Data transmission from raid services

• US 6,950,966 B2
• Filed: 07/17/2001
• Issued: 09/27/2005
• Est. Priority Date: 07/17/2001
• Status: Expired due to Term

• Current Assignee: SeaChange International Incorporated
• Original Assignee: SeaChange International Incorporated
• Inventors: Raspuzzi, Michael D., Mann, Bruce, Chiquoine, Kenneth F., Trasatti, Philip J.
• Primary Examiner(s): Baderman, Scott
• Assistant Examiner(s): Damiano, Anne L.
• Application Number:
  US09/907,534
• Publication Number:
  US 20030016596A1
• Time in Patent Office: 1,533 Days
• Field of Search: 714/6, 714/8, 714/42, 711/137, 711/114
• US Class Current: 714/42
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity

Abstract

A redundant array includes a plurality of disks, a bus coupling the disks, a receiving device, and a device to reconstruct a block stored in one of the disks. The device reconstructs the block with associated data and parity blocks from other disks. The device transmits the reconstructed block to the receiving device in response to the one of the disks being unavailable or degraded.

Claims

1. A method for reading data from a clustered system of a plurality of redundant array of inexpensive disks (RAID) device configurations, the method comprises:

receiving a message from a requesting one of members of the clustered system that indicates a next location for a particular block for a subsequent read operation from a drive in the RAID device configurations; and

returning to the requesting one of members of the clustered system a hint that indicates the state of the drive in the RAID device configurations corresponding to the next location for the subsequent read operation;

wherein returning the hint instructs the requesting member to start a recovery process or requesting process without waiting for degradation of performance to occur.

2. The method of claim 1 wherein the hint indicates that performance of the device is degraded or the drive is unavailable.

3. The method of claim 1 wherein the system returns a next bad byte offset message to the requesting member.

4. The method of claim 1 wherein the requesting member will skip the drive and instead read redundant information and at least one data block from one of the other drives in the RAID device configurations.

5. The method of claim 1 wherein the requesting member will skip the drive and reconstruct data from the skipped drive from redundant information from one of the other drives in the RAID device configurations.

6. The method of claim 5 further comprising:

performing an XOR operation on parity and data to reconstruct missing data corresponding to data on the skipped drive.

7. The method of claim 1 further comprising:

requesting a first drive of the RAID device configurations to transmit a first data block stored therein to a receiving device;

reconstructing the first data block from associated data stored in other drives of the RAID device configurations; and

transmitting the reconstructed first data block directly to the receiving device.

8. The method of claim 7 wherein the reconstructing and the transmitting are performed in response to receiving the hint indicating that performance of the drive is degraded or the drive is unavailable.

9. The method of claim 1 wherein a disk controller returns a next bad byte offset, and the requesting member receives the next byte offset and determines that the RAID device configurations has a bad or reconstructing drive.

10. A clustered system of plurality of redundant array of inexpensive disks (RAID) device configurations to transmit data blocks to a receiving device, comprising:

a plurality of cluster members coupled so that any one cluster member can deliver data to at least some of remaining cluster members, each cluster member comprising;

a plurality of disks adapted to store the blocks and to transmit the stored blocks to the receiving device;

a processor to control reads from and writes to the plurality of disks; and

a process to receive a message that indicates a next location for a particular block for a subsequent read operation from a drive in the RAID device configurations and produce a hint that indicates the state of the drive in the RAID device configurations corresponding to the next location for the subsequent read operation;

wherein a disk controller returns a next bad byte offset, and the requesting system receives the next bad byte offset and determines that the RAID device configuration has a bad or reconstructing drive.

11. The system of claim 10 further comprising:

a device to reconstruct a particular block from associated blocks and to transmit the reconstructed block to the receiving device in response to the hint that indicated the state of the drive in the RAID device configurations.

12. The system of claim 10 wherein the processor starts a recovery process based on a state of the hint.

13. A clustered configuration comprises:

a plurality of clustered nodes each node comprising a redundant array of inexpensive disks (RAID) and a processor adapted to write blocks to and read blocks from the redundant array of inexpensive disks;

a process to receive a message that indicates a next location for a particular block for a subsequent read operation from a drive in the redundant array of inexpensive disks of one of the nodes and produce a hint that indicates the state of the drive in the redundant array of inexpensive disks corresponding to the next location for the subsequent read operation; and

a device to reconstruct a particular block from associated blocks and parity information and to transmit the reconstructed block to a receiving device in response to the hint that indicates the state of the drive in the redundant array of inexpensive disks.

14. The configuration of claim 13 wherein the hint indicates that performance of the drive is degraded or the drive is unavailable.

15. A method for reading data from a clustered system including a redundant array of disks, the method comprising:

receiving a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor;

returning to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request; and

in response to receiving a hint, requesting redundant information for reconstructing the desired data.

16. The method of claim 15, wherein receiving the first message from the requestor comprises receiving the first message from a device external to the clustered system.

17. The method of claim 15, wherein receiving the first message from the requestor comprises receiving the first message from a member of the clustered system.

18. The method of claim 15, wherein the first message includes a read request.

19. The method of claim 15, wherein the hint indicates that performance of a drive in the redundant array of disks is degraded or a drive in the redundant array of disks is unavailable.

20. The method of claim 15, further comprising:

performing an XOR operation on parity and data to reconstruct the desired data.

21. A method for reading data from a clustered system including a redundant array of disks, the method comprising:

receiving a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor; and

returning to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request;

wherein the hint includes a next bad byte offset.

22. A method for reading data from a clustered system including a redundant array of disks, the method comprising:

receiving a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor; and

returning to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request;

wherein the hint instructs the requestor to start a recovery process or requesting process without waiting for degradation of performance to occur.

23. A clustered system comprising:

a plurality of cluster members coupled so that any one cluster member can deliver data to at least some of remaining cluster members, each cluster member comprising;

a redundant array of disks adapted to transmit stored data to a requestor; and

a processor configured to

receive a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor, and

return to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request;

wherein the requestor is configured to, in response to receiving a hint, request redundant information for reconstructing the desired data.

24. The system of claim 23, wherein receiving the first message from the requestor comprises receiving the first message from a device external to the clustered system.

25. The system of claim 23, wherein receiving the first message from the requestor comprises receiving the first message from a member of the clustered system.

26. The system of claim 23, wherein the first message includes a read request.

27. The system of claim 23, wherein the hint indicates that performance of a drive in the redundant array of disks is degraded or a drive in the redundant array of disks is unavailable.

30. The system of claim 23, wherein the requestor is further configured to perform an XOR operation on parity and data to reconstruct the desired data.

28. A clustered system comprising:

a plurality of cluster members coupled so that any one cluster member can deliver data to at least some of remaining cluster members, each cluster member comprising;

a redundant array of disks adapted to transmit stored data to a requestor; and

a processor configured to

receive a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor, and

return to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request;

wherein the hint includes a next bad byte offset.

29. A clustered system comprising:

a plurality of cluster members coupled so that any one cluster member can deliver data to at least some of remaining cluster members, each cluster member comprising;

a redundant array of disks adapted to transmit stored data to a requestor; and

a processor configured to

receive a first message at a member of the clustered system from a requestor, the first message indicating next desired data to be requested in a subsequent read request from the requestor; and

return to the requestor a hint characterizing an ability of the redundant array of disks to respond to the subsequent read request;

wherein the hint instructs the requestor to start a recovery process or requesting process without waiting for degradation of performance to occur.