OPTIMIZED READ ACCESS TO SHARED DATA VIA MONITORING OF MIRRORING OPERATIONS

• US 20160085460A1
• Filed: 09/22/2014
• Published: 03/24/2016
• Est. Priority Date: 09/22/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Chandrashekar, Girish
• Granted Patent: US 9,830,088 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/16 Error detection or correction of the data by redundancy in hardware
• CPC Class Codes: G06F 11/2064 while ensuring consistency
• CPC Class Codes: G06F 11/2074 Asynchronous techniques
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 2212/1008 Correctness of operation, e.g. memory ordering
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: G06F 2212/163 Server or database system
• CPC Class Codes: G06F 2212/251 Local memory within processor subsystem
• CPC Class Codes: G06F 2212/286 Mirrored cache memory
• CPC Class Codes: G06F 2212/314 In storage network, e.g. network attached cache
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0658 Controller construction arrangements
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A method and system for optimized read access to shared data via monitoring of mirroring operations are described. A data storage system performs operations that include one controller in a dual-controller host storage appliance in an asymmetric active/active configuration receiving a request from the host for data on a logical unit number owned by the partner controller. The receiving controller, which has a mirror cache of the partner controller'"'"'s memory for failure recovery, accesses the mirror cache using a data structure that was populated during previous mirror operations. If the data is found in the mirror cache, it is read from the cache and returned to the requesting host without having to contact the partner controller for the data.

Claims

1. A method of retrieving data in a storage appliance, the method being implemented by one or more processors and comprising:

receiving a request for data from a host at a first controller of the storage appliance, wherein the data is associated with a logical unit number (LUN) owned by a second controller of the storage appliance;

making a determination that the data resides in a cache on the first controller, wherein the cache contains information stored in a memory of the second controller; and

upon determining that the data resides in the cache, returning the data from the cache to the host.

2. The method of claim 1, further comprising:

upon determining that the data does not reside in the cache, retrieving the data from the LUN without accessing the second controller; and

returning the data to the host.

3. The method of claim 1, further comprising:

upon determining that the data resides in the cache, suspending acknowledgments to the second controller until the cache is no longer being read.

4. The method of claim 1, wherein the storage appliance is in an asymmetric active/active configuration.

5. The method of claim 1, wherein the second controller is a primary controller for storing write request data from the host to the LUN, and the first controller is an alternate controller for storing write request data from the host to the LUN.

6. The method of claim 1, further comprising:

receiving a mirror operation at the first controller from the second controller, wherein the mirror operation includes a recovery control block containing data associated with the LUN owned by the second controller;

creating a cache control block associated with the recovery control block; and

storing the cache control block in a data structure in a memory area of the cache corresponding to the memory of the second controller.

7. The method of claim 6, wherein the data structure is a hash table and making the determination that the data resides in the cache uses a hash table lookup on a cache address from the recovery control block.

8. A data storage system comprising:

a memory containing machine readable medium comprising machine executable code having stored thereon;

a processing module, coupled to the memory, to execute the machine executable code to;

receive a request for data from a host at a first controller of the storage appliance, wherein the data is associated with a logical unit number (LUN) owned by a second controller of the storage appliance;

make a determination that the data resides in a cache on the first controller, wherein the cache contains information stored in a memory of the second controller; and

upon determining that the data resides in the cache, return the data from the cache to the host.

9. The system of claim 8, wherein the processing module is to further:

upon determining that the data does not reside in the cache, retrieve the data from the LUN without accessing the second controller; and

return the data to the host.

10. The system of claim 8, wherein the processing module is to further:

upon determining that the data resides in the cache, suspend acknowledgments to the second controller until the cache is no longer being read.

11. The system of claim 8, wherein the storage appliance is in an asymmetric active/active configuration.

12. The system of claim 8, wherein the second controller is a primary controller for storing write request data from the host to the LUN, and the first controller is an alternate controller for storing write request data from the host to the LUN.

13. The system of claim 8, wherein the processing module is to further:

receive a mirror operation at the first controller from the second controller, wherein the mirror operation includes a recovery control block containing data associated with the LUN owned by the second controller;

create a cache control block associated with the recovery control block; and

store the cache control block in a data structure in a memory area of the cache corresponding to the memory of the second controller.

14. The system of claim 13, wherein the data structure is a hash table and making the determination that the data resides in the cache uses a hash table lookup on a cache address from the recovery control block.

15. A computer-readable medium for retrieving data in a storage appliance, the computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations that include:

receiving a request for data from a host at a first controller of the storage appliance, wherein the data is associated with a logical unit number (LUN) owned by a second controller of the storage appliance;

making a determination that the data resides in a cache on the first controller, wherein the cache contains information stored in a memory of the second controller; and

upon determining that the data resides in the cache, returning the data from the cache to the host.

16. The computer-readable medium of claim 15, further comprising instructions for:

upon determining that the data does not reside in the cache, retrieving the data from the LUN without accessing the second controller; and

returning the data to the host.

17. The computer-readable medium of claim 15, further comprising instructions for:

upon determining that the data resides in the cache, suspending acknowledgments to the second controller until the cache is no longer being read.

18. The computer-readable medium of claim 15, wherein the storage appliance is in an asymmetric active/active configuration.

19. The computer-readable medium of claim 15, wherein the second controller is a primary controller for storing write request data from the host to the LUN, and the first controller is an alternate controller for storing write request data from the host to the LUN.

20. The computer-readable medium of claim 15, further comprising instructions for:

receiving a mirror operation at the first controller from the second controller, wherein the mirror operation includes a recovery control block containing data associated with the LUN owned by the second controller;

creating a cache control block associated with the recovery control block; and

storing the cache control block in a data structure in a memory area of the cache corresponding to the memory of the second controller.