Dispersed storage write process

Patent metadata

Field	Value
Publication number	US-9354974-B2
Application number	US-201514792577-A
Country	US
Kind code	B2
Filing date	Jul 6, 2015
Priority date	Sep 30, 2005
Publication date	May 31, 2016
Grant date	May 31, 2016

Abstract

A method includes issuing write commands to DS storage units regarding encoded data slices. A write command causes a storage unit to store an encoded data slice, but not allow access to the stored encoded data slices. The method includes receiving write acknowledgements from at least some of DS storage units to produce received write acknowledgements. The method includes, when a write threshold number of the received write acknowledgements have been received within a given time frame, issuing commit commands to the DS storage units. A commit command causes the storage unit to allow access to the stored encoded data slice. The method includes, when the write threshold number of the received write acknowledgements have not been received within the given time frame, issuing rollback commands to the DS units. A rollback command causes the storage unit to continue to not allow access to the stored encoded data slice.

First claim

What is claimed is:

1. A method for execution by a dispersed storage (DS) processing module, the method comprises:
issuing write commands to DS storage units regarding a set of encoded data slices, wherein a data segment of data was dispersed storage error encoded to produce the set of encoded data slices, and wherein a write command of the write commands causes a storage unit of the storage units to store an encoded data slice of the set of encoded data slices, but not allow access to the stored encoded data slices;
receiving write acknowledgements from at least some of DS storage units to produce received write acknowledgements;
when a write threshold number of the received write acknowledgements have been received within a given time frame, issuing commit commands to the DS storage units, wherein a commit command of the commit commands causes the storage unit to allow access to the stored encoded data slice; and
when the write threshold number of the received write acknowledgements have not been received within the given time frame, issuing rollback commands to the DS units, wherein a rollback command of the rollback commands causes the storage unit to continue to not allow access to the stored encoded data slice.

2. The method of claim 1 further comprises:
the rollback command causing the storage unit to continue to not allow access to the stored encoded data slice by instructing the storage unit to delete the stored encoded data slice.

3. The method of claim 1 further comprises:
the commit command further causing the storage unit to not allow access to an old version of the encoded data slice.

4. The method of claim 1 further comprises:
receiving commit acknowledgements from at least some of the DS storage units within a second given time period; and
when a write threshold number of the received commit acknowledgements have been received, issuing finalize commands to the DS storage units, wherein a finalize command of the finalize commands causes the storage unit to delete a stored old version of the encoded data slice.

5. The method of claim 1 further comprises:
receiving commit acknowledgements from at least some of the DS storage units within a second given time period; and
when a write threshold number of the received commit acknowledgements have not been received, issuing undo commands to the DS storage units, wherein an undo command of the undo commands causes the storage unit to delete the stored encoded data slice.

6. The method of claim 5 further comprises:
the undo command further causing the storage unit to allow access to an old version of the encoded data slice.

7. The method of claim 1 , wherein the write command comprises:
a write operation code that includes the encoded data slice, a write instruction and a dispersed storage network (DSN) address of the encoded data slice.

8. A non-transitory computer readable memory device comprises:
a first memory section that stores operational instructions that, when read by a computing device, causes the computing device to:
issue write commands to DS storage units regarding a set of encoded data slices, wherein a data segment of data was dispersed storage error encoded to produce the set of encoded data slices, and wherein a write command of the write commands causes a storage unit of the storage units to store an encoded data slice of the set of encoded data slices, but not allow access to the stored encoded data slices;

a second memory section that stores operational instructions that, when read by the computing device, causes the computing device to:
receive write acknowledgements from at least some of DS storage units to produce received write acknowledgements; and

a third memory section that stores operational instructions that, when read by the computing device, causes the computing device to:
when a write threshold number of the received write acknowledgements have been received within a given time frame, issue commit commands to the DS storage units, wherein a commit command of the commit commands causes the storage unit to allow access to the stored encoded data slice; and
when the write threshold number of the received write acknowledgements have not been received within the given time frame, issue rollback commands to the DS units, wherein a rollback command of the rollback commands causes the storage unit to continue to not allow access to the stored encoded data slice.

9. The non-transitory computer readable memory device of claim 8 further comprises:
the rollback command causing the storage unit to continue to not allow access to the stored encoded data slice by instructing the storage unit to delete the stored encoded data slice.

10. The non-transitory computer readable memory device of claim 8 further comprises:
the commit command further causing the storage unit to not allow access to an old version of the encoded data slice.

11. The non-transitory computer readable memory device of claim 8 further comprises:
receiving commit acknowledgements from at least some of the DS storage units within a second given time period; and
when a write threshold number of the received commit acknowledgements have been received, issuing finalize commands to the DS storage units, wherein a finalize command of the finalize commands causes the storage unit to delete a stored old version of the encoded data slice.

12. The non-transitory computer readable memory device of claim 8 further comprises:
a fourth memory section that stores operational instructions that, when read by the computing device, causes the computing device to:
receive commit acknowledgements from at least some of the DS storage units within a second given time period; and
when a write threshold number of the received commit acknowledgements have not been received, issue undo commands to the DS storage units, wherein an undo command of the undo commands causes the storage unit to delete the stored encoded data slice.

13. The non-transitory computer readable memory device of claim 12 further comprises:
the undo command further causing the storage unit to allow access to an old version of the encoded data slice.

14. The non-transitory computer readable memory device of claim 8 , wherein the write command comprises:
a write operation code that includes the encoded data slice, a write instruction and a dispersed storage network (DSN) address of the encoded data slice.

Assignees

• Cleversafe Inc
• IBM

Inventors

• Clifone Bart
• Baptist Andrew
• Dhuse Greg
• Volvovski Ilya
• Resch Jason K

Classifications

• G06F11/1076 Primary

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title

• G06F2211/1028

  Distributed, i.e. distributed RAID systems with parity · CPC title

• G06F11/1092 Primary

  Rebuilding, e.g. when physically replacing a failing disk · CPC title

• G06F3/0607

  by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device · CPC title

• H04L67/1097

  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] · CPC title