SCALABLE CLOUD STORAGE ARCHITECTURE

• US 20120179874A1
• Filed: 01/07/2011
• Published: 07/12/2012
• Est. Priority Date: 01/07/2011
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chang, Rong N., Tang, Chunqiang, Tak, Byung C.
• Application Number:
  US12/986,466
• Publication Number:
  US 20120179874A1
• Time in Patent Office: Days
• US Class Current: 711/128
• CPC Class Codes: G06F 11/1453 using de-duplication of the data
• CPC Class Codes: G06F 12/0802 Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
• CPC Class Codes: G06F 12/0808 with cache invalidating means G06F12/0815 takes precedence
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 2009/45579 I/O management, e.g. providing access to device drivers or storage
• CPC Class Codes: G06F 2009/45583 Memory management, e.g. access or allocation
• CPC Class Codes: G06F 2212/152 Virtualized environment, e.g. logically partitioned system
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

a virtual storage module operable to run in a virtual machine monitor may include a wait-queue operable to store incoming block-level data requests from one or more virtual machines. In-memory metadata may store information associated with data stored in local persistent storage that is local to a host computer hosting the virtual machines. The data stored in local persistent storage replicates a subset of data in one or more virtual disks provided to the virtual machines. The virtual disks are mapped to remote storage accessible via a network connecting the virtual machines and the remote storage. A cache handling logic may be operable to handle the block-level data requests by obtaining the information in the in-memory metadata and making I/O re-quests to the local persistent storage or the remote storage or combination of the local persistent storage and the remote storage to service the block-level data requests.

Claims

1. A storage system for handling data for virtual machines, comprising:

a virtual storage module operable to run in a virtual machine monitor, the virtual storage module including at least,

a wait-queue operable to store incoming block-level data requests from one or more virtual machines;

in-memory metadata for storing information associated with data stored in local persistent storage that is local to a host computer hosting the virtual machines, the data stored in local persistent storage being replication of a subset of data in one or more virtual disks provided to the virtual machines, the virtual disks being mapped to remote storage accessible via a network connecting the virtual machines and the remote storage; and

a cache handling logic operable to handle the block-level data requests by obtaining the information in the in-memory metadata and making I/O requests to the local persistent storage or the remote storage or combination of the local persistent storage and the remote storage to service the block-level data requests.

2. The system of claim 1, wherein the in-memory metadata includes at least virtual disk identifier that identifies a virtual disk stored on the remote storage, remote address of the data in the remote storage, a bit vector that indicates whether the data is valid, and a dirty bit that indicates whether the data is modified.

3. The system of claim 2, wherein the virtual storage module manages block groups and performs I/O requests to the local persistent storage in units of one or more predetermined sized blocks.

4. The system of claim 3, wherein each block stored in the local persistent storage includes a trailer that stores metadata of the block and hash value of the block used for checking data integrity of data content of the block, wherein after a host crash and recovery, the virtual storage module can examine the trailer to determine a virtual disk that owns said each block stored in the local persistent storage, and determine whether the data content of the block and the hash value are consistent.

5. The system of claim 4, wherein the data content of the block and the trailer are read and written together in a single disk I/O operation.

6. The system of claim 3, wherein the virtual storage module organizes the local persistent storage as set-associative cache structured into a table-like structure with rows and columns, each of the rows having multiple block groups wherein the block groups in a same row are laid out in logically contiguous disk blocks, and wherein each block group in the same row can store contents coming from a different virtual disk.

7. The system of claim 6, wherein the one or more predetermined sized blocks can store data and metadata associated with the data, and wherein the in-memory metadata includes each of the metadata stored in the one or more predetermined sized blocks.

8. The system of claim 7, wherein the predetermined sized blocks can further store hash value of the data.

9. The system of claim 1, wherein the cache handling logic replaces data in the local persistent storage based on a score determined from summing weighted values associated with how recently the data was accessed, how sequential the data is with respect to an adjacent data, how far away the data is from a base row, how sequential the data would be if new block is cached, how far away from the base row the data would be if a new block is cached, and whether the data is modified.

10. The system of claim 1, wherein the virtual storage module automatically destages modified data in the local persistent storage to the remote storage in response to determining that the modified data has reached a threshold.

11. The system of claim 10, wherein the virtual storage module further determines how many blocks of data to destage at a given time based on total allowed data transmission size including combined data transmission size for both remote storage accesses and destaging.

12. The system of claim 1, wherein the in-memory metadata are persisted on disk in a write-through manner to guarantee data integrity in an event of a host crash.

13. A method for handling data storage for virtual machines, comprising:

intercepting one or more incoming block-level data requests received by a virtual machine monitor from one or more virtual machines;

obtaining from in-memory metadata, information associated with data of the block-level data request, the in-memory metadata for storing information associated with data stored in local persistent storage that is local to a host computer hosting the virtual machines, the data stored in local persistent storage being replication of a subset of data in one or more virtual disks provided to the virtual machines, the virtual disks being mapped to remote storage accessible via a network connecting the virtual machines and the remote storage; and

making I/O requests to the local persistent storage or the remote storage or combination of the local persistent storage and the remote storage to service the block-level data requests.

14. The method of claim 13, wherein the in-memory metadata includes at least virtual disk identifier that identifies a virtual disk stored on the remote storage, remote address of the data in the remote storage, a bit vector that indicates whether the data is valid, and a dirty bit that indicates whether the data is modified.

15. The method of claim 14, further including managing block groups and performing I/O requests to the local persistent storage in units of predetermined sized blocks.

16. The method of claim 15, further including organizing the local persistent storage as set-associative cache structured into a table-like structure with rows and columns, each of the rows having multiple block groups wherein the block groups in a same row are laid out in logically contiguous disk blocks, and wherein each block group in the same row can store contents coming from a different virtual disk

17. The method of claim 16, wherein the one or more predetermined sized blocks can store data and metadata associated with the data, and wherein the in-memory metadata includes each of the metadata stored in the one or more predetermined sized blocks.

18. The method of claim 17, wherein the predetermined sized blocks can further store hash value of the data.

19. The method of claim 13, further including replacing data in the local persistent storage based on a score determined from summing weighted values associated with how recently the data was accessed, how sequential the data is with respect to an adjacent data, how far away the data is from a base row, how sequential the data would be if new block is cached, how far away from the base row the data would be if a new block is cached, and whether the data is modified.

20. The method of claim 13, further including automatically destaging modified data in the local persistent storage to the remote storage in response to determining that the modified data has reached a threshold.

21. The method of claim 20, further including determining how many blocks of data to destage at a given time based on total allowed data transmission size including combined data transmission size for both remote storage accesses and destaging.

24. The computer readable storage medium of claim 20, further including managing block groups and performing I/O requests to the local persistent storage in units of predetermined sized blocks.

25. The computer readable storage medium of claim 24, further including organizing the local persistent storage as set-associative cache structured into a table-like structure with rows and columns, each of the rows having multiple block groups wherein the block groups in a same row are laid out in logically contiguous disk blocks, wherein each block group in the same row can store contents coming from a different virtual disk, wherein the one or more predetermined sized blocks can store data and metadata associated with the data, and wherein the in-memory metadata includes each of the metadata stored in the one or more predetermined sized blocks.

22. A computer readable storage medium storing a program of instructions executable by a machine to perform a method for handling data storage for virtual machines, comprising:

intercepting one or more incoming block-level data requests received by a virtual machine monitor from one or more virtual machines;

obtaining from in-memory metadata, information associated with data of the block-level data request, the in-memory metadata for storing information associated with data stored in local persistent storage that is local to a host computer hosting the virtual machines, the data stored in local persistent storage being replication of a subset of data in one or more virtual disks provided to the virtual machines, the virtual disks being mapped to remote storage accessible via a network connecting the virtual machines and the remote storage; and

making I/O requests to the local persistent storage or the remote storage or combination of the local persistent storage and the remote storage to service the block-level data requests.

23. The computer readable storage medium of claim 22, wherein the in-memory metadata includes at least virtual disk identifier that identifies a virtual disk stored on the remote storage, remote address of the data in the remote storage, a bit vector that indicates whether the data is valid, and a dirty bit that indicates whether the data is modified.