Performance in virtual tape libraries

• US 8,055,938 B1
• Filed: 06/09/2006
• Issued: 11/08/2011
• Est. Priority Date: 06/10/2005
• Status: Active Grant

• Current Assignee: AmZetta Technologies, LLC (American Megatrends International, LLC)
• Original Assignee: American Megatrends Incorporated
• Inventors: Vempati, Srinivasa Rao, Chatterjee, Paresh, Grandhi, Suresh, Subramanian, Srikumar
• Primary Examiner(s): LOHN, JOSHUA A
• Application Number:
  US11/450,653
• Time in Patent Office: 1,978 Days
• Field of Search: 714/6, 714/7, 714/6.21, 714/6.24, 711/114
• US Class Current: 714/6.24
• CPC Class Codes: G06F 11/1084 Degraded mode, e.g. caused by single or multiple storage removals or disk failures
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 2211/104 Metadata, i.e. metadata associated with RAID systems with parity
• CPC Class Codes: G06F 2211/1057 Parity-multiple bits-RAID6, i.e. RAID 6 implementations
• CPC Class Codes: G06F 2211/1059 Parity-single bit-RAID5, i.e. RAID 5 implementations
• CPC Class Codes: G06F 2211/108 RAIT, i.e. RAID on tape drive

Abstract

A method, system, apparatus, and computer-readable medium are provided for storing data at a virtual tape library (“VTL”) computer or server. According to one method, a VTL computer maintains one or more storage volumes for use by initiators on an array of mass storage devices. Space on each of the volumes is allocated using thin provisioning. The VTL computer may also include a cache memory that is at least the size of a full stripe of the array. Write requests received at the VTL computer are stored in the cache memory until a full stripe of data has been received. Once a full stripe of data has been received, the full stripe of data is written to the array at once. The array utilized by the VTL computer may include a hot spare mass storage device. When a failed mass storage device is identified, only the portions of the failed device that have been previously written are rebuilt onto the hot spare. The array may be maintained using RAID-5. If one of the mass storage devices in the array fails, any subsequent writes directed to the array may be stored using RAID-0.

Claims

1. A method for storing data at a virtual tape library server computer, the method comprising:

receiving data write requests at the virtual tape library server computer, the data write requests directed to one or more volumes maintained by the virtual tape library server computer on an array of mass storage devices; and

storing data for the write requests on the volumes of the array utilizing thin provisioning comprising

sequentially allocating storage space on the array for write requests such that the data is capable of being stored sequentially on the array in the order that the write requests arrive at the volumes, and

storing the data in the allocated storage space in the same order as the write requests arrive at the volumes by;

providing a cache memory at the virtual tape library server computer at least the size of a full stripe of the array;

caching the data for the write requests in the cache until a full stripe of data has been received; and

in response to determining that a full stripe of data has been received, calculating a parity utilizing the contents of the cache directly, writing the contents of the cache and parity data associated with the parity to the array at one time, wherein the parity is only calculated for the full stripe of the array from the contents of the cache without reading data from the array, and flushing the contents of the cache after writing the contents of the cache to the array.

2. The method of claim 1, wherein the array further comprises a hot spare mass storage device and wherein the method further comprises:

identifying a failed mass storage device in the array;

in response to identifying the failed mass storage device, rebuilding only the written portions of the failed mass storage device onto the hot spare; and

while the written portions of the failed mass storage device are being rebuilt, receiving write requests directed to unwritten portions of the array, and processing the write requests in a non-degraded manner.

3. The method of claim 1, wherein the array comprises a RAID-5 array, and wherein the method further comprises:

detecting a failure of one of the mass storage devices of the array; and

in response to detecting the failure, processing write requests for volumes on the array received after detecting the failure of the mass storage device using RAID-0.

4. The method of claim 3, further comprising:

storing metadata in a configuration area of the array indicating a location on the array where the array was converted to a RAID-0 array.

5. A virtual tape library computer system, the computer system comprising:

an array of mass storage devices storing one or more storage volumes maintained by the computer system;

a cache memory for caching data to be stored on the array, the cache memory sized at least as large as a single stripe of the array;

a central processing unit; and

a memory storing computer-executable instructions which, when executed by the central processing unit, causes the computer system to receive data write requests directed toward the storage volumes of the array, to store the write requests in the cache, to calculate a parity utilizing the contents of the cache directly, to write the contents of the cache and parity data associated with the parity to the array at one time utilizing thin provisioning when the cache memory has accumulated data to fill a single stripe of the array, wherein the parity is only calculated for the full stripe of the array from the contents of the cache without reading data from the array, and to flush the contents of the cache after writing the contents of the cache to the array.

6. The virtual tape library computer system of claim 5, wherein the array further comprises a hot spare mass storage device and wherein the memory stores further computer-executable instructions which, when executed by the central processing unit, causes the computer system to identify a failed mass storage device in the array, in response thereto to rebuild only the written portions of the failed mass storage device onto the hot spare, and to process write requests directed to unwritten portions of the array and received while the rebuild is being performed in a non-degraded manner.

7. The virtual tape library computer system of claim 6, wherein the array comprises a RAID-5 array, and wherein the memory stores further computer-executable instructions which, when executed by the central processing unit, causes the computer system to detect a failure of one of the mass storage devices of the array and to process write requests received after detecting the failure using RAID-0.

8. The virtual tape library computer system of claim 7, wherein the memory stores further computer-executable instructions which, when executed by the central processing unit, causes the computer system to store metadata in a configuration area of the array indicating a location on the array where write requests began to be stored using RAID-0.