Redundant, fault-tolerant, distributed remote procedure call cache in a storage system

• US 10,114,714 B2
• Filed: 07/18/2016
• Issued: 10/30/2018
• Est. Priority Date: 07/02/2014
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Pure Storage, Inc.
• Inventors: Hayes, John, Lee, Robert, Vajgel, Peter, Robinson, Joshua
• Primary Examiner(s): Wilson, Yolanda L
• Application Number:
  US15/213,271
• Publication Number:
  US 20160328305A1
• Time in Patent Office: 834 Days
• Field of Search: None
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 11/1469 Backup restoration techniques
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area
• CPC Class Codes: G06F 11/2056 by mirroring
• CPC Class Codes: G06F 11/2058 using more than 2 mirrored copies
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/0875 with dedicated cache, e.g. instruction or stack
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 2212/1032 Reliability improvement, data loss prevention, degraded operation etc
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: G06F 2212/284 being distributed
• CPC Class Codes: G06F 2212/286 Mirrored cache memory
• CPC Class Codes: G06F 2212/452 Instruction code
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices

Abstract

A method of operating a remote procedure call cache in a storage cluster is provided. The method includes receiving a remote procedure call at a first storage node having solid-state memory and writing information, relating to the remote procedure call, to a remote procedure call cache of the first storage node. The method includes mirroring the remote procedure call cache of the first storage node in a mirrored remote procedure call cache of a second storage node. A plurality of storage nodes and a storage cluster are also provided.

Claims

1. A storage cluster, comprising:

a plurality of storage nodes configurable to cooperate as a storage cluster and to support a plurality of filesystems, each storage node of the plurality of storage nodes having solid-state storage;

a first remote procedure call cache in a first one of the plurality of storage nodes, the first remote procedure call cache configurable to receive a remote procedure call under a first one of the plurality of filesystems; and

a first mirrored remote procedure call cache in a second one of the plurality of storage nodes, configurable to mirror the first remote procedure call cache.

2. The storage cluster of claim 1, further comprising:

a second mirrored remote procedure call cache in the first one of the plurality of storage nodes, configurable to mirror a second remote procedure call cache of a further one of the plurality of storage nodes.

3. The storage cluster of claim 1, further comprising:

a second remote procedure call cache in a further one of the plurality of storage nodes, configurable to receive a further remote procedure call; and

a second mirrored remote procedure call cache in a still further one of the plurality of storage nodes, configurable to mirror the second remote procedure call cache.

4. The storage cluster of claim 1, further comprising:

a second remote procedure call cache in a second one of the plurality of storage nodes, configurable to receive a remote procedure call under a second filesystem.

5. The storage cluster of claim 1, further comprising:

the plurality of storage nodes configurable to receive a remote procedure call relating to a file with a first Mode version, corresponding to the first one of the plurality of filesystems, at a first Internet Protocol (IP) address, and receive a further remote procedure call relating to a file with a second Mode version, corresponding to a second one of the plurality of filesystems, at a second IP address.

6. The storage cluster of claim 1, further comprising:

each of the plurality of storage nodes configurable to receive a remote procedure call, determine which one of the plurality of storage nodes has an authority for data relating to the remote procedure call, and forward the remote procedure call to the one of the plurality of storage nodes that has the authority for the data relating to the remote procedure call.

7. The storage cluster of claim 1, further comprising:

each storage node of the plurality of storage nodes having a remote procedure call cache and one or more mirrored remote procedure call caches, with the remote procedure call cache associated with a primary authority relating to a range of user data and each of the one or more mirrored remote procedure call caches associated with a corresponding backup authority relating to a further range of user data.

8. A method for fault-tolerant operation of remote procedure call caches in a storage system, comprising:

receiving, at a first remote procedure call cache in a first one of a plurality of storage nodes, a first remote procedure call under a first filesystem;

mirroring the first remote procedure call cache in a first mirrored remote procedure call cache in a storage node other than the first one of the plurality of storage nodes;

receiving, at a second remote procedure call cache in a second one of the plurality of storage nodes, a second remote procedure call under a second filesystem; and

mirroring the second remote procedure call cache in a second mirrored remote procedure call cache in a storage node other than the second one of the plurality of storage nodes.

9. The method of claim 8, further comprising:

mirroring, at a third mirrored remote procedure call cache in the first one of the plurality of storage nodes, a third remote procedure call cache of a differing one of the plurality of storage nodes.

10. The method of claim 8, wherein:

the first remote procedure call relates to a file with a first Mode version, corresponding to the first filesystem, and is received at a first Internet Protocol (IP) address associated with the first filesystem; and

the second remote procedure call relates to a file with a second Mode version, corresponding to the second filesystem, and is received at a second IP address associated with the second filesystem.

11. The method of claim 8, further comprising:

receiving the first remote procedure call at a differing one of the plurality of storage nodes;

determining, at the differing one of the plurality of storage nodes, that the first one of the plurality of storage nodes has an authority for data relating to the first remote procedure call; and

forwarding the first remote procedure call to the first one of the plurality of storage nodes, responsive to the determining.

12. The method of claim 8, further comprising:

establishing a plurality of mirrored remote procedure call caches each associated with a backup authority relating to a corresponding range of user data, wherein the first remote procedure call cache is associated with a first authority relating to a first range of user data and the second remote procedure call cache is associated with a second authority relating to a second range of user data.

13. The method of claim 8, further comprising:

further mirroring the first remote procedure call cache in a third mirrored remote procedure call cache in a further storage node.

14. The method of claim 8, further comprising:

determining which one of the plurality of storage nodes is a destination for the first remote procedure call, based on an Mode number for data relative to the first remote procedure call; and

routing the first remote procedure call to the first one of the plurality of storage nodes, responsive to the determining.