10

The non-transitory computer readable medium of 8, wherein the active logical partition mapping specifies a plurality of logical partitions, wherein each of the plurality of logical partitions are associated with a persistent storage device in the host computing device.

### Claim 11

The non-transitory computer readable medium of 8, wherein the method further comprises:
performing an error analysis on the most probable tracks to generate an error score; and
generating an error report based on the error score.

### Claim 12 (depends on 11)

The non-transitory computer readable medium of claim 11, wherein the error score is sent to the host computing device if the error score exceeds a significance of error.

### Claim 13 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the predicted active logical partition data is generated after an active logical partition predictor (ALPP) time interval.

### Claim 14 (depends on 8)

The non-transitory computer readable medium of claim 8,
wherein the active memory track maps specify a plurality of active tracks, and
wherein each active track in the plurality of active tracks is associated with at least one logical partition.

### Claim 15

An offload device system, comprising:
a processor;
memory comprising instructions, which when executed by the processor, perform a method, the method comprising:
generating, by an offload device, predicted active logical partition data using an active logical partition mapping obtained from a host computing device;
generating logical partition correlation data using active memory track maps obtained from the host computing device;
generating most probable tracks using the predicted active logical partition data and the logical partition correlation data; and
sending the most probable tracks to the host computing device,
wherein the host computing device evicts data from one or more memory devices based on the most probable tracks

### Claim 16 (depends on 15)

The offload device of claim 15, wherein the memory device comprises at least a plurality of memory slots.

### Claim 17 (depends on 15)

The offload device of claim 15, wherein the active logical partition mapping specifies a plurality of logical partitions, wherein each of the plurality of logical partitions are associated with a persistent storage device in the host computing device.

### Claim 18 (depends on 15)

The offload device of claim 15, wherein the offload device is further programmed to:
perform an error analysis on the most probable tracks to generate an error score; and
generate an error report based on the error score.

### Claim 19 (depends on 18)

The offload device of claim 18, wherein the error score is sent to the host computing device if the error score exceeds a significance of error.

### Claim 20 (depends on 15)

The offload device of claim 15, wherein the predicted active logical partition data is generated after an active logical partition predictor (ALPP) time interval.
