Content addressable storage system utilizing content-based and address-based mappings

Patent metadata

Field	Value
Publication number	US-10296451-B1
Application number	US-201816177890-A
Country	US
Kind code	B1
Filing date	Nov 1, 2018
Priority date	Nov 1, 2018
Publication date	May 21, 2019
Grant date	May 21, 2019

Abstract

A storage system in one embodiment comprises a plurality of storage devices and a storage controller. The storage controller is configured to receive a plurality of logical addresses. Each logical address has one of a content-based mapping type and an address-based mapping type. Responsive to a first logical address of the plurality of logical addresses having the content-based mapping type, the storage controller is configured to utilize a content-based mapping generated based on content of a data page associated with the first logical address to identify a corresponding physical address. Responsive to a second logical address of the plurality of logical addresses having the address-based mapping type, the storage controller is configured to utilize an address-based mapping generated based on the second logical address to identify a corresponding physical address.

First claim

What is claimed is:

1. An apparatus comprising:
a storage system comprising a plurality of storage devices and a storage controller;
the storage controller being configured:
to receive a plurality of logical addresses, each logical address having one of a content-based mapping type and an address-based mapping type;
responsive to a first logical address of the plurality of logical addresses having the content-based mapping type, to utilize a content-based mapping generated based on content of a data page associated with the first logical address to identify a corresponding physical address; and
responsive to a second logical address of the plurality of logical addresses having the address-based mapping type, to utilize an address-based mapping generated based on the second logical address to identify a corresponding physical address;

wherein the storage controller is implemented by at least one processing device comprising a processor coupled to a memory.

2. The apparatus of claim 1 wherein the storage controller is further configured to determine the mapping type of each logical address based at least in part on information contained in a metadata structure associated with the plurality of logical addresses.

3. The apparatus of claim 2 wherein the information contained in the metadata structure comprises a flag corresponding to each logical address, the flag corresponding to a given logical address indicating whether the given logical address has the content-based mapping type or the address-based mapping type.

4. The apparatus of claim 2 wherein the information contained in the metadata structure comprises an entry for each logical address, each entry comprising a hash value associated with the corresponding logical address.

5. The apparatus of claim 4 wherein the hash value for an entry corresponding to a given logical address having the content-based mapping type comprises a content-based signature generated based on content of a data page associated with the given logical address.

6. The apparatus of claim 4 wherein the hash value for an entry corresponding to a given logical address having the address-based mapping type comprises a hash of the given logical address.

7. The apparatus of claim 1 wherein data pages associated with logical addresses having the address-based mapping type are not deduplicated by the storage system.

8. The apparatus of claim 1 wherein the mapping generated based on the second logical address comprises a mapping to a range of physical addresses, the range of physical addresses comprising the physical address corresponding to the second logical address.

9. The apparatus of claim 8 wherein the second logical address comprises a base logical address in a range of logical addresses having the address-based mapping type, the storage controller further configured:
to identify an offset of a given logical address in the range of logical addresses relative to the base logical address;
to utilize the identified physical address corresponding to the second physical address as a base physical address in the range of physical addresses; and
to identify a physical address corresponding to the given logical address from the range of physical addresses using the identified offset as an offset relative to the base physical address.

10. The apparatus of claim 8 wherein the range of physical addresses comprises a redundant array of independent disks (RAID) stripe distributed across the plurality of storage devices.

11. The apparatus of claim 1 wherein the plurality of storage devices are configured to store data corresponding to logical addresses having the address-based mapping type in a first volume and to store data corresponding to logical addresses having the content-based mapping type in a second volume different than the first volume.

12. The apparatus of claim 11 wherein the plurality of storage devices are configured to store data corresponding to logical addresses having the address-based mapping type and data corresponding to logical addresses having the content-based mapping type together in the same volume.

13. A method comprising:
receiving a plurality of logical addresses, each logical address having one of a content-based mapping type and an address-based mapping type;
responsive to a first logical address of the plurality of logical addresses having the content-based mapping type, utilizing a content-based mapping generated based on content of a data page associated with the first logical address to identify a corresponding physical address; and
responsive to a second logical address of the plurality of logical addresses having the address-based mapping type, utilizing an address-based mapping generated based on the second logical address to identify a corresponding physical address;
wherein the method is implemented by at least one processing device comprising a processor coupled to a memory.

14. The method of claim 13 wherein the method further comprises determining the mapping type of each logical address based at least in part on information contained in a metadata structure associated with the plurality of logical addresses.

15. The method of claim 14 wherein the information contained in the metadata structure comprises a flag corresponding to each logical address, the flag corresponding to a given logical address indicating whether the given logical address has the content-based mapping type or the address-based mapping type.

16. The method of claim 14 wherein the information contained in the metadata structure comprises an entry for each logical address, each entry comprising a hash value associated with the corresponding logical address,
wherein the hash value for an entry corresponding to a given logical address having the content-based mapping type comprises a content-based signature generated based on content of a data page associated with the given logical address, and
wherein the hash value for an entry corresponding to a given logical address having the address-based mapping type comprises a hash of the given logical address.

17. The method of claim 13 wherein data pages associated with logical addresses having the address-based mapping type are not deduplicated by the storage system.

18. The method of claim 13 wherein the mapping generated based on the second logical address comprises a mapping to a range of physical addresses, the range of physical addresses comprising the physical address corresponding to the second logical address.

19. The method of claim 18 wherein the second logical address comprises a base logical address in a range of logical addresses having the address-based mapping type, the method further comprising:
identifying an offset of a given logical address in the range of logical addresses relative to the base logical address;
utilizing the identified physical address corresponding to the second physical address as a base physical address in the range of physical addresses; and
identifying a physical address corresponding to the given logical address from the range of physical addresses using the identified offset as an offset relative to the base physical address.

20. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device:
to receive a plurality of logical addresses, each logical address having one of a co

Assignees

• Emc Ip Holding Co Llc

Inventors

• Schneider Zvi
• Alkalay Amitai
• Natanzon Assaf

Classifications

• G06F2212/7207

  management of metadata or control data · CPC title

• G06F2212/151

  Emulated environment, e.g. virtual machine · CPC title

• G06F2212/262

  configured as RAID · CPC title

• G06F12/0238 Primary

  Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory · CPC title

• G06F2212/1016

  Performance improvement · CPC title