Distributed file system that provides scalability and resiliency

Patent metadata

Field	Value
Publication number	US-12045207-B2
Application number	US-202117449758-A
Country	US
Kind code	B2
Filing date	Oct 1, 2021
Priority date	Jun 7, 2021
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

A distributed storage management system comprising nodes that form a cluster, a distributed block layer that spans the nodes in the cluster, and file system instances deployed on the nodes. Each file system instance comprises a data management subsystem and a storage management subsystem disaggregated from the data management subsystem. The storage management subsystem comprises a node block store that forms a portion of the distributed block layer and a storage manager that manages a key-value store and virtualized storage supporting the node block store. A file system volume hosted by the data management subsystem maps to a logical block device hosted by the virtualized storage in the storage management subsystem. The key-value store includes, for a data block of the logical block device, a key that comprises a block identifier for the logical block device and a value that comprises the data block.

First claim

What is claimed is:

1. A distributed storage management system comprising:
a plurality of nodes that form a cluster;
a distributed block layer that spans the plurality of nodes in the cluster; and
a plurality of file system instances deployed on the plurality of nodes, wherein each file system instance of the plurality of file system instances comprises:
a data management subsystem; and
a storage management subsystem disaggregated from the data management subsystem, wherein the storage management subsystem comprises a node block store that forms a portion of the distributed block layer and a storage manager that manages a key-value store and virtualized storage supporting the node block store,
wherein a file system volume hosted by the data management subsystem maps to a logical block device hosted by the virtualized storage in the storage management subsystem; and
wherein the key-value store includes, for a data block of the logical block device, a key that comprises a block identifier for the logical block device and a value that comprises the data block.

2. The distributed storage management system of claim 1 , wherein the distributed block layer includes a metadata block layer that is distributed across the plurality of nodes and a data block layer that is distributed across the plurality of nodes.

3. The distributed storage management system of claim 1 , wherein the data management subsystem exposes the file system volume to an application layer and wherein the file system volume maps to a logical aggregate that maps to the logical block device in the storage management subsystem.

4. The distributed storage management system of claim 1 , wherein the key-value store is one instance of a distributed key-value store that spans the plurality of nodes in the cluster.

5. The distributed storage management system of claim 1 , wherein the logical block device has a corresponding metadata object stored in a node metadata block store of the node block store, the corresponding metadata object being replicated on at least one other node in the plurality of nodes.

6. The distributed storage management system of claim 1 , wherein the storage management subsystem is configured to replicate each data block of a plurality of data blocks that have been distributed within the distributed block layer on at least one other node in the plurality of nodes.

7. The distributed storage management system of claim 1 further comprising expanding a file system instance of the plurality of file system instances by leveraging resources available within the cluster.

8. The distributed storage management system of claim 1 , wherein the virtualized storage is protected by redundant array of independent disks (RAID) storage.

9. A distributed storage management system comprising:
a plurality of nodes that form a cluster;
a distributed block layer that spans the plurality of nodes in the cluster;
a data management subsystem hosted within an application layer in communication with the cluster; and
a file system instance deployed on a node of the plurality of nodes and comprising:
a cluster management subsystem; and
a storage management subsystem that comprises a metadata service, a block service, and a storage manager,
wherein the metadata service and the block service manage a node block store that forms a portion of the distributed block layer; and
wherein the storage manager manages a key-value store and a virtualized storage supporting the node block store.

10. The distributed storage management system of claim 9 , wherein the virtualized storage is protected by redundant array of independent disks (RAID) storage.

11. The distributed storage management system of claim 9 , wherein the key-value store is one instance of a distributed key-value store that spans the plurality of nodes in the cluster.

12. The distributed storage management system of claim 9 , wherein the storage management subsystem further comprises a persistence abstraction layer through which the metadata service and the block service communicate with the storage manager.

13. The distributed storage management system of claim 9 , wherein the storage management subsystem is further configured to replicate a data bock of a plurality of data blocks that is hosted on a first node of the plurality of nodes on at least one other node of the plurality of nodes.

14. The distributed storage management system of claim 9 , wherein the storage management subsystem is further configured to redistribute a plurality of data blocks across a plurality of node block data stores within the distributed block layer in response to a new node being added to the plurality of nodes.

15. A method for managing file system volumes across a cluster, the method comprising:
hosting a file system volume on a node of a plurality of nodes in a cluster, wherein the file system volume is exposed to an application layer by a data management subsystem;
mapping file system data and file system metadata of the file system volume to a data block of a logical block device in a storage management subsystem that is disaggregated from the data management subsystem; and
mapping the data block to a block identifier that is stored in a metadata object corresponding to the logical block device, wherein the block identifier identifies a selected node of the plurality of nodes in the cluster and a location within a node block store of the selected node where the data block resides.

16. The method of claim 15 , wherein mapping the file system data and the file system metadata comprises mapping the file system data and the file system metadata of the file system volume to a logical aggregate in the data management subsystem and mapping the logical aggregate to the logical block device.

17. The method of claim 15 , further comprising scaling the key-value store on-demand in response to an increased number of applications mounting the file system volumes via the application layer.

18. The method of claim 15 , further comprising scaling performance of the cluster by adding a set of additional nodes to the plurality of nodes to increase central processing unit (CPU) power.

19. The method of claim 18 , wherein at least one node of the set of additional nodes is unattached to storage.

20. The method of claim 15 , further comprising scaling a capacity of the cluster by adding a set of additional nodes to the plurality of nodes in which each additional node of the set of additional nodes is attached to storage.

21. The method of claim 15 , wherein the block identifier comprises a cryptographic hash and wherein a first portion of the cryptographic hash identifies an internal storage container for a particular node of the plurality of nodes and wherein a second portion of the cryptographic hash identifies a location of the data block within the particular node.

22. The method of claim 15 , wherein mapping a logical block address of a set of logical block addresses within the logical block device to the block identifier that is stored in the key-value store that is distributed enables sharing of data blocks between multiple logical block devices.

23. The method of claim 15 , wherein the data block is stored in a data block store that is distributed across nodes within the cluster independently of a metadata block store in which the metadata object is stored to enable global deduplication of data blocks within the data block store.

24. A distributed

Assignees

• Netapp Inc

Inventors

• Dronamraju Ravikanth
• Subramanian Ananthan
• Mccarthy Daniel
• Cason Christopher
• Banerjee Arindam

Classifications

• G06F16/182

  Distributed file systems · CPC title

• G06F9/5077

  Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title

• G06F11/2023

  Failover techniques · CPC title

• G06F11/1662

  the resynchronized component or unit being a persistent storage device (re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008) · CPC title

• G06F11/0751

  Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06) · CPC title