Apparatus for performing storage virtualization

• US 20070239944A1
• Filed: 02/16/2007
• Published: 10/11/2007
• Est. Priority Date: 02/17/2006
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Emulex Design & Manufacturing Corp. (Broadcom, Inc.)
• Inventors: Bhide, Parag, Rupanagunta, Sriram
• Granted Patent: US 9,032,164 B2
• Time in Patent Office: Days
• US Class Current: 711/147
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 11/2005 using redundant communication controllers
• CPC Class Codes: G06F 11/201 between storage system components
• CPC Class Codes: G06F 11/2033 switching over of hardware resources
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 3/0607 by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0664 at device level, e.g. emulation of a storage device or system
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 45/62 Wavelength based optical switching H04Q11/0062

Abstract

The splitting of storage applications and functions into a control path (CP) component and a data path (DP) component is disclosed. Reads and writes may be handled primarily in the DP. The CP may be responsible for discovery, configuration, and exception handling. The CP can also be enabled for orchestrating complex data management operations such as snapshots and migration. Storage virtualization maps a virtual I/O to one or more physical I/O. A virtual target (vTarget) in the virtual domain is associated with one physical port in the physical domain. Each vTarget may be associated with one or more virtual LUNs (vLUNs). Each vLUN includes one or more vExtents. Each vExtent may point to a region table, and each entry in the region table may contain a pointer to a region representing a portion of a pExtent, and attributes (e.g. read/write, read only, no access) for that region.

Claims

1. An apparatus for performing storage applications on storage using a split-path architecture, comprising:

a first data path (DP) for virtualizing the storage and performing data functions, the first DP including one or more DP processors (DPPs) and memory configured for storing firmware and one or more virtualization tables; and

a first control path (CP) communicatively coupled to the DP, the first CP including one or more CP processors (CPPs) and software configured for performing control functions in conjunction with the first DP.

2. The apparatus of claim 1, the one or more virtualization tables including a virtual disk table (VDT) having one or more virtual disk (vDisk) entries representing a vDisk, each vDisk entry containing one or more virtual extents (vExtents), and each vExtent containing a pointer for mapping the vExtent to a physical extent (pExtent) in the storage.

3. The apparatus of claim 2, wherein at least one vExtent is partitioned into multiple regions, the virtualization tables further including a region table pointed to by the vExtent that is partitioned into the multiple regions, the region table including multiple region table entries, each region table entry containing a pointer for mapping a region in the vExtent to a pExtent.

4. The apparatus of claim 3, the virtualization tables further including a layout table pointed to by either a vExtent or a region table entry, the layout table containing one or more pointers to a pExtent in accordance with a layout table type.

5. The apparatus of claim 1, further comprising a second CP communicatively coupled to the first DP for performing the control functions in conjunction with the first DP should the first CP fail.

6. The apparatus of claim 1, further comprising a second DP communicatively coupled to the first CP for performing the data functions in conjunction with the first CP should the first DP fail.

7. The apparatus of claim 1, the apparatus communicatively coupled to one or more hosts and one or more targets in a storage area network (SAN).

8. A computer comprising the apparatus of claim 1.

9. The apparatus of claim 1, the DP contained within a switch and the CP contained within a computer coupled to the switch.

10. A method for performing storage applications on storage using a split-path architecture, comprising:

virtualizing the storage and performing data functions in a first data path (DP) including one or more DP processors (DPPs) and one or more virtualization tables; and

performing control functions in conjunction with the first DP in a first control path (CP) including one or more CP processors (CPPs).

11. The method of claim 10, the step of virtualizing the storage comprising:

creating a virtual disk table (VDT) as one of the virtualization tables;

creating one or more virtual disk (vDisk) entries representing a vDisk in the VDT;

creating one or more virtual extents (vExtents) in each vDisk entry; and

storing a pointer in each vExtent for mapping the vExtent to a physical extent (pExtent) in the storage.

12. The method of claim 11, further comprising:

partitioning at least one vExtent into multiple regions;

creating a region table pointed to by the vExtent that is partitioned into the multiple regions, the region table including multiple region table entries; and

storing a pointer in each region table entry for mapping a region in the vExtent to a pExtent.

13. The method of claim 12, further comprising:

creating a layout table pointed to by either a vExtent or a region table entry, the layout table containing one or more pointers to a pExtent in accordance with a layout table type.

14. The method of claim 10, further comprising communicatively coupling a second CP to the first DP for performing the control functions in conjunction with the first DP should the first CP fail.

15. The method of claim 10, further comprising communicatively coupling a second DP to the first CP for performing the data functions in conjunction with the first CP should the first DP fail.

16. The method of claim 10, further comprising communicatively coupling the apparatus to one or more hosts and one or more targets in a storage area network (SAN).

17. The method of claim 10, further comprising providing an application programming interface (API) library to the CP for enabling partner applications to be written using the API library to perform virtualization services.

18. The method of claim 11, further comprising processing an input/output (I/O) request in the DP by:

identifying the logical block address (LBA) in the I/O request;

identifying the vExtent to which the LBA belongs;

using the pointer in the vExtent to identify the pExtent involved in the I/O request; and

forwarding the I/O request to the identified pExtent.

19. The method of claim 12, further comprising processing an input/output (I/O) request in the DP by:

identifying the logical block address (LBA) in the I/O request;

identifying the vExtent and the region to which the LBA belongs;

using the pointer in the vExtent to identify the region table associated with the vExtent;

accessing the region table entry corresponding to the identified region to determine the pExtent involved in the I/O request;

determining an access attribute for the pExtent; and

forwarding the I/O request to the identified pExtent if access is allowed in accordance with the access attribute.

20. The method of claim 13, further comprising processing an input/output (I/O) request in the DP by:

identifying the logical block address (LBA) in the I/O request;

identifying the vExtent and the region to which the LBA belongs;

using the pointer in the vExtent to locate the layout table associated with the vExtent; and

forwarding the I/O request to the one or more pExtents pointed to in the layout table.

21. The method of claim 20, further comprising faulting the I/O request to the CP for exception handling if access to the pExtent is not allowed in accordance with the access attribute.

22. The method of claim 11, further comprising performing a snapshot by:

copying a first vDisk to a second vDisk, and maintaining all pointers stored in the first vDisk in the second vDisk;

setting all region attributes in the first vDisk to have no write access;

if a write request for a particular region in the first vDisk is received,

faulting the write request to the CP for delayed processing,

performing a block copy of a particular pExtent in a first physical LUN (PLUN) pointed to by the particular region to a new pExtent in a second pLUN,

changing the pointer in the region in the second vDisk corresponding to the particular region in the first vDisk to point to the new pExtent in the second pLUN,

setting the region attribute for the particular region in the first vDisk to read/write access, and

allowing the faulted write request to be forwarded to the particular pExtent in the first pLUN.

23. The method of claim 11, further comprising performing data migration by:

setting an attribute of a region in a vDisk pointing to a particular pExtent in a first physical disk (pDisk) to be migrated to have no write access;

performing a block copy of the particular pExtent in the first pDisk to a new pExtent in a second pDisk;

if a write request for the region in the vDisk is received during the block copy process, faulting the write request to the CP for delayed processing;

changing the pointer in the region in the vDisk to point to the new pExtent in the second pDisk after the block copy process is completed;

setting the attribute for the region in the vDisk to read/write access; and

allowing any faulted write request to be forwarded to the new pExtent in the second pDisk.

24. The method of claim 13, wherein one layout type is a mirroring layout type containing two pointers to different pExtents to perform a mirroring function.

25. The method of claim 24, further comprising utilizing the mirroring layout type when receiving a write request to a target to write data to a caching appliance in addition to the target.

26. The method of claim 24, further comprising utilizing the virtualized storage to create a hierarchical arrangement of vDisks.