Granted Patent B2

US 9,542,108 · App. 14/320,427 · Granted Jan 10, 2017

Inventor: Philip Andrew White (San Francisco, CA)

Assignee: Scale Computing, Inc.

G06F3/0619G06F3/065G06F3/067G06F3/0647G06F9/5088G06F11/1456G06F17/30088

Abstract

Claims (66)

1. A method comprising:

receiving, at a first node, a first request to initiate a migration operation that migrates a resource from the first node to a second node;

transmitting a second request from the first node to the second node to create a new instance of the resource, wherein the second node, in response to receiving the second request, generates the new instance of the resource in a memory associated with the second node based on a snapshot of the resource captured by the first node and stored in the memory associated with the second node at a previous point in time, wherein the first request is received by the first node after the previous point in time;

collecting, in the first node, a set of changes associated with the resource in a data structure, wherein the set of changes represents any modifications to the resource since the previous point in time during which the snapshot was captured;

transmitting the data structure that includes the set of changes to the second node, wherein the second node is configured to update the new instance of the resource based on the set of changes such that the new instance of the resource on the second node matches the resource on the first node,

determining that a period of time that has elapsed since the start of the migration operation is greater than a timeout period; and

configuring the resource to operate in a protected operating mode,

wherein the timeout period is set dynamically during the migration operation based on characteristics of the migration operation.

2. The method of claim 1 , wherein the resource comprises a virtual storage device.

3. The method of claim 2 , wherein the snapshot comprises an additional data structure that represents a state of the virtual storage device at a particular point in time.

4. The method of claim 2 , further comprising:

collecting an additional set of changes associated with the virtual storage device in an additional data structure while the previous set of changes is transmitted to the second node; and

transmitting the additional data structure that includes the additional set of changes to the second node.

5. The method of claim 4 , further comprising:

determining whether the additional set of changes is below a threshold value; and

if the additional set of changes is below the threshold value, then configuring the virtual storage device to operate in a protected operating mode, or

if the additional set of changes is not below the threshold value, then repeating the steps of collecting one or more additional sets of changes associated with the virtual storage device in one or more additional data structures and transmitting the one or more additional data structures to the second node.

6. The method of claim 5 , wherein placing the virtual storage device into the protected operating mode comprises modifying the permissions of the virtual storage device such that the data on the virtual storage device is marked as read-only.

7. The method of claim 4 , wherein setting the timeout period dynamically comprises:

decreasing the timeout period if the additional set of changes is larger than the previous set of changes; or

increasing the timeout period if the additional set of changes is smaller than the previous set of changes.

8. The method of claim 2 , further comprising freeing memory associated with the virtual storage device on the first node once the new instance of the virtual storage device on the second node matches the virtual storage device on the first node.

9. The method of claim 1 , wherein transmitting the data structure to the second node comprises generating a number of packets in a memory associated with the first node and transmitting the packets to the second node via a network, wherein each packet includes at least a portion of the data structure.

10. The method of claim 1 , wherein the resource comprises a virtual machine.

11. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform steps comprising:

receiving, at a first node, a first request to migrate a resource from the first node to a second node;

transmitting a second request from the first node to the second node to create a new instance of the resource, wherein the second node, in response to receiving the second request, generates the new instance of the resource in a memory associated with the second node based on a snapshot of the resource captured by the first node and stored in the memory associated with the second node at a previous point in time, wherein the first request is received by the first node after the previous point in time;

collecting, in the first node, a set of changes associated with the resource in a data structure, wherein the set of changes represents any modifications to the resource since the previous point in time during which the snapshot was captured;

transmitting the data structure that includes the set of changes to the second node, wherein the second node is configured to update the new instance of the resource based on the set of changes such that the new instance of the resource on the second node matches the resource on the first node;

determining that a period of time that has elapsed since the start of the migration operation is greater than a timeout period; and

configuring the resource to operate in a protected operating mode,

wherein the timeout period is set dynamically during the migration operation based on characteristics of the migration operation.

12. The computer-readable storage medium of claim 11 , wherein the resource comprises a virtual storage device.

13. The computer-readable storage medium of claim 12 , the steps further comprising:

collecting an additional set of changes associated with the virtual storage device in an additional data structure while the previous set of changes is transmitted to the second node; and

transmitting the additional data structure that includes the additional set of changes to the second node.

14. The computer-readable storage medium of claim 13 , the steps further comprising:

determining whether the additional set of changes is below a threshold value; and

if the additional set of changes is below the threshold value, then configuring the virtual storage device to operate in a protected operating mode, or

if the additional set of changes is not below the threshold value, then repeating the steps of collecting one or more additional sets of changes associated with the resource in one or more additional data structures and transmitting the one or more additional data structures to the second node.

15. A system comprising:

a first node comprising a processor and a memory; and

a second node comprising a second processor and an additional memory,

wherein the first node is configured to:

receive a first request to migrate a resource from the first node to the second node,

transmit a second request to the second node to create a new instance of the resource,

collect a set of changes associated with the resource in a data structure, wherein the set of changes represents any modifications to the resource since a previous point in time; and

transmit the data structure that includes the set of changes to the second node,

determine that a period of time that has elapsed since the start of the migration operation is greater than a timeout period, and

configure the resource to operate in a protected operating mode,

wherein the timeout period is set dynamically during the migration operation based on characteristics of the migration operation;

and wherein the second node is configured to:

in response to receiving the second request, generate the new instance of the resource in the additional memory based on a snapshot of the resource captured by the first node and stored in the additional memory at the previous point in time, wherein the first request is received by the first node after the previous point in time, and

update the new instance of the resource based on the set of changes such that the new instance of the resource on the second node matches the resource on the first node.

16. The system of claim 15 , wherein the resource comprises a virtual storage device.

17. The system of claim 16 , wherein the first node is further configured to:

collect an additional set of changes associated with the virtual storage device in an additional data structure while the previous set of changes is transmitted to the second node; and

transmit the additional data structure that includes the additional set of changes to the second node.

18. The system of claim 17 , wherein the first node is further configured to:

determine that a period of time that has elapsed since the start of the migration operation is greater than a timeout period; and

configure the virtual storage device to operate in a protected operating mode.

19. The system of claim 17 , wherein the first node is further configured to:

determine whether the additional set of changes is below a threshold value; and

if the additional set of changes is below the threshold value, then configure the virtual storage device to operate in a protected operating mode, or

if the additional set of changes is not below the threshold value, then repeat the steps of collecting one or more additional sets of changes associated with the virtual storage device in one or more additional data structures and transmitting the one or more additional data structures to the second node.

20. The system of claim 15 , wherein the first node is connected to the second node via a network.

Assignments (18)

Continuity (1)