Method and device for storage management

Patent metadata

Field	Value
Publication number	US-10521362-B2
Application number	US-201715628862-A
Country	US
Kind code	B2
Filing date	Jun 21, 2017
Priority date	Jun 21, 2016
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

Embodiments of the present disclosure provide a method and device for storage management. The method comprises receiving at a storage management device a configuration request for a storage space managed by the storage management device, the configuration request indicating a capacity of the storage space and a target size of a chunk in the storage space; and based on the capacity and the target size, dividing the storage space into a metadata region storing a chunk status indicator indicating whether the chunk is assigned with data and a data region including the chunk with the target size. Embodiments of the present disclosure also provide a corresponding device.

First claim

We claim:

1. A method for storage management, comprising:
receiving, at a storage management device, a configuration request for a storage space managed by the storage management device, the configuration request indicating a capacity of the storage space and a target size of a chunk in the storage space;
dividing, based on the capacity and the target size, the storage space into a metadata region storing a chunk status indicator indicating whether the chunk is assigned with data and a data region including the chunk with the target size;
dividing a plurality of chunks in the storage space into a plurality of clusters of chunks, each of the plurality of clusters of chunks including two or more chunks among the plurality of chunks;
determining, for a first cluster among the plurality of clusters of chunks, a cluster status indicator indicating whether the first cluster is assigned with data based on chunk status indicators of the two or more chunks included in the first cluster;
receiving, at the storage management device, a write request involving the first cluster; and
processing the write request based on the cluster status indicator of the first cluster,
wherein the processing the write request comprises:
in response to the cluster status indicator of the first cluster indicating that the first cluster is not assigned with data, writing data associated with the write request to at least one first chunk included in the first cluster; and
updating the cluster status indicator of the first cluster and a chunk status indicator of the at least one first chunk included in the first cluster; and

wherein the writing data to at least one first chunk included in the first cluster comprises:
in response to determining that the at least one first chunk includes a respective chunk to be partially used by the write request, writing predetermined filling data to a portion that is not to be used in the respective chunk by the write request.

2. The method of claim 1 , further comprising:
receiving, at the storage management device, a read request involving at least one cluster among the plurality of clusters of chunks; and
processing the read request based on a cluster status indicator of the at least one cluster involved in the read request.

3. The method of claim 2 , wherein the at least one cluster includes a second cluster, and the processing the read request comprises:
obtaining a cluster status indicator of the second cluster involved in the read request; and
in response to the cluster status indicator of the second cluster indicating that the second cluster is assigned with data, retrieving data stored in the second cluster associated with the read request.

4. The method, of claim 2 , wherein the at least one cluster includes a second cluster, and the processing the read request comprises:
obtaining a cluster status indicator of the second cluster involved in the read request; and
in response to the cluster status indicator of the second cluster indicating that the second cluster is not assigned with data, returning a predetermined response for the read request.

5. The method of claim 2 , wherein the at least one cluster includes a second cluster, and the processing the read request comprises:
obtaining a cluster status indicator of the second cluster involved in the read request;
in response to the cluster status indicator of the second cluster indicating that a status of the second cluster is unknown, obtaining chunk status indicators of chunks in the second cluster; and
processing the read request based on the obtained chunk status indicators.

6. The method of claim 5 , wherein the processing the read request based on the obtained chunk status indicators comprises:
in response to a chunk status indicator of a first chunk included in the second cluster indicating that the first chunk is assigned with data, retrieving data stored in the first chunk associated with the read request; and
in response to a chunk status indicator of a second chunk included in the second cluster indicating that the second chunk is not assigned with data, returning a predetermined response for the read request.

7. The method of claim 1 , wherein the at least one cluster includes a second cluster, and the processing the write request comprises:
obtaining a cluster status indicator of the second cluster involved in the write request; and
in response to the cluster status indicator of the second cluster indicating that the second cluster is assigned with data, writing data associated with the write request to the second cluster.

8. The method of claim 1 , wherein the at least one cluster includes a second cluster, and the processing the write request comprises:
obtaining a cluster status indication of the second cluster involved in the write request;
in response to the cluster status indicator of the second cluster indicating that a status of the second cluster is unknown, obtaining chunk status indicators of chunks in the second cluster; and
processing the write request based on the chunk status indicators of the chunks in the second cluster.

9. The method of claim 8 , wherein the processing the write request based on the chunk status indicators of the chunks in the second cluster comprises:
in response to a chunk status indicator of a second chunk included in the second cluster indicating that the second chunk is assigned with data, writing data associated with the write request to the second chunk; and
in response to the chunk status indicator of a third chunk included in the second cluster indicating that the third chunk is not assigned with data, writing data associated with the write request to the third chunk; and
updating the chunk status indicator of the third chunk and the cluster status indicator of the second cluster.

10. The method of claim 9 , wherein the writing data to the third chunk comprises:
in response to determining that the third chunk is to be only partially used by the write request, writing predetermined filling data to a portion that is not to be used in the third chunk by the write request.

11. A method for storage management, comprising:
receiving, at a storage management device, a configuration request for a storage space managed by the storage management device, the configuration request indicating a capacity of the storage space and a target size of a chunk in the storage space;
dividing, based on the capacity and the target size, the storage space into a metadata region storing a chunk status indicator indicating whether the chunk is assigned with data and a data region including the chunk with the target size;
dividing a plurality of chunks in the storage space into a plurality of clusters of chunks, each of the plurality of clusters of chunks including two or more chunks among the plurality of chunks;
determining, for a respective cluster among the plurality of clusters of chunks, a cluster status indicator indicating whether the respective cluster is assigned with data based on chunk status indicators of the two or more chunks included in the respective cluster;
receiving, at the storage management device, a storage release request; and
in response to determining that the storage release request is to release only a portion of a first chunk included in the plurality of chunks, overriding data associated with the release request in the first chunk with predetermined filling data.

12. A method for storage management, comprising:
receiving, at a storage management device, a configuration request for a storage space managed by the storage management device, the configuration request indicating a capacity of the storage space

Assignees

• Emc Ip Holding Co Llc

Inventors

• Dong Jibing
• Han Geng
• Gao Jian
• Kang Jamin Jianbin
• Gao Hongpo
• Li Huadong

Classifications

• G06F3/0671

  In-line storage system · CPC title

• G06F12/16 Primary

  Protection against loss of memory contents {(contains no material, see G06F11/00)} · CPC title

• G06F3/0604 Primary

  Improving or facilitating administration, e.g. storage management · CPC title

• G06F11/0727

  in a storage system, e.g. in a DASD or network based storage system (drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units 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) · CPC title

• G06F11/1458

  Management of the backup or restore process · CPC title