Keeping synchronized writes from getting out of synch

• US 10,623,495 B2
• Filed: 12/04/2017
• Issued: 04/14/2020
• Est. Priority Date: 12/31/2014
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Pure Storage, Inc.
• Inventors: Gray, Adam M., Dhuse, Greg R., Baptist, Andrew D., Khadiwala, Ravi V., Leggette, Wesley B., Horan, Scott M., Borich, Franco V., Cilfone, Bart R., Scholl, Daniel J.
• Primary Examiner(s): Shin, Kyung H
• Application Number:
  US15/830,321
• Publication Number:
  US 20180091595A1
• Time in Patent Office: 862 Days
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: H04L 47/28 in relation to timing considerations
• CPC Class Codes: H04L 67/1097 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]

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 receiving a portion of a data stream from a requesting entity for storage in a plurality of storage vaults. The method continues by encoding the portion of the data stream in accordance with dispersal parameters of the storage vault to produce a corresponding plurality of sets of encoded data slices. The method continues by facilitating storage of the corresponding plurality of sets of encoded data slices in the storage vault. The method continues by determining an ingestion rate capability level for the plurality of storage vaults and issuing stream pacing information to the requesting entity based on the ingestion rate capability level.

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:

receiving a portion of a data stream from a requesting entity for storage in a plurality of storage vaults;

encoding, for each of the plurality of storage vaults, the portion of the data stream in accordance with dispersal parameters of a corresponding one of the storage vaults to produce a corresponding plurality of sets of encoded data slices;

facilitating storage of the corresponding plurality of sets of encoded data slices in the plurality of storage vaults;

determining an ingestion rate capability level for the plurality of storage vaults, wherein the ingestion rate capability level is based on a fastest storage vault ingestion rate, a slowest storage vault ingestion rate and a maximum allowable difference in data storage; and

issuing stream pacing information to the requesting entity based on the ingestion rate capability level.

2. The method of claim 1, wherein the fastest storage vault ingestion rate and the slowest storage vault ingestion rate is based on respective received slice information.

3. The method of claim 2 further comprises determining the fastest storage vault ingestion rate for the fastest storage vault and the slowest storage vault ingestion rate for the slowest storage vault.

4. The method of claim 3, wherein the fastest storage vault ingestion rate and the slowest storage vault ingestion rate are determined by dividing a size of the portion of a data stream by a storage time.

5. The method of claim 4 further comprises identifying a maximum allowable difference in data stored based on the fastest storage vault ingestion rate, the slowest storage vault ingestion rate and a processing capacity level.

6. The method of claim 1, wherein the encoding includes obtaining the dispersal parameters for the storage vault and dispersed storage error encodes the portion of the data stream using the dispersal parameters to produce the plurality of sets of encoded data slices when substantially same dispersal parameters have not already been utilized to produce encoded data slices for another storage vault.

7. The method of claim 1, wherein the facilitating storage includes issuing write slice requests to the storage vault, where the write slice requests include the corresponding plurality of sets of encoded data slices, receives read slice responses, and timestamps write slice responses when receiving responses to produce an ingestion rate for a corresponding storage vault.

8. The method of claim 7, wherein the ingestion rate includes required memory and processing resource utilization levels that are within capability and capacity limitations.

9. The method of claim 1, wherein the stream pacing information includes one or more of:

the ingestion rate capability level for the plurality of storage vaults, a desired portion size, an estimated time of data transmission, a request to stop sending the data stream, or a request to resume sending of the data stream.

10. 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 processing module operably coupled to the interface and the local memory, wherein the processing module functions to;

receive a portion of a data stream from a requesting entity for storage in a plurality of storage vaults;

for each of the plurality of storage vaults, encode the portion of the data stream in accordance with dispersal parameters of a corresponding one of the storage vaults to produce a corresponding plurality of sets of encoded data slices;

for each of the plurality of storage vaults, facilitate storage of the corresponding plurality of sets of encoded data slices in the corresponding one of the storage vaults;

determine an ingestion rate capability level for the plurality of storage vaults, wherein the ingestion rate capability level is based on a fastest storage vault ingestion rate, a slowest storage vault ingestion rate and a maximum allowable difference in data storage; and

issue stream pacing information to the requesting entity based on the ingestion rate capability level.

11. The computing device of claim 10, wherein the encoding includes obtaining the dispersal parameters for the storage vault and dispersed storage error encodes the portion of the data stream using the dispersal parameters to produce the plurality of sets of encoded data slices when substantially same dispersal parameters have not already been utilized to produce encoded data slices for another storage vault.

12. The computing device of claim 10, wherein the facilitate storage includes issuing write slice requests to the storage vault, where the write slice requests include the corresponding plurality of sets of encoded data slices, receives read slice responses, and timestamps write slice responses when receiving responses to produce an ingestion rate for a corresponding storage vault.

13. The computing device of claim 12, wherein the ingestion rate includes required memory and processing resource utilization levels that are within capability and capacity limitations.

14. The computing device of claim 10, wherein the stream pacing information includes one or more of:

the ingestion rate capability level for the plurality of storage vaults, a desired portion size, an estimated time of data transmission, a request to stop sending the data stream, or a request to resume sending of the data stream.

15. The computing device of claim 10, wherein the determine an ingestion rate capability level includes determining a fastest storage vault and a slowest storage vault based on received slice information.

16. The computing device of claim 10, wherein the fastest storage vault ingestion rate and the slowest storage vault ingestion rate are determined by dividing a size of the portion of a data stream by a storage time.

17. The computing device of claim 16 further comprises identifying a processing capacity level.

18. 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 a portion of a data stream from a requesting entity for storage in a plurality of storage vaults included in a synchronized set of storage vaults;

for each storage vault, encoding the portion of the data stream in accordance with dispersal parameters of the storage vault to produce a corresponding plurality of sets of encoded data slices;

for each storage vault, facilitating storage of the corresponding plurality of sets of encoded data slices in the storage vault;

determining a fastest storage vault and a slowest storage vault based on received slice information;

determining an ingestion rate capability level for the plurality of storage vaults based on the determined fastest and slowest storage vault; and

issuing stream pacing information to the requesting entity based on the ingestion rate capability level.

19. The method of claim 18, wherein the determining an ingestion rate capability level includes determining a fastest ingestion rate and a slowest ingestion rate by dividing a size of the portion of a data stream by a storage time and identifying a maximum allowable difference in data stored based on the fastest ingestion rate, the slowest ingestion rate and a processing capacity level.