Centralized fine-grained enhancements for distributed table driven I/O mapping

• US 20020029326A1
• Filed: 06/01/2001
• Published: 03/07/2002
• Est. Priority Date: 06/02/2000
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Helliwell, Richard P., Thiel, David W., Reuter, James M.
• Granted Patent: US 7,720,928 B2
• Time in Patent Office: Days
• US Class Current: 711/206
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; 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], H04L67/1097
• CPC Class Codes: G06F 11/0772 Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0683 Plurality of storage devices

Abstract

In response to these and other needs, the present invention provides a virtual storage system that generally uses larger segmentations, but has the ability to divide the large segments into smaller sub-segments during data movement operations. The mapping has large segments except for those segments undergoing data movement. For those segments being moved, the mapping uses the smallest segment size possible, namely, a single disk block. The present invention provides a method and system having this hierarchy of segment sizes, a large segment for normal uses and breaking the large segment into single disk blocks during data movement. In this way, the administration costs are generally low, but latencies caused by the movement of large data blocks are avoided. The hierarchy of segment sizes is accomplished through a distributed virtual storage system having a controller that manages a mapping table and multiple agents that present the mapping to devices on the network. The present invention adapts the mapping table to include a first and a second storage locations and a bit map of the actual storage segments. When the first storage location is occupied during a move operation, the controller causes other I/O operations to occur at the second location. The bitmap stores, on a block by block basis, the blocks at the second location affected by the I/O operations. During future operations, the mapping table maps to first the storage location, except for the block indicated in the bitmap. The bitmap is stored only by the controller and is sent out to the agents as part of an instruction to read from parts of first storage location not contained in the bitmap and parts of the second storage location contained in the bitmap.

Claims

1. A virtual storage system for mapping virtual storage segments of differing sizes to storage locations, comprising:

an agent coupled to the host, the agent having volatile memory for storing a first table, the table having entries to map the virtual storage segments to the storage locations; and

a controller coupled to the agent, the controller having non-volatile memory for storing a second table, the controller intermittently causing contents of the first table to be replaced by contents of the second table,

whereby during an input/output (I/O) operation, the host accesses one of the entries in the first table to determine one of the storage locations.

2. The system of claim 1, wherein the second table identifies an alternate storage location within the storage locations.

3. The system of claim 2, wherein the second table further includes a bitmap that having entries that correspond to blocks of data stored within the alternate storage location.

4. The system of claim 1, further comprising an alternate storage container comprising alternate storage locations of the storage location correlating to the virtual storage segments.

5. The system of claim 4, wherein an I/O operation accesses information on both the storage location and the alternative storage location.

6. The system of claim 5 wherein a bitmap designates blocks at the alternative storage location to use for the I/O operation.

7. A system for mapping a virtual disk segment to a storage location within a storage device, such that a host queries said system to determine said storage location for input/output operations, said system comprising:

a first table having a first table entry mapping the virtual disk segment to the storage location;

a second table having a second table entry corresponding to said storage location and to an alternate storage location, and block bitmap information identifying blocks of data having differing sizes within the alternate storage location;

a plurality of variables indicating states of the entry;

an offset for the entry, wherein the offset includes a logic unit number identifier and a block identifier;

a first memory to store the first table and

a second memory to store the second table.

8. The system of claim 7, wherein said first memory is a volatile memory.

9. The system of claim 7, wherein said second memory is a non-volatile memory.

10. The system of claim 7, wherein the states include a no-write state.

11. The system of claim 7, wherein the states include an error state.

13. The method of claim 12, wherein the turning off step includes activating an invalid state.

14. The method of claim 12, wherein a subsequent read operation for the virtual segment occur at portions of the first storage location not included in the identified portions and the portions of the second storage location associated with the identified portions. .

15. The method of claim 14, wherein the first table is stored by an agent and during the read operation, the record of the identified portions is sent to the agent.

16. The method of claim 15, wherein the mapping between the virtual storage segment and first storage location is contained in numerous first tables, each of the first table stored by a different agent.

12. A method for performing an input/output operation on a virtual storage segment defined by a first table that maps the storage segment to a first storage location, the method comprising:

turning off input/output operations at the first storage location;

identifying portions of the virtual storage segment to be effected during the write operation;

storing a record of the identified portions at a second table and not at the first table; and

writing to a second storage location, whereby the writing operation occurs at portions of the second storage location associated with the identified portions.