Method, device, and computer program product for adjusting data placement

Patent metadata

Field	Value
Publication number	US-12536072-B2
Application number	US-202418591916-A
Country	US
Kind code	B2
Filing date	Feb 29, 2024
Priority date	Jan 5, 2024
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

Data placement is adjusted. For instance, it is determined whether a node Failure To Tolerate (FTT) of a chunk in a storage system meets an optimized node FTT corresponding to the chunk, and, when it is determined that it does not meet, an FTT task entry for the chunk is added to a chunk index of the storage system. The added FTT task entry includes an identifier of the chunk, its node FTT, and the corresponding optimized system node FTT. Furthermore, instead of scanning placement information for each chunk, the storage system may adjust, based on the FTT task entry in the chunk index, placement of blocks of the corresponding chunk in system nodes. Therefore, the need to scan the placement information of all chunks and calculate their node FTTs in rebalance operations and minimum node FTT queries is eliminated, thereby improving the performance of the storage system.

First claim

What is claimed is:

1 . A method, comprising:
determining, by a system comprising at least one processor, whether a node Failure To Tolerate (node FTT) of a chunk in a storage system meets an optimized node FTT corresponding to the chunk, wherein the storage system comprises nodes and the chunk comprises blocks, wherein the node FTT indicates a first number of node failures that the chunk is able to tolerate before being associated with data loss, and wherein the optimized node FTT indicates a second number of node failures for which the chunk is able to be configured based on a third number of the nodes and an erasure coding schema of the system; adding, in response to the node FTT being determined not to meet the optimized node FTT, a FTT task entry for the chunk to a chunk index of the storage system, wherein the FTT task entry comprises an identifier of the chunk, the node FTT, and the optimized system node FTT; and adjusting placement of the blocks in the nodes based on the FTT task entry to increase the first number of node failures that the chunk is able to tolerate before being associated with data loss.

2 . The method according to claim 1 , wherein adjusting the placement of the blocks in the nodes based on the FTT comprises:
adjusting the placement of the blocks in a way that a performance of the node FTT according to a defined performance criterion, resulting in an improved node FTT; and removing the FTT task entry from the chunk index in response to the improved node FTT being determined to meet the optimized node FTT.

3 . The method according to claim 1 , wherein adjusting the placement of the blocks based on the FTT task entry comprises:
scanning the chunk index to search for the FTT task entry for the chunk; and adjusting the placement of the blocks in response to determining that the FTT task entry is detected during scanning.

4 . The method according to claim 1 , wherein the storage system stores types of chunks, and wherein the optimized node FTT corresponding to a corresponding chunk corresponds to a type of the corresponding chunk.

5 . The method according to claim 4 , further comprising:
determining, in response to addition of a new node to the storage system, whether there is a change in the optimized node FTT for the type of the chunk in the storage system; and updating, in response to determining that the change exists, the FTT task entry for the chunk in the chunk index based on the change.

6 . The method according to claim 4 , further comprising:
performing, in response to a node being removed from the storage system, recovery of data in the storage system; and updating, after the recovery is completed, the FTT task entry for the chunk in the chunk index based on the placement of the recovered data on the nodes.

7 . The method according to claim 4 , further comprising:
updating, in response to performing an action of temporarily invalidating a node of the nodes, the optimized node FTT for the type of the chunk in the storage system based on other nodes in the nodes.

8 . The method according to claim 1 , further comprising:
receiving a query, wherein the query targets a minimum value of the node FTTs for chunks in the storage system; and determining, in response to the query, the minimum value based on at least one of: the optimized node FTTs for types of the chunks in the storage system, a target node FTT for the storage system, or FTT task entries for the chunks in the chunk index.

9 . A device, comprising:
at least one processor; and at least one memory coupled to the at least one processor, wherein the memory has instructions stored therein, and the instructions, when executed by the processor, cause the device to perform actions comprising:
determining whether a node Failure To Tolerate (node FTT) of a chunk in a storage system meets an optimized node FTT corresponding to the chunk, wherein the storage system comprises a group of nodes and the chunk comprises a group of blocks, wherein the node FTT indicates a first number of node failures that the chunk is able to tolerate before being associated with data loss, and wherein the optimized node FTT indicates a second number of node failures for which the chunk is able to be configured based on a third number of the nodes and an erasure coding schema of the system;
adding, in response to the node FTT not meeting the optimized node FTT, a FTT task entry for the chunk to a chunk index of the storage system, wherein the FTT task entry comprises an identifier of the chunk, the node FTT, and the optimized node FTT; and
adjusting placement of the group of blocks in the group of nodes based on the FTT task entry to increase the first number of node failures that the chunk is able to tolerate before being associated with data loss.

10 . The device according to claim 9 , wherein adjusting the placement of the group of blocks in the group of nodes based on the FTT comprises:
adjusting the placement of the group of blocks in a way that improves the node FTT according to a defined improvement criterion, the adjusting resulting in an improved node FTT; and removing the FTT task entry from the chunk index in response to the improved node FTT meeting the optimized node FTT.

11 . The device according to claim 9 , wherein adjusting the placement of the group of blocks based on the FTT task entry comprises:
scanning the chunk index to search for the FTT task entry for the chunk; and adjusting the placement of the group of blocks in response to determining that the FTT task entry is detected during scanning.

12 . The device according to claim 9 , wherein the storage system stores a group of types of chunks, and wherein the optimized node FTT corresponding to a corresponding chunk corresponds to a type of the corresponding chunk.

13 . The device according to claim 12 , wherein the actions further comprise:
determining, in response to addition of a new node to the storage system, whether there is a change in the optimized node FTT for the type of the chunk in the storage system; and updating, in response to the existence of the change, the FTT task entry for the chunk in the chunk index based on the change.

14 . The device according to claim 12 , wherein the actions further comprise:
performing, in response to a node being removed from the storage system, recovery of data in the storage system; and updating, after the recovery is completed, the FTT task entry for the chunk in the chunk index based on the placement of the recovered data on the group of nodes.

15 . The device according to claim 12 , wherein the actions further comprise:
updating, in response to performing an action of temporarily invalidating a node of the group of nodes, the optimized node FTT for the type of the chunk in the storage system based on other nodes in the group of nodes.

16 . The device according to claim 9 , wherein the actions further comprise:
receiving a query, wherein the query targets a minimum value of the node FTTs for chunks in the storage system; and determining, in response to the query, the minimum value based on at least one of the following: the optimized node FTTs for types of the chunks in the storage system, a target node FTT for the storage system, and FTT task entries for the chunks in the chunk index.

17 . A computer program product tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions, wherein the machine-executable instructions, when executed, cause a machine to perform operatio

Assignees

• Dell Products Lp

Inventors

• Yu Chark Wenshuai
• Lei Lu
• Cao Jiang

Classifications

• G06F11/1016 Primary

  Error in accessing a memory location, i.e. addressing error · CPC title

• G06F11/141 Primary

  for bus or memory accesses · CPC title

• G06F11/2094

  Redundant storage or storage space (G06F11/2056 takes precedence) · 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

• G06F3/0614

  Improving the reliability of storage systems · CPC title