Methods and apparatus to implement failure recovery of data

Patent metadata

Field	Value
Publication number	US-2025181451-A1
Application number	US-202318525281-A
Country	US
Kind code	A1
Filing date	Nov 30, 2023
Priority date	Nov 30, 2023
Publication date	Jun 5, 2025
Grant date	—

Abstract

Disclosed examples include writing first information blocks in first storage; transmitting second information blocks to second storage, the first and second information blocks including data blocks and parity blocks; determining whether a failed information block can be reconstructed based on available ones of the first information blocks in the first storage; and writing a reconstructed information block in the first storage to replace the failed information block.

First claim

What is claimed is:

1 . An apparatus comprising:
a block generator to generate information blocks, the information blocks to include data blocks and parity blocks; a storage interface to write first information blocks of the information blocks in first storage; a network interface to send second information blocks of the information blocks to second storage; a block monitor to determine whether a failed information block can be reconstructed based on available ones of the first information blocks in the first storage; and the storage interface to write a reconstructed information block in the first storage to replace the failed information block.

2 . The apparatus of claim 1 , wherein after a determination that the failed information block cannot be reconstructed based on the available ones of the first information blocks in the first storage:
the block monitor is to generate a reconstruction request, the reconstruction request to cause recovery of the failed information block as the reconstructed information block based on at least some of the second information blocks in the second storage; and the network interface is to send the reconstruction request to a failure recovery manager corresponding to the second storage.

3 . The apparatus of claim 1 , wherein the block generator is to reconstruct the failed information block after a determination that the failed information block can be reconstructed based on the available ones of the first information blocks in the first storage.

4 . The apparatus of claim 1 , wherein the block generator is to reconstruct the failed information block based on forward error correction.

5 . The apparatus of claim 1 , wherein the first information blocks include at least some of the data blocks and at least one of the parity blocks, the second information blocks to include at least some of the parity blocks and at least one of the data blocks.

6 . The apparatus of claim 1 , wherein the network interface is to send the second information blocks from a first data center to a second data center, the first storage located in the first data center, the second storage located in the second data center.

7 . The apparatus of claim 1 , wherein the first information blocks in the first storage include different information relative to the second information blocks in the second storage.

8 . The apparatus of claim 1 , wherein the first storage is in a first power domain of a data center and the second storage is in a second power domain of the data center.

9 . The apparatus of claim 1 , wherein the first storage includes a plurality of storage resource nodes, ones of the first information blocks stored in corresponding ones of the storage resource nodes.

10 . A non-transitory computer-readable medium comprising instructions to cause programmable circuitry to at least:
write first information blocks in first storage; cause transmission of second information blocks to second storage, the first and second information blocks including data blocks and parity blocks; determine whether a failed information block can be reconstructed based on available ones of the first information blocks in the first storage; and write a reconstructed information block in the first storage to replace the failed information block.

11 . The non-transitory computer-readable medium of claim 10 , wherein after a determination that the failed information block cannot be reconstructed based on the available ones of the first information blocks in the first storage, the instructions are to cause the programmable circuitry to:
generate a reconstruction request, the reconstruction request to cause recovery of the failed information block as the reconstructed information block based on at least some of the second information blocks in the second storage; and cause transmission of the reconstruction request to a failure recovery manager corresponding to the second storage.

12 . The non-transitory computer-readable medium of claim 10 , wherein the instructions are to cause the programmable circuitry to reconstruct the failed information block after a determination that the failed information block can be reconstructed based on the available ones of the first information blocks in the first storage.

13 . The non-transitory computer-readable medium of claim 10 , wherein the instructions are to cause the programmable circuitry to reconstruct the failed information block based on forward error correction.

14 . The non-transitory computer-readable medium of claim 10 , wherein the first information blocks include at least some of the data blocks and at least one of the parity blocks, the second information blocks to include at least some of the parity blocks and at least one of the data blocks.

15 . The non-transitory computer-readable medium of claim 10 , wherein the instructions are to cause the programmable circuitry to cause transmission of the second information blocks from a first data center to a second data center, the first storage located in the first data center, the second storage located in the second data center.

16 . The non-transitory computer-readable medium of claim 10 , wherein the first information blocks in the first storage include different information relative to the second information blocks in the second storage.

17 . The non-transitory computer-readable medium of claim 10 , wherein the first storage is in a first power domain of a data center and the second storage is in a second power domain of the data center.

18 . The non-transitory computer-readable medium of claim 10 , wherein the first storage includes a plurality of storage resource nodes, ones of the first information blocks stored in corresponding ones of the storage resource nodes.

19 . A method comprising:
writing first information blocks in first storage; transmitting second information blocks to second storage, the first and second information blocks including data blocks and parity blocks; determining whether a failed information block can be reconstructed based on available ones of the first information blocks in the first storage; and writing a reconstructed information block in the first storage to replace the failed information block.

20 . The method of claim 19 , including, after a determination that the failed information block cannot be reconstructed based on the available ones of the first information blocks in the first storage:
generating a reconstruction request, the reconstruction request to cause recovery of the failed information block as the reconstructed information block based on at least some of the second information blocks in the second storage; and transmitting the reconstruction request to a failure recovery manager corresponding to the second storage.

21 . The method of claim 19 , including reconstructing the failed information block after a determination that the failed information block can be reconstructed based on the available ones of the first information blocks in the first storage.

22 . The method of claim 19 , including reconstructing the failed information block based on forward error correction.

23 . The method of claim 19 , including transmitting the second information blocks from a first data center to a second data center, the first storage located in the first data center, the second storage located in the second data center.

Assignees

• Cloudera Inc

Inventors

• Gangumalla Uma Maheswara Rao
• Pogde Prashant
• Wagle Siddharth Jivan
• Shukla Ritesh H
• Krishnamoorthy Karthik

Classifications

• G06F11/1076 Primary

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

• G06F11/1092 Primary

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