Pessimistic data reading in a dispersed storage network

• US 8,880,940 B2
• Filed: 10/01/2013
• Issued: 11/04/2014
• Est. Priority Date: 10/09/2007
• Status: Expired due to Fees

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Dhuse, Greg
• Primary Examiner(s): Leibovich, Yair
• Application Number:
  US14/042,844
• Publication Number:
  US 20140032961A1
• Time in Patent Office: 399 Days
• Field of Search: 714/6.24, 714/6.22
• US Class Current: 714/6.22
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1443 Transmit or communication errors
• CPC Class Codes: G06F 11/1474 in transactions G06F16/20 takes precedence
• CPC Class Codes: G06F 11/18 using passive fault-masking of the redundant circuits error detection by comparing the output of redundant processing systems with continued operation after detection of the error G06F11/165
• CPC Class Codes: G06F 11/186 Passive fault masking when reading multiple copies of the same data
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 2211/1057 Parity-multiple bits-RAID6, i.e. RAID 6 implementations

Abstract

A method begins by a processing module receiving a data retrieval request and determining a read threshold number of dispersed storage (DS). The method continues with the processing module sending read request messages to DS units and receiving encoded data slices to produce received encoded data slices. The method continues with the processing module determining an incremental number of encoded data slices based on the number of received encoded data slices, determining an incremental number of DS units, and sending a read request message to each of the incremental number of DS units when the number of received encoded data slices compares unfavorably to a decode threshold number. The method continues with the processing module dispersed storage error decoding the received encoded data slices to produce data when the number of received encoded data slices compares favorably to the decode threshold number of encoded data slices.

Claims

1. A method comprises:

receiving a data retrieval request;

determining a read threshold number of encoded data slices in response to the data retrieval request;

sending read request messages regarding the read threshold number of encoded data slices to storage units of a dispersed storage network;

entering a loop, wherein the loop includes;

receiving encoded data slices of the read threshold number of encoded data slices within a time period to produce received encoded data slices;

when a number of received encoded data slices compares unfavorably to a decode threshold number;

determining an incremental number of encoded data slices based on the number of received encoded data slices and the decode threshold number;

sending a read request message regarding the incremental number of encoded data slices to other storage units of the dispersed storage network; and

repeating the loop; and

when the number of received encoded data slices compares favorably to the decode threshold number of encoded data slices, exiting the loop; and

dispersed storage error decoding the received encoded data slices to recapture a data segment of data.

2. The method of claim 1, wherein the read threshold number comprises at least one of:

the read threshold number is equal to the decode threshold; and

the read threshold number is greater than the decode threshold and less than a pillar width.

3. The method of claim 1, wherein the determining of the read threshold number of encoded data slices is based on at least one of:

a read threshold number;

a data identifier (ID);

a user ID;

error coding dispersal storage function parameters;

storage unit performance history;

one or more storage unit queries;

a virtual DSN address to physical location table lookup;

a list;

a vault lookup;

a command;

a predetermination;

a message;

a source name; and

a slice name.

4. The method of claim 1, wherein the time period comprises:

a dynamic time duration that is based on at least one of a list, a performance indicator, and a reliability indicator.

5. The method of claim 1, wherein the determining an incremental number of encoded data slices as at least one of:

the difference between the decode threshold number and the number of received encoded data slices;

the difference between the read threshold number and the number of received encoded data slices; and

the difference between a pillar width number and the number of received encoded data slices.

6. The method of claim 1, wherein the determining of the incremental number of encoded data slice is based on at least one of:

identifying a previously responding storage unit;

identifying a previously non-responding storage unit;

identifying a storage unit associated with a timeout indication;

a list;

a vault lookup;

a command;

a predetermination;

a message;

a source name; and

a slice name.

7. A computer comprises:

an interface; and

a processing module operable to;

receive, via the interface, a data retrieval request;

determine a read threshold number of encoded data slices in response to the data retrieval request;

send read request messages regarding the read threshold number of encoded data slices to storage units of a dispersed storage network;

enter a loop, wherein the loop includes;

receive encoded data slices of the read threshold number of encoded data slices within a time period to produce received encoded data slices;

when a number of received encoded data slices compares unfavorably to a decode threshold number;

determine an incremental number of encoded data slices based on the number of received encoded data slices and the decode threshold number;

send a read request message regarding the incremental number of encoded data slices to other storage units of the dispersed storage network; and

repeat the loop; and

when the number of received encoded data slices compares favorably to the decode threshold number of encoded data slices, exit the loop; and

dispersed storage error decode the received encoded data slices to recapture a data segment of data.

8. The computer of claim 7, wherein the read threshold number comprises at least one of:

the read threshold number is equal to the decode threshold; and

the read threshold number is greater than the decode threshold and less than a pillar width.

9. The computer of claim 7, wherein the processing module further functions to determine the read threshold number of encoded data slices based on at least one of:

a read threshold number;

a data identifier (ID);

a user ID;

error coding dispersal storage function parameters;

storage unit performance history;

one or more storage unit queries;

a virtual DSN address to physical location table lookup;

a list;

a vault lookup;

a command;

a predetermination;

a message;

a source name; and

a slice name.

10. The computer of claim 7, wherein the time period comprises:

a dynamic time duration that is based on at least one of a list, a performance indicator, and a reliability indicator.

11. The computer of claim 7, wherein the processing module further functions to determine the incremental number of encoded data slices as at least one of:

the difference between the decode threshold number and the number of received encoded data slices;

the difference between the read threshold number and the number of received encoded data slices; and

the difference between a pillar width number and the number of received encoded data slices.

12. The computer of claim 7, wherein the processing module determines the incremental number of encoded data slices based on at least one of:

identifying a previously responding storage unit;

identifying a previously non-responding storage unit;

identifying a storage unit associated with a timeout indication;

a list;

a vault lookup;

a command;

a predetermination;

a message;

a source name; and

a slice name.