Virtual multi-cluster clouds

Patent metadata

Field	Value
Publication number	US-9405781-B2
Application number	US-201414249301-A
Country	US
Kind code	B2
Filing date	Apr 9, 2014
Priority date	Mar 8, 2011
Publication date	Aug 2, 2016
Grant date	Aug 2, 2016

Abstract

An improved scalable object storage system includes methods and systems allowing multiple clusters to work together. Users working with a first cluster, or with a multi-cluster gateway, can ask for services and have the request or data transparently proxied to a second cluster. This gives transparent cross-cluster replication, as well as multi-cluster compute or storage farms based upon spot availability or various provisioning policies. Vendors providing a cloud storage “frontend” can provide multiple backends simultaneously. In one embodiment, a multi-cluster gateway can have a two, three, or higher-level ring that transparently matches an incoming request with the correct cluster. In the ring, a request is first mapped to an abstract “partition” based on a consistent hash function, and then one or more constrained mappings map the partition number to an actual resource. In another embodiment, the multi-cluster gateway is a dumb gateway, and the rings are located only at the cluster level.

First claim

The invention claimed is:

1. A system for coordinating a plurality of clusters, the system comprising:
a first cluster including a first plurality of information processing devices;
a second cluster including a second plurality of information processing devices; and
a multi-cluster gateway coupled to the first and second clusters, wherein the multi-cluster gateway includes a ring that performs a first hashing function and a second hashing function responsive to a request to interact with the system, wherein the request includes an object,
wherein the ring performs the first hashing function on an attribute of the object, and an output of the first hashing function is a partition identifier of a partition corresponding to computing resources available at one of the first cluster and the second cluster, and wherein the partition identifier includes a plurality of portions,
wherein the ring performs the second hashing function on each portion of the plurality of portions, and an output of the second hashing function identifies a storage pool location for a portion of the plurality of portions on which the second hashing function is applied, and wherein the storage pool location is located in a responsive cluster from one of the first cluster and the second cluster, and
wherein the multi-cluster gateway sends a message to the responsive cluster.

2. The system of claim 1 , wherein the first hashing function comprises a consistent hashing function.

3. The system of claim 1 , wherein the second hashing function comprises a constrained mapping function.

4. The system of claim 1 , wherein the output of the second hashing function further identifies a specific resource within the responsive cluster.

5. The system of claim 4 , wherein the message to the responsive cluster is addressed to the specific resource within the responsive cluster.

6. The system of claim 1 , further comprising a return message from the responsive cluster responsive to the request to interact with the system.

7. The system of claim 1 , wherein the multi-cluster gateway further includes a proxy module.

8. The system of claim 7 , wherein the proxy module sends a return message from the responsive cluster in response to the request to interact with the system.

9. The system of claim 1 , wherein one of the first cluster and the second cluster further comprises a cluster-level ring, wherein the cluster-level ring performs a third hashing function responsive to a message identifying the cluster as a responsive cluster, wherein the output of the third hashing function is a cluster-level partition associated with the resources available within the cluster.

10. The system of claim 9 , wherein the cluster-level ring performs a fourth hashing function, wherein the output of the fourth hashing function identifies a specific responsive resource associated with the cluster-level partition.

11. The system of claim 1 , wherein the first cluster is controlled by a first party and the second cluster is controlled by a second party.

12. The system of claim 1 , wherein the second hashing function uses geographic distance to choose which cluster is the responsive cluster.

13. The system of claim 1 , wherein the second hashing function uses network latency to choose which cluster is the responsive cluster.

14. A method of coordinating a plurality of clusters, the method comprising:
receiving a request including an object;
performing a first hashing function on an attribute of the object;
obtaining an output of the first hashing function, the output being a partition identifier of a partition corresponding to computing resources available at one of a first cluster and a second cluster, the partition identifier including a plurality of portions;
performing a second hashing function on a portion of the plurality of portions;
obtaining an output of the second hashing function, the output identifying a storage pool location, the storage pool location being located in a responsive cluster from one of the first cluster and the second cluster; and
sending a message to the responsive cluster.

15. The method of claim 14 , further comprising:
receiving a responsive message from a cluster.

16. The method of claim 14 , wherein only one of the first cluster and the second cluster is the responsive cluster, and wherein a response to the request is sent by the responsive cluster.

17. The method of claim 14 , wherein either of the first cluster and the second cluster can be a responsive cluster, and wherein the first cluster to formulate a response sends the response.

18. The method of claim 14 , wherein the sending the message includes sending the message to the cluster that is closer geographically to the source of the request.

19. The method of claim 14 , wherein the sending the message includes sending the message to the cluster that has lower latency between the cluster and the source of the request.

20. The method of claim 14 , wherein the first cluster is controlled by a first party and the second cluster is controlled by a second party.

Assignees

• Rackspace Us Inc

Inventors

• Holt Gregory Lee
• Gerrard Clay
• Goetz David Patrick
• Barton Michael

Classifications

• G06F3/0644 Primary

  Management of space entities, e.g. partitions, extents, pools · CPC title

• G06F11/1004

  to protect a block of data words, e.g. CRC or checksum (G06F11/1076 takes precedence; security arrangements for protecting computers or computer systems against unauthorized activity G06F21/00) · CPC title

• G06F17/30318 Primary

  Physics · mapped topic

• H04L67/06

  specially adapted for file transfer, e.g. file transfer protocol [FTP] · CPC title

• G06F17/30864

  Physics · mapped topic