Distributed file system with reduced write and read latencies

Patent metadata

Field	Value
Publication number	US-12141104-B2
Application number	US-202117449760-A
Country	US
Kind code	B2
Filing date	Oct 1, 2021
Priority date	Jun 7, 2021
Publication date	Nov 12, 2024
Grant date	Nov 12, 2024

Abstract

A method for reducing write latency in a distributed file system. A write request that includes a volume identifier is received at a data management subsystem deployed on a node within a distributed storage system. The data management subsystem maps the volume identifier to a file system volume and maps the file system volume to a set of logical block addresses in a logical block device in a storage management subsystem deployed on the node. The storage management subsystem maps the logical block device to a metadata object for the logical block device on the node that is used to process the write request. The mapping of the file system volume to the set of logical block addresses in the logical block device enables co-locating the metadata object with the file system volume on the node, which reduces the write latency associated with processing the write request.

First claim

What is claimed is:

1. A method for reducing write latency in a distributed file system, the method comprising:
receiving a write request that includes a volume identifier at a data management subsystem deployed on a node within a distributed storage system;
mapping, by the data management subsystem, the volume identifier to a file system volume;
mapping, by the data management subsystem, the file system volume to a set of logical block addresses in a logical block device in a storage management subsystem deployed on the node; and
mapping, by the storage management subsystem, the logical block device to a metadata object for the logical block device on the node that is used to process the write request,
wherein the mapping of the file system volume to the set of logical block addresses in the logical block device enables co-locating the metadata object with the file system volume on the node; and
wherein co-locating the metadata object with the file system volume on the node reduces the write latency associated with processing the write request.

2. The method of claim 1 , wherein mapping, by the data management subsystem, the file system volume to the set of logical block addresses in the logical block device comprises mapping, by the data management subsystem, the file system volume to a logical aggregate and mapping, by the data management subsystem, the logical aggregate to the set of logical block addresses in the logical block device.

3. The method of claim 1 , wherein co-locating the file system volume, the logical block device, and the metadata object on the node reduces the write latency associated with the write request by enabling local metadata updates.

4. The method of claim 1 , further comprising sending, by the data management subsystem, a request that identifies a set of logical block addresses to which data from the write request is to be written in the logical block device over a local pathway to the storage management subsystem.

5. The method of claim 1 , further comprising computing, by a metadata service in the storage management subsystem, a set of block identifiers based on a request received from the data management subsystem, the request identifying the set of logical block addresses to which data from the write request is to be written in the logical block device.

6. The method of claim 1 , further comprising computing a cryptographic hash for a data block formed by file system data and file system metadata that is to be written in the logical block device based on the write request; and storing the cryptographic hash as a key within a key-value store and the data block as a value within the key-value store.

7. The method of claim 1 , wherein servicing the write request includes overwriting a logical block address in the logical block device and further comprising overwriting a previously computed cryptographic hash associated with a selected block address in the logical block device with a new cryptographic hash.

8. The method of claim 1 , further comprising sending a response to a source of the write request after metadata and data associated with the write request are stored in a logging storage device associated with the node.

9. The method of claim 1 , further comprising computing a block identifier for a data block corresponding to write data and write metadata associated with the write request; and storing the block identifier in a set of indirect nodes in a buffer tree within the data management subsystem.

10. A method for reducing read latency in a distributed file system, the method comprising:
receiving, at a data management subsystem deployed on a node within a distributed storage system, a read request from a source, the read request including a volume identifier;
mapping, by the data management subsystem, the volume identifier to a file system volume managed by the data management subsystem;
associating, by the data management subsystem, a file system volume object with a block identifier that corresponds to a data block of a logical block device in a distributed block layer of the distributed file system; and
sending data stored in the data block to the source with the read latency associated with processing of the read request being reduced.

11. The method of claim 10 , wherein the file system volume object comprises at least one of a file system volume data block or a file system volume metadata block and wherein the block identifier is a computed hash value for the data block or metadata block and is stored within a buffer cache in the data management subsystem.

12. The method of claim 10 , wherein the read request is received after an initial read request; wherein the block identifier is stored within a set of indirect blocks in a buffer tree during processing of a write request received prior to the initial read request; and wherein processing the initial read request causes the set of indirect blocks to be paged into memory from disk to thereby enable the block identifier to be available in a buffer cache in the data management subsystem.

13. The method of claim 10 , wherein associating the file system volume block with the block identifier comprises looking up the block identifier corresponding to the read request using a set of indirect blocks and a buffer cache in the data management subsystem, thereby bypassing consultation of a metadata object corresponding to the logical block device.

14. The method of claim 10 , further comprising caching the set of indirect blocks with the block identifier within the data management subsystem such that association of the file system volume block with the block identifier reduces the read latency associated with the read request.

15. The method of claim 10 , wherein the file system volume object comprises at least one of a file system volume data block or a file system volume metadata block and wherein the data block identified by the block identifier resides on a different node from the node on which the data management subsystem is deployed.

16. A distributed storage system comprising:
one or more central processor unit (CPU) resources; and
instructions that when executed by the one or more CPU resources cause the distributed storage system to:
receive, at a data management subsystem deployed on a node of a plurality of nodes of a cluster representing the distributed storage system, a write request that includes a volume identifier;
map, by the data management subsystem, the volume identifier to a file system volume;
enable co-locating of a metadata object for a logical block device of a storage management subsystem deployed on the node that is used to process the write request by mapping, by the data management subsystem, the file system volume to a set of logical block addresses in the logical block device; and
reduce write latency associated with processing of the write request by mapping, by the storage management subsystem, the logical block device to the metadata object.

17. The distributed storage system of claim 16 , wherein said mapping, by the data management subsystem, the file system volume to a set of logical block addresses in the logical block device comprises:
mapping, by the data management subsystem, the file system volume to a logical aggregate; and
mapping, by the data management subsystem, the logical aggregate to the set of logical block addresses in the logical block device.

18. The distributed storage system of claim 16 , wherein co-locating of the file system volume, the logical block device, and the metadata object on the node reduce

Assignees

• Netapp Inc

Inventors

• Subramanian Ananthan
• Mccarthy Daniel
• Banerjee Arindam

Classifications

• G06F16/188

  Virtual file systems · CPC title

• G06F16/164

  File meta data generation · CPC title

• H04L67/00

  Network arrangements or protocols for supporting network services or applications (user-to-user messaging H04L51/00; network arrangements, protocols or services for supporting real-time applications in data packet communications networks H04L65/00) · CPC title

• G06F3/0611

  in relation to response time · CPC title

• G06F3/0631

  by allocating resources to storage systems · CPC title