System and Method for Raid Recovery Arbitration in Shared Disk Applications

• US 20080215912A1
• Filed: 04/17/2008
• Published: 09/04/2008
• Est. Priority Date: 04/26/2005
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: Fernandez, Anthony, Ahmadian, Mahmoud
• Granted Patent: US 7,650,463 B2
• Time in Patent Office: Days
• US Class Current: 714/6
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality

Abstract

A RAID controller is provided for each host sharing a RAID. Each RAID controller can determine whether another host is sharing the RAID and assume a master or slave status with respect to rebuild operations for the shared disk. The master controller may then manage any rebuild operations on rebuild disks within the RAID.

Claims

1-20. -20. (canceled)

21. An information handling system, comprising:

a redundant array of independent disks (RAID) having a plurality of storage disks;

a first host in operative communication with the RAID and having a first RAID controller assigned as a master RAID controller; and

a second host in operative communication with the RAID and having a second RAID controller assigned as a slave RAID controller;

wherein a particular one of the RAID controllers is configured to;

compare a transaction level of the master RAID controller with a transaction level of the slave RAID controller; and

select either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller.

22. An information handling system according to claim 21, wherein the particular RAID controller is configured to:

select the master RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is lower than the transaction level of the slave RAID controller; and

select the slave RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is higher than the transaction level of the slave RAID controller.

23. An information handling system according to claim 21, wherein:

the first RAID controller assumed the master RAID controller status in response to determining that no other host was sharing the RAID during initialization of the first RAID controller; and

the second RAID controller assumed the slave RAID controller status in response to determining that the first host was sharing the RAID during initialization of the second RAID controller.

24. An information handling system according to claim 21, wherein:

the transaction level of the master RAID controller is based on the number of transactions handled by the master RAID controller; and

the transaction level of the slave RAID controller is based on the number of transactions handled by the slave RAID controller.

25. An information handling system according to claim 21, wherein the RAID comprises a plurality of virtual disks.

26. An information handling system according to claim 21, wherein the particular RAID controller is configured to:

compare a first SCSI ID assigned to the first host with a second SCSI ID assigned to the second host; and

select either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on (a) the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller and (b) the results of the comparison between the first SCSI ID assigned to the first host with the second SCSI ID assigned to the second host.

27. An information handling system according to claim 21, wherein the particular RAID controller is configured to:

access a first SCSI ID assigned to the first host and a second SCSI ID assigned to the second host; and

if the master RAID controller and the slave RAID controller have a substantially equal transaction level, utilize the first SCSI ID and the second SCSI ID to select which RAID controller to perform the rebuild operation.

28. An information handling system according to claim 21, wherein the particular RAID controller comprises the master RAID controller.

29. A redundant array of independent disks (RAID) controller operable to communicate with a RAID in a shared disk environment, the RAID controller assigned as a master RAID controller and comprising:

logic instructions configured to;

compare a transaction level of the master RAID controller with a transaction level of a slave RAID controller in communication with the RAID; and

select either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller.

30. A master RAID controller according to claim 29, further comprising logic instructions configured to:

select the master RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is lower than the transaction level of the slave RAID controller; and

select the slave RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is higher than the transaction level of the slave RAID controller.

31. A master RAID controller according to claim 29, the master RAID controller having assumed master RAID controller status in response to determining that no other host was sharing the RAID during initialization of the first RAID controller.

32. A master RAID controller according to claim 29, further comprising logic instructions configured to:

compare a first SCSI ID assigned to the first host with a second SCSI ID assigned to the second host; and

select either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on (a) the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller and (b) the results of the comparison between the first SCSI ID assigned to the first host with the second SCSI ID assigned to the second host.

33. A master RAID controller according to claim 29, further comprising logic instructions configured to:

access a first SCSI ID assigned to the first host and a second SCSI ID assigned to the second host; and

if the master RAID controller and the slave RAID controller have a substantially equal transaction level, utilize the first SCSI ID and the second SCSI ID to select which RAID controller to perform the rebuild operation.

34. A master RAID controller according to claim 29, wherein the logic instructions are embodied in firmware.

35. A master RAID controller according to claim 29, wherein:

the transaction level of the master RAID controller is based on the number of transactions handled by the master RAID controller; and

the transaction level of the slave RAID controller is based on the number of transactions handled by the slave RAID controller.

36. A method for managing a disk rebuild operation in a system including a redundant array of independent disks (RAID) having a plurality of storage disks, a first host coupled to the RAID and having a RAID controller assigned as a master RAID controller, and a second host coupled to the RAID and having a RAID controller assigned as a slave RAID controller, the method comprising:

monitoring a transaction level of the master RAID controller;

monitoring a transaction level of the slave RAID controller;

comparing the transaction level of the master RAID controller with the transaction level of a slave RAID controller; and

selecting either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller.

37. A method according to claim 36, further comprising:

selecting the master RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is lower than the transaction level of the slave RAID controller; and

selecting the slave RAID controller to perform the disk rebuild operation if the transaction level of the master RAID controller is higher than the transaction level of the slave RAID controller.

38. A method according to claim 36, further comprising:

the master RAID controller having assumed master status in response to determining that no other host was sharing the RAID during initialization of the master RAID controller; and

the slave RAID controller having assumed slave status in response to determining that another host was sharing the RAID during initialization of the slave RAID controller.

39. A method according to claim 36, further comprising:

comparing a first SCSI ID assigned to the first host with a second SCSI ID assigned to the second host; and

selecting either the master RAID controller or the slave RAID controller to perform a disk rebuild operation based at least on (a) the results of the comparison between the transaction levels of the master RAID controller and the slave RAID controller and (b) the results of the comparison between the first SCSI ID assigned to the first host with the second SCSI ID assigned to the second host.

40. A method according to claim 36, further comprising:

accessing a first SCSI ID assigned to the first host and a second SCSI ID assigned to the second host; and

if the master RAID controller and the slave RAID controller have a substantially equal transaction level, utilizing the first SCSI ID and the second SCSI ID to select which RAID controller to perform the rebuild operation.