Storing and retrieving mutable objects

• US 10,042,577 B2
• Filed: 11/03/2016
• Issued: 08/07/2018
• Est. Priority Date: 01/04/2013
• Status: Expired due to Fees

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Leggette, Wesley B., Resch, Jason K., Smith, Eric G., Vas, Sebastien, Vedpathak, Yogesh R.
• Primary Examiner(s): Kerveros, James C
• Application Number:
  US15/342,238
• Publication Number:
  US 20170052733A1
• Time in Patent Office: 642 Days
• Field of Search: 714763
• CPC Class Codes: G06F 11/1008 in individual solid state devices G06F11/1004 takes precedence
• CPC Class Codes: G06F 11/1044 with specific ECC/EDC distribution
• CPC Class Codes: G06F 11/1068 in sector programmable memories, e.g. flash disk G06F11/1072 takes precedence
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), the method begins by identifying a data object to access within a DSN. The method continues by identifying a vault ID based on the data object. The method continues by obtaining an object ID based on the data object. The method continues by selecting at least one generation ID based on generation status. The method continues, for each generation ID, by generating at least one set of slice names using the vault ID, the generation ID, and the object ID. The method continues, for each set of slice names, by generating a set of slice access requests that includes the set of slice names and accessing the DSN utilizing the set of slice access requests.

Claims

1. A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), the method comprises:

identifying, by a dispersed storage module, a data object to access within a DSN vault, where the DSN vault includes a virtual memory block associated with a portion of an overall namespace of the DSN;

identifying, by a dispersed storage module, a vault ID based on the data object and the DSN vault, where the vault ID identifies a vault of the DSN associated with a data object requesting entity;

obtaining, by a dispersed storage module, an object ID based on the data object, where the object ID is retrieved from a DSN index lookup based on a data name and performing a deterministic function on the data name;

selecting, by a dispersed storage module, one or more generation IDs based on generation status, where the generation status is at least based on accessing a generation utilization list of a registry to identify a fullness level associated with each potential one of the one or more generation IDs for the DSN vault;

for each of the one or more generation IDs, generating, by a dispersed storage module, at least one set of slice names using the vault ID, the generation ID, and the object ID; and

for each set of slice names, generating, by a dispersed storage module, a set of slice access requests that includes the set of slice names; and

accessing, by a dispersed storage module, DSN storage units utilizing the set of slice access requests; and

wherein the accessing may further be based on a request type wherein, for a read request type, slice access responses are received, and favorable slice access responses decoded using a dispersed storage error coding function to reproduce one or more data segments of data and, for a write request type, storage of the data object is confirmed when receiving a write threshold number of favorable slice access responses from the DSN for each data segment of a plurality of data segments of the data.

2. The method of claim 1, wherein the dispersed storage module identifies a data object access request within a dispersed storage network (DSN).

3. The method of claim 2 wherein the identifying a data object to access within a DSN is based on receiving the data object access request that includes one or more of:

a data name, a requester identifier (ID), a vault ID, an object ID, a source name, or data.

4. The method of claim 1, wherein the identifying a vault ID is based on an ID lookup based on a data name.

5. The method of claim 1, wherein the identifying a vault ID is based on a data object requester ID.

6. The method of claim 1, wherein the obtaining further includes obtaining the object ID based on one or more of:

a request type, data, receiving the object ID, or a data name.

7. The method of claim 1, wherein the generation status further indicates availability of one or more generation IDs.

8. The method of claim 1, wherein the fullness level indicates full or not full.

9. The method of claim 1, wherein the selecting further includes selecting the generation IDs based on one or more of:

a request type and the generation status.

10. The method of claim 1, wherein the selecting, for a read request, includes selecting each of the generation IDs associated with a generation status that indicates that a generation is full and selects a generation ID that is one greater than a largest generation ID of one or more generation IDs that are full, if any.

11. The method of claim 1, wherein the selecting, for a write request, selecting a lowest generation ID associated with a generation that is not full.

12. The method of claim 1, wherein the generating, for a write request, includes a set of slice names and includes a set of encoded data slices that are encoded, using a dispersed storage error coding function, from a corresponding data segment of the data.

13. The method of claim 1, wherein the generating, for a read request, the processing module includes a set of slice names.

14. The method of claim 1, wherein the accessing includes outputting the set of slice access requests to the DSN.

15. A computing device of a group of computing devices of a dispersed storage network (DSN), the computing device comprises:

an interface;

a local memory; and

a dispersed storage module operably coupled to the interface and the local memory, wherein the processing module functions to;

identify a data object to access within a DSN vault, where the DSN vault includes a virtual memory block associated with a portion of an overall namespace of the DSN;

identify a vault ID based on the data object and the DSN vault, where the vault ID identifies a vault of the DSN associated with a data object requesting entity;

obtain an object ID based on the data object, where the object ID is retrieved from a DSN index lookup based on a data name and performing a deterministic function on the data name;

select at least one or more generation IDs based on generation status, where the generation status is at least based on accessing a generation utilization list of a registry to identify a fullness level associated with each potential one of the one or more generation IDs for the DSN vault;

for each of the one or more generation IDs, generate at least one set of slice names using the vault ID, the generation ID, and the object ID; and

for each set of slice names, generate a set of slice access requests that includes the set of slice names; and

access DSN storage units utilizing the set of slice access requests, and

wherein the access may further be based on a request type wherein, for a read request type, slice access responses are received, and favorable slice access responses decoded using a dispersed storage error coding function to reproduce one or more data segments of the data and, for a write request type, storage of the data object is confirmed when receiving a write threshold number of favorable slice access responses from the DSN for each data segment of a plurality of data segments of the data.

16. A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), the method comprises:

receiving, by a dispersed storage module, a data name for retrieval from DSN storage units;

identifying, by a dispersed storage module, a data object based on the data name to access within a DSN vault, where the DSN vault includes a virtual memory block associated with a portion of an overall namespace of the DSN;

identifying, by a dispersed storage module, a vault ID based on the data object and the DSN vault, where the vault ID identifies a vault of the DSN associated with a data object requesting entity;

obtaining, by a dispersed storage module, an object ID based on the data object, where the object ID is retrieved from a DSN index lookup based on a data name and performing a deterministic function on the data name;

selecting, by a dispersed storage module, each generation of the DSN vault that is full for a corresponding source name and a next generation of the DSN vault after a last full generation, where a DSN vault is full at least based on accessing a generation utilization list of a registry to identify a fullness level associated with each potential generation IDs for the DSN vault;

for each generation of the DSN vault selected, generating, by a dispersed storage module, at least one set of slice names using the vault ID, a generation ID, and the object ID; and

for each set of slice names, generating, by a dispersed storage module, a set of slice access requests to read slices that includes the set of slice names; and

outputting, by a dispersed storage module, the slice access requests to a DS (dispersed storage) unit set;

receiving, by a dispersed storage module, at least a decode threshold of the set of slices; and

decoding, by a dispersed storage module, the received slices to produce the data object.