# US 2019/0377494 A1 · Placement of host data based on data characteristics

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

- Number: US 2019/0377494 A1
- Document ID: US20190377494A1
- Status: Published application
- Kind: A1
- Application number: 16/101,158
- Filed: 2018-08-10
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Western Digital Technologies, Inc.
- Applicants: Western Digital Technologies, Inc.
- Inventors: Abhijit RAO; Vishwas SAXENA
- Web page: https://patentgrep.com/patent/US20190377494A1

## CPC

- G06F 3/064: {Management of blocks}
- G06F 3/061: {Improving I/O performance}
- G06F 3/0616: {in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]}
- G06F 3/0652: {Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket}
- G06F 3/0679: {Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]}
- G06F 12/0246: {in block erasable memory, e.g. flash memory}
- G06F 2212/1016: Performance improvement
- G06F 2212/1036: Life time enhancement
- G06F 2212/7201: Logical to physical mapping or translation of blocks or pages
- G06F 2212/7205: Cleaning, compaction, garbage collection, erase control
- G06F 2212/7207: management of metadata or control data
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Methods for classifying data in a storage device are provided. A data classifier module in a controller calculates a placement factor of one or more streams of data associated with one or more logical block addresses based on a metadata update and recency count table. The data classifier module then classifies the one or more streams of data associated with one or more logical block addresses as hot, warm, or cold streams of data. Hot streams of data are routed to hot open memory blocks, warm streams of data are routed to warm open memory blocks, and cold streams of data are routed to cold open memory blocks. Routing streams of data to hot, warm, or cold open memory blocks results in more efficient garbage collection procedures and the reduction of block erasures.

## Claims

### Claim 1

A method for classifying data in a data storage device, comprising:
receiving, by a controller of the data storage device, one or more streams of data associated with one or more logical block addresses;
calculating a placement factor for each of the one or more logical block addresses;
calculating an average placement factor based on the total number of logical block addresses in the data storage device;
comparing the placement factor of each of the one or more logical block addresses to the average placement factor;
classifying each of the one or more logical block addresses as hot logical block addresses, warm logical block addresses, or cold logical block addresses based on the comparison of the placement factor of each of the one or more logical block addresses to the average placement factor; and
routing each of the one or more streams of data associated with the hot logical block addresses to a hot open memory block of the data storage device, each of the one or more streams of data associated with the warm logical block addresses to a warm open memory block of the data storage device, and each of the one or more streams of data associated with the cold logical block addresses to a cold open memory block of the data storage device.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
determining whether the each of the one or more logical block addresses has undergone one or more overwrites; and
routing each of the one or more streams of data associated with the one or more logical block addresses that have been determined not to have undergone one or more overwrites to a cold open memory block of the data storage device.

### Claim 3 (depends on 1)

The method of claim 1, further comprising: updating, in a data classifier module of the data storage device, a metadata update and recency count table for each of the one or more logical block addresses, wherein the metadata update and recency count table is utilized in calculating the placement factor for each of the one or more logical block addresses.

### Claim 4 (depends on 3)

The method of claim 3, wherein the metadata update and recency count table comprises a metadata entry update count for each of the one or more logical block addresses and a recency count for each of the one or more logical block addresses.

### Claim 5 (depends on 4)

The method of claim 4, wherein the metadata entry update count is directly proportional to the number of times a logical block address has been referenced.

### Claim 6 (depends on 4)

The method of claim 4, wherein the metadata entry update count is increased if a logical block address has been overwritten or updated.

### Claim 7 (depends on 4)

The method of claim 4, wherein the recency count comprises a time stamp associated with each of the one or more logical block addresses, and wherein the time stamp increases when a corresponding logical block address has been updated.

### Claim 8 (depends on 7)

The method of claim 7, wherein the recency count of a logical block address is increased each time the time stamp is increased.

### Claim 9 (depends on 4)

The method of claim 4, wherein the placement factor is equal to a predetermined metadata update count weightage multiplied by the metadata update count for the logical block address added to a predetermined recency count weightage multiplied by the recency count for the logical block address.

### Claim 10 (depends on 9)

The method of claim 9, wherein the average placement factor is equal to a sum of the total placement factors for all valid logical block addresses divided by the total number of valid un-erased logical block addresses.

### Claim 11 (depends on 1)

The method of claim 1, wherein a logical block address is classified as hot if the placement factor of the logical block address is greater than the average placement factor.

### Claim 12 (depends on 1)

The method of claim 1, wherein a logical block address is classified as cold if the placement factor of the logical block address is lower than 50% of the average placement factor.

### Claim 13 (depends on 1)

The method of claim 1, wherein a logical block address is classified as warm if the placement factor of the logical block address is greater than 50% of the average placement factor but less than 100% of the average placement factor.

### Claim 14

A method for classifying data in a data storage device, comprising:
receiving, by a controller of the data storage device, one or more streams of data associated with one or more logical block addresses;
determining that there is a stream switch of the one or more streams of data;
determining whether each of the one or more streams of data that have been determined to have undergone a stream switch have further undergone one or more overwrites;
calculating, in a data classifier module of the data storage device, a placement factor for each of the one or more streams of data that have been determined to have undergone one or more overwrites;
classifying each of the one or more streams of data as hot streams of data or warm streams of data based on the placement factor of each of the one or more streams of data; and
routing the hot streams of data to a hot open memory block of a plurality of memory blocks and the warm streams of data to a warm open memory block of the plurality of memory blocks.

### Claim 15 (depends on 14)

The method of claim 14, wherein the one or more streams of data are sequential streams of data.

### Claim 16 (depends on 14)

The method of claim 14, further comprising: classifying each of the one or more streams of data as cold streams of data, and routing the cold streams of data to a cold open memory block of the plurality of memory blocks.

### Claim 17 (depends on 14)

The method of claim 14, wherein the placement factor is based on a metadata update and recency count table for each of the one or more streams of data.

### Claim 18

A data storage device, comprising:
one or more memory devices comprising a plurality of memory blocks;
a controller coupled to the one or more memory devices, wherein the controller is configured to receive one or more streams of data associated with one or more logical block addresses;
a random access memory coupled to the controller, wherein the random access memory includes a flash transition layer and a log page coupled to the one or more memory devices; and
a data classifier module located in the random access memory, the data classifier module coupled to the controller and the plurality of memory blocks, wherein the data classifier module is configured to store a metadata entry update count and a recency count of each of the one or more logical block addresses, and wherein the metadata update and recency count table is stored in the log page.

### Claim 19 (depends on 18)

The data storage device of claim 18, wherein the data classifier module is further configured to calculate a placement factor of the one or more logical block addresses.

### Claim 20 (depends on 19)

The data storage device of claim 19, wherein the data classifier module is further configured to classify each of the one or more streams of data as hot, warm, or cold based on the placement factor of each of the one or more streams of data.

### Claim 21 (depends on 20)

The data storage device of claim 20, wherein the data classifier module is further configured to route each of the one or more streams of data to a hot open memory block of the plurality of memory blocks, a warm open memory block of the plurality of memory blocks, or a cold open memory block of plurality of memory blocks based on the classification of each of the one or more streams of data as hot, warm, or cold.

### Claim 22

A data storage device, comprising:
one or more memory devices comprising a plurality of memory blocks;
means for receiving one or more streams of data associated with one or more logical block addresses;
means for updating a metadata update and recency count table for each of the one or more logical block addresses;
means for calculating a placement factor for each of the one or more streams of data associated with the one or more logical block addresses based on the metadata update and recency count table;
means for classifying each of the one or more streams of data associated with the one or more logical block addresses as hot streams of data, warm streams of data, or cold streams of data based on the placement factor; and
means for routing the hot streams of data to a hot open memory block of the plurality of memory blocks, routing the warm streams of data to a warm open memory block of the plurality of memory blocks, and routing the cold streams of data to a cold open memory block of the plurality of memory blocks.

### Claim 23 (depends on 22)

The data storage device of claim 22, further comprising: means for comparing the placement factor of each of the one or more streams of data associated with the one or more logical block addresses to an average placement factor.

### Claim 24

A data storage system, comprising:
a host device; and
a storage device coupled to the host device, the storage device comprising:
one or more memory devices comprising a plurality of memory blocks;
a controller coupled to the one or more memory devices, wherein the controller is configured to receive one or more streams of data from the host device; and
a data classifier module coupled to the controller and the one or more memory devices, wherein the data classifier module is configured to classify each of the one or more streams of data as hot, warm, or cold based on a placement factor of each of the one or more streams of data, and route each of the one or more streams of data to a hot open memory block of the plurality of memory blocks, a warm open memory block of the plurality of memory blocks, or a cold open memory block of plurality of memory blocks based on the classification of each of the one or more streams of data as hot, warm, or cold.

### Claim 25 (depends on 24)

The data storage system of claim 24, wherein the one or more streams of data are sequential streams of data.

### Claim 26 (depends on 24)

The data storage system of claim 24, wherein the storage device further includes a storage address table module.

### Claim 27 (depends on 24)

The data storage system of claim 24, wherein the data classifier module is further configured to calculate the placement factor of the one or more streams of data.
