Changing storage volume ownership using cache memory

Patent metadata

Field	Value
Publication number	US-9836223-B2
Application number	US-201615142691-A
Country	US
Kind code	B2
Filing date	Apr 29, 2016
Priority date	Apr 29, 2016
Publication date	Dec 5, 2017
Grant date	Dec 5, 2017

Abstract

A method, a computing device, and a non-transitory machine-readable medium for changing ownership of a storage volume from a first controller to a second controller without flushing data, is provided. In the system, the first controller is associated with a first DRAM cache comprising a primary partition that stores data associated with the first controller and a mirror partition that stores data associated with the second controller. The second controller in the system is associated with a second DRAM cache comprising a primary partition that stores data associated with the second controller and the mirror partition associated with the first controller. Further, the mirror partition in the second DRAM cache stores a copy of a data in the primary partition of the first DRAM cache and the mirror partition in the first DRAM cache stores a copy of a data in the primary partition of the second DRAM cache.

First claim

What is claimed is:

1. A method comprising:
storing, using a first controller, data and recovery metadata of a storage volume owned by the first controller in a primary partition of a memory cache of the first controller, and a copy of the data and the recovery metadata in a mirror partition of a memory cache of a second controller that is allocated to the first controller;
receiving an indication of an ownership change for the storage volume from the first controller to the second controller;
scanning, using the second controller, the mirror partition allocated to the first controller for the recovery metadata associated with the storage volume;
generating an active metadata from the recovery metadata scanned from the mirror partition, wherein the active metadata manages input/output (I/O) requests for the data stored in the mirror partition; and
using the active metadata to access the data in the mirror partition allocated to the first controller to process an input/output (I/O) request associated with the storage volume using the second controller.

2. The method of claim 1 , wherein the recovery metadata is metadata required to recreate data associated with the storage volume in a primary partition of the second controller.

3. The method of claim 1 , wherein the data comprises dirty data associated with the storage volume that has not been flushed to an array of storage drives.

4. The method of claim 1 , further comprising:
marking the active metadata with an indication that the active metadata is associated with the data in the mirror partition and data in a primary partition of the memory cache of the second storage controller, wherein the data in the mirror partition is associated with the first controller and the data in the primary partition is associated with a second controller.

5. The method of claim 1 , wherein the memory cache of the first controller is a first dynamic random access memory (DRAM) cache comprising the primary partition that stores a first data associated with the first controller and a mirror partition that stores data associated with the second controller, and
wherein the memory cache of the second controller is a second DRAM cache comprising a primary partition that stores a second data associated with the second controller and the mirror partition associated with the first controller, and
wherein the mirror partition in the second DRAM cache stores a copy of a first data in the primary partition of the first DRAM cache, and
wherein the mirror partition in the first DRAM cache stores a copy of a second data in the primary partition of the second DRAM cache.

6. The method of claim 5 , wherein the first data comprises the data and the recovery metadata for the storage volume before the ownership change.

7. The method of claim 5 , wherein the second data comprises data and metadata for the storage volume after the ownership change.

8. The method of claim 1 , wherein the second controller is associated with a general storage separate from the memory cache, and the method further comprises storing the generated active metadata associated with the storage volume in the general storage.

9. The method of claim 1 , wherein the memory cache is a DRAM cache comprising a primary partition and the method further comprises storing dirty data and recovery metadata associated with the storage volume in the primary partition after the second storage controller receives ownership of the storage volume, wherein the dirty data includes a portion of the data in the mirror partition.

10. A non-transitory machine readable medium having stored thereon instructions for performing a method comprising machine executable code, which when executed by at least one machine, causes the machine to:
store, using a first controller, data and recovery metadata of a storage volume owned by the first controller in a primary partition of a memory cache of the first controller, and a copy of the data and the recovery metadata in a mirror partition of a memory cache of a second controller that is allocated to the first controller;
receive an indication of an ownership change for the storage volume from the first controller to the second controller;
scan using the second controller, the mirror partition allocated to the first controller for recovery metadata associated with the storage volume;
generate an active metadata from the scanned recovery metadata, wherein the active metadata manages input/output (I/O) requests for the data stored in the mirror partition; and
use the active metadata to access the data in the mirror partition allocated to the first controller to process an input/output (I/O) request associated with the storage volume using the second controller.

11. The non-transitory machine readable medium of claim 10 , wherein the data is dirty data associated with the storage volume that has not been flushed to the hard disk drive.

12. The non-transitory machine readable medium of claim 10 , further comprising instructions for performing the method comprising machine executable code, which when executed by at least one machine, further causes the machine to:
mark the active metadata with an indication indicating that the active metadata is associated with the data in the mirror partition and data in a primary partition of the memory cache, wherein the data in the mirror partition is associated with the first controller and the data in the primary partition is associated with a second controller.

13. The non-transitory machine readable medium of claim 10 , wherein the second controller is associated with a general storage and the instructions for performing the method comprising machine executable code, which when executed by at least one machine, further causes the machine to:
store the generated active metadata associated with the storage volume in the general storage.

14. The non-transitory machine readable medium of claim 10 , wherein the memory cache is a DRAM cache comprising a primary partition and wherein the instructions for performing the method comprising machine executable code, which when executed by at least one machine, further causes the machine to:
store dirty data and recovery metadata associated with the storage volume in the primary partition after the second storage controller receives ownership of the storage volume, wherein the dirty data includes a portion of the data in the mirror partition.

15. The non-transitory machine readable medium of claim 10 , wherein the instructions for performing the method comprising machine executable code, which when executed by at least one machine, further causes the machine to:
accesses, using the second controller, the memory cache associated with the first controller; and
store a copy of the dirty data and a copy of the recovery metadata in a mirror partition of the memory cache associated with the first controller, wherein the mirror partition stores data accessible to the second controller.

16. A computing device comprising:
a memory containing machine readable medium comprising machine executable code having stored thereon instructions for performing a method of transferring ownership of a storage volume; and
a processor coupled to the memory, the processor configured to execute the machine executable code to cause the processor to:
store, using a first controller, data and recovery metadata of a storage volume owned by the first controller in a primary partition of a memory cache of the first controller, and a copy of the data and the recovery metadata in a mirror partition of a memory cache of a second controller

Assignees

• Netapp Inc

Inventors

• Mckean Brian D
• Humlicek Donald R

Classifications

• G06F11/2092

  Techniques of failing over between control units · CPC title

• G06F2212/466

  Metadata, control data · CPC title

• G06F2212/263

  Network storage, e.g. SAN or NAS · CPC title

• G06F2212/1024

  Latency reduction · CPC title

• G06F11/2056

  by mirroring · CPC title