Method to perform parallel data migration in a clustered storage environment

• US 20060136691A1
• Filed: 12/20/2004
• Published: 06/22/2006
• Est. Priority Date: 12/20/2004
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: DesRoches, David W., Brown, Michael F., Madnani, Kiran P.
• Granted Patent: US 7,343,467 B2
• Time in Patent Office: Days
• US Class Current: 711/165
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A clustered storage array consists of several nodes coupled to one or more storage systems. The nodes provide a LUN-device for access by a client, the LUN-device mapping to a source logical unit corresponding to areas of storage on the one or more storage systems. A target logical unit corresponds to different areas of storage on the one or more storage systems. The source logical unit is migrated in parallel by the several nodes to the target logical unit.

Claims

1. A method comprising the steps of:

providing a plurality of nodes operational with one or more storage systems;

providing by the nodes a LUN-device for access by a client, the LUN-device mapping to a source logical unit corresponding to areas of storage on the one or more storage systems;

migrating in parallel by two or more of the plurality of nodes the source logical unit to a target logical unit, the target logical unit corresponding to different areas of storage on the one or more storage systems.

2. The method of claim 1 wherein the step of migrating comprises:

defining chunks of data to be moved from the source logical unit to the target logical unit;

providing a bit-mask having one bit for each chunk;

dividing the bit-mask into splices of multiple bits;

performing by each of the two or more of the plurality of nodes the following steps repeatedly until the source logical unit has been fully migrated to the target logical unit;

attempting to lock a splice;

if the splice is successfully locked, then;

copying the chunks of data corresponding to each bit in the splice to the target logical unit;

setting the bits in the bit-mask corresponding to the copied chunks;

unlocking the splice when all the chunks corresponding to the bits in the splice have been copied.

3. The method of claim 2 wherein the plurality of nodes comprises a clustered system, and wherein the source logical unit and target logical unit are logical entities utilizing the clustered system to access the corresponding areas of storage, and wherein the step of copying the chunks operates over the clustered system.

4. The method of claim 3 further comprising the step of canceling the step of migrating at any time, the step of canceling comprising the steps of:

coordinating the cancel request amongst all nodes in the cluster;

preserving the source logical unit and its corresponding LUN-device;

deleting the target logical unit and bit mask.

5. The method of claim 4 further comprising the steps of:

storing multiple copies of the bit mask in the clustered system, each copy having associated with it a checksum;

if any node of the plurality of nodes fails, checking by the surviving node(s) the checksums to identify a valid copy of the bit mask.

6. The method of claim 5 further comprising the step of:

performing synchronous, sequential updates to those copies to ensure only one copy is being updated at any given time.

7. The method of claim 6 wherein the step of migrating completes successfully if any of the plurality of nodes fails.

8. The method of claim 7 further comprising the steps of:

performing an I/O access by a node from a client to the LUN-device during the step of migrating, the step of performing comprising the steps of;

if the I/O access is a read access, returning data from the source logical unit to the client;

if the I/O access is a write access including data to be written;

ascertaining the chunk to which data is to be written;

locking the splice containing the chunk;

if all the bits in the splice are set, then writing the data to be written to the source logical unit and the target logical unit;

if less than all of the bits in the splice are set, then reading the chunks of data in the splice from the source logical unit, combining the data to be written with the chunks of data read, and writing the combined data to the target logical unit and source logical unit;

setting the bits in the bit mask corresponding to the copied chunks;

unlocking the splice.

9. Apparatus comprising:

a plurality of nodes operational with one or more storage systems, the nodes providing a LUN-device for access by a client, the LUN-device mapping to a source logical unit corresponding to areas of storage on the one or more storage systems;

a mechanism on each node for causing two or more of the plurality of nodes to migrate in parallel the source logical unit to a target logical unit, the target logical unit corresponding to different areas of storage on the one or more storage systems.

10. The apparatus of claim 9 wherein the mechanism on each node comprises:

logic for defining chunks of data to be moved from the source logical unit to the target logical unit;

a bit-mask having one bit for each chunk;

logic for dividing the bit-mask into splices of multiple bits;

logic for attempting to lock a splice;

logic for performing the following if the splice is successfully locked;

copying the chunks of data corresponding to each bit in the splice to the target logical unit;

setting the bits in the bit-mask corresponding to the copied chunks;

unlocking the splice when all the chunks corresponding to the bits in the splice have been copied.

11. The apparatus of claim 10 wherein the plurality of nodes comprises a clustered system, and wherein the source logical unit and target logical unit are logical entities utilizing the clustered system to access the corresponding areas of storage, and wherein the logic for copying the chunks operates over the clustered system.

12. The apparatus of claim 11 further comprising logic in the mechanism for canceling the step of migrating at any time, the logic for canceling comprising logic for:

coordinating the cancel request amongst all nodes in the cluster;

preserving the source logical unit and its corresponding LUN-device;

deleting the target logical unit and bit mask.

13. The apparatus of claim 12 further comprising:

multiple copies of the bit-mask in the clustered system, each copy having associated with it a checksum;

logic operational if any node of the plurality of nodes fails for checking by surviving node(s) the checksums to identify a valid copy of the bit mask.

14. The apparatus of claim 13 further comprising logic for performing synchronous, sequential updates to those copies to ensure only one copy is being updated at any given time.

15. The apparatus of claim 14 wherein the source logical unit is successfully migrated to the target logical unit if any of the plurality of nodes fails.

16. The apparatus of claim 15 further comprising the steps of:

logic performing an I/O access by a node from a client to the LUN-device during the step of migrating, the logic for performing comprising;

logic for returning data from the source logical unit to the client if the I/O access is a read access;

logic for performing the following if the I/O access is a write access including data to be written;

ascertaining the chunk to which data is to be written;

locking the splice containing the chunk;

if all the bits in the splice are set, then writing the data to be written to the source logical unit and the target logical unit;

if less than all of the bits in the splice are set, then reading the chunks of data in the splice from the source logical unit, combining the data to be written with the chunks of data read, and writing the combined data to the target logical unit and source logical unit;

setting the bits in the bit mask corresponding to the copied chunks;

unlocking the splice.

17. A program product comprising a computer readable medium having embodied therein a computer program for storing data, the computer program for operation on each of a plurality of nodes, the computer program comprising:

logic for providing a LUN-device for access by a client, the LUN-device mapping to a source logical unit corresponding to areas of storage on the one or more storage systems;

migration logic for migrating data in the source logical unit to a target logical unit, the target logical unit corresponding to different areas of storage on the one or more storage systems, the migration logic for operating in parallel with the migration logic on the other nodes such that each node participates in parallel in the migration of the data.

18. The program product of claim 17 wherein the migration logic comprises:

logic for defining chunks of data to be moved from the source logical unit to the target logical unit;

logic for providing a bit-mask having one bit for each chunk;

logic for dividing the bit-mask into splices of multiple bits;

logic for attempting to lock a splice;

logic for performing the following if the splice is successfully locked;

copying the chunks of data corresponding to each bit in the splice to the target logical unit;

setting the bits in the bit-mask corresponding to the copied chunks;

unlocking the splice when all the chunks corresponding to the bits in the splice have been copied.

19. The program product of claim 18 wherein the plurality of nodes comprises a clustered system, and wherein the source logical unit and target logical unit are logical entities utilizing the clustered system to access the corresponding areas of storage, and wherein the logic for copying the chunks operates over the clustered system.

20. The program product of claim 19 wherein the migration logic further comprises logic for canceling the migrating at any time, the logic for canceling comprising:

logic for coordinating the cancel request amongst all nodes in the cluster;

logic for preserving the source logical unit and its corresponding LUN-device;

logic for deleting the target logical unit and bit mask.

21. The program product of claim 20 further comprising:

logic for providing multiple copies of the bit-mask in the clustered system, each copy having associated with it a checksum;

logic operational if any node of the plurality of nodes fails for checking by surviving node(s) the checksums to identify a valid copy of the bit mask.

22. The program product of claim 21 further comprising logic for performing synchronous, sequential updates to the copies to ensure only one copy is being updated at any given time.

23. The program product of claim 22 wherein the source logical unit is successfully migrated to the target logical unit if any of the plurality of nodes fails.

24. The program product of claim 23 further comprising:

logic for performing an I/O access by a node from a client to the LUN-device during the step of migrating, the logic for performing comprising;

logic for returning data from the source logical unit to the client if the I/O access is a read access;

logic for performing the following if the I/O access is a write access including data to be written;

ascertaining the chunk to which data is to be written;

locking the splice containing the chunk;

if all the bits in the splice are set, then writing the data to be written to the source logical unit and the target logical unit;

if less than all of the bits in the splice are set, then reading the chunks of data in the splice from the source logical unit, combining the data to be written with the chunks of data read, and writing the combined data to the target logical unit and source logical unit;

setting the bits in the bit mask corresponding to the copied chunks;

unlocking the splice.