Hypervisor-based server duplication system and method and storage medium storing server duplication computer program

• US 8,997,098 B2
• Filed: 02/05/2013
• Issued: 03/31/2015
• Est. Priority Date: 10/31/2012
• Status: Expired due to Fees

• Current Assignee: Samsung SDS (China) Co., Ltd. (Samsung Group)
• Original Assignee: Samsung SDS (China) Co., Ltd. (Samsung Group)
• Inventors: Lee, Kwang-Hyun, Kim, Jong-Sung
• Primary Examiner(s): Puente, Emerson
• Assistant Examiner(s): KIM, DONG U
• Application Number:
  US13/759,336
• Publication Number:
  US 20140123138A1
• Time in Patent Office: 784 Days
• Field of Search: None
• US Class Current: 718/1
• CPC Class Codes: G06F 11/1484 involving virtual machines
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2041 with more than one idle spare processing component
• CPC Class Codes: G06F 11/2056 by mirroring
• 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 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 2201/815 Virtual middleware or OS functionality using virtual machines to implement generic software techniques for error detection or fault masking G06F11/1484
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Disclosed herein are a server duplication system and method and a storage medium storing a server duplication computer program. The server duplication system includes a primary server including a hypervisor including a hypervisor-based fault tolerance module and a first file system virtual machine (FS VM), and a first standby server including a hypervisor including a hypervisor-based fault tolerance module that exchanges data with a fault tolerance module provided on the hypervisor of the primary server and duplicates the primary server. The first FS VM provides a first file system that is shared by a user virtual machine (USER VM), and a buffer cache that is used in conjunction with the first file system is provided on virtual memory. The first FS VM is duplicated into the standby server using the hypervisor-based fault tolerance module of the primary server and the hypervisor-based fault tolerance module of the standby server.

Claims

1. A non-transitory computer-readable storage medium storing a computer program that enables a computer system to perform operations comprising:

generating a first file system virtual machine (FS VM) on a respective hypervisor of a primary server;

installing a file system in the first FS VM;

disposing a buffer cache, operating in conjunction with the file system installed in the first FS VM, in a virtual memory allocated to the first FS VM;

generating a user virtual machine (USER VM) on the respective hypervisor of the primary server so that the USER VM shares the file system of the first FS VM; and

duplicating the buffer cache into a buffer cache of a second FS VM generated on a respective hypervisor of a standby server,

wherein the disposing of the buffer cache, in the virtual memory, comprises;

receiving information about resources allocated to the file system;

allocating resources to the first FS VM according to the information about the resources; and

allocating a storage area of the virtual memory, to the buffer cache, of a size allocated to the first FS VM based on a predetermined ratio and on the information about the resources.

2. The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise managing, by the first FS VM, the buffer cache in a write-back manner.

3. The non-transitory computer-readable storage medium of claim 1, wherein the second FS VM is generated by duplicating the first FS VM into the standby server.

4. The non-transitory computer-readable storage medium of claim 1, wherein:

the respective hypervisor of the primary server and the respective hypervisor of the standby server comprise hypervisor-based fault tolerance modules, respectively; and

the duplicating of the buffer cache further comprises duplicating the buffer cache of the first FS VM into the buffer cache of the second FS VM using the respective fault tolerance module of the respective hypervisor of the primary server and the respective fault tolerance module of the respective hypervisor of the standby server.

5. The non-transitory computer-readable storage medium of claim 4, wherein the duplicating of the buffer cache further comprises:

when the USER VM invokes a data write call, loading write target data in the buffer cache of the first FS VM;

loading the write target data in the buffer cache of the second FS VM via the respective fault tolerance module of the respective hypervisor of the primary server and the respective fault tolerance module of the respective hypervisor of the standby server; and

once the loading of the write target data in the buffer cache of the second FS VM has been completed, returning a response to the data write call.

6. The non-transitory computer-readable storage medium of claim 1, wherein the duplicating of the buffer cache is performed by duplicating the FS VM generated on the primary server into the standby server.

7. The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise adjusting a size of the buffer cache depending on a number of user virtual machines (USER VMs) generated on the primary server.

8. The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise adjusting a size of the buffer cache depending on a number of data write calls made by all USER VMs generated on the primary server.

9. The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise requesting, by the first FS VM, the hypervisor of the primary server to cause data, loaded in the buffer cache, to be flushed based on at least one of an amount of I/O of the primary server and an amount of use of the buffer cache.

10. A method of duplicating a primary server into a standby server that is a fault tolerance partner of a primary server, comprising:

generating a first FS VM on a hypervisor of the primary server that provides a file system that is outsourced by a USER VM generated on the respective hypervisor of the primary server;

generating a second FS VM on a respective hypervisor of the standby server that provides the same file system that is outsourced by the USER VM that is duplicated on the respective hypervisor of the standby server;

disposing a first buffer cache, that the first FS VM manages in conjunction with the file system, in a virtual memory allocated to the first FS VM; and

duplicating the buffer cache into a second buffer cache that the second FS VM manages in conjunction with the file system,

wherein the disposing of the first buffer cache in the virtual memory comprises;

receiving information about resources allocated to the file system;

allocating resources to the first FS VM according to the information about the resources; and

allocating a storage area of the virtual memory, to the first buffer cache, of a size allocated to the first FS VM based on a predetermined ratio and on the information about the resources.

11. The method of claim 10, wherein:

the respective hypervisor of the primary server and the respective hypervisor of the standby server comprise hypervisor-based fault tolerance modules, respectively; and

the duplicating of the first buffer cache comprises duplicating the first buffer cache of the first FS VM into the second buffer cache of the second FS VM using the respective fault tolerance module of the respective hypervisor of the primary server and the respective fault tolerance module of the respective hypervisor of the standby server.

12. The method of claim 10, further comprising disposing, by the first FS VM and the second FS VM, the buffer caches in their respective virtual memory areas.

13. The method of claim 12, wherein:

the respective hypervisor of the primary server and the respective hypervisor of the standby server comprise hypervisor-based fault tolerance modules, respectively; and

the duplicating of the first buffer cache comprises duplicating, by a respective fault tolerance module of a respective hypervisor of the primary server, the respective virtual memory area of the first FS VM into the respective virtual memory area of the second FS VM using the respective fault tolerance module of the respective hypervisor of the standby server.

14. A server duplication system, comprising:

a primary server comprising a respective hypervisor including a respective hypervisor-based fault tolerance module and a first file system virtual machine (FS VM); and

a first standby server comprising a respective hypervisor including a respective hypervisor-based fault tolerance module that exchanges data with a fault tolerance module provided on the respective hypervisor of the primary server and duplicates the primary server,

wherein;

the first FS VM provides a first file system that is shared by a USER VM generated on the respective hypervisor of the primary server, and disposes a buffer cache that is used in conjunction with the first file system on virtual memory allocated to the first FS VM;

the first FS VM is duplicated into the standby server using the respective hypervisor-based fault tolerance module of the primary server and the respective hypervisor-based fault tolerance module of the standby server; and

the first FS VM disposes the buffer cache on the virtual memory by receiving information about resources allocated to the first file system, allocating resources to the first FS VM according to the information about the resources, and allocating a storage area of the virtual memory, to the buffer cache, of a size allocated to the first FS VM based on a predetermined ratio and on the information about the resources.

15. The server duplication system of claim 14, wherein the first FS VM allocates a virtual volume to a partial area of virtual storage allocated to the first FS VM, and mounts the first file system in the virtual volume.

16. The server duplication system of claim 15, wherein the first FS VM:

allocates a virtual volume to another partial area of the virtual storage allocated to the first FS VM,

mounts a second file system different from the first file system in the virtual volume, and

provides the second file system that is shared by another USER VM generated on the respective hypervisor of the primary server.

17. The server duplication system of claim 14, further comprising a second standby server including a respective hypervisor that:

includes a respective hypervisor-based fault tolerance module that duplicates the primary server by exchanging data with the respective fault tolerance module provided in the respective hypervisor of the primary server, and

duplicates the first standby server by exchanging data with the respective fault tolerance module provided in the respective hypervisor of the first standby server.

18. The server duplication system of claim 17, wherein, when the primary server crashes, all USER VMs of the primary server are inactivated, all USER VMs of the second standby server are activated, and the first standby server is duplicated into the primary server.