DYNAMIC HYPERVISOR RELOCATION

• US 20130138995A1
• Filed: 11/30/2011
• Published: 05/30/2013
• Est. Priority Date: 11/30/2011
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Sivaramakrishnan, Ramaswamy, Lu, Jiejun, Wynn, Aaron S.
• Granted Patent: US 8,793,528 B2
• Time in Patent Office: Days
• US Class Current: 714/4.2
• CPC Class Codes: G06F 11/141 for bus or memory accesses
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 11/2043 where the redundant components share a common memory address space
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors

Abstract

A method for managing multiple nodes hosting multiple memory segments, including: identifying a failure of a first node hosting a first memory segment storing a hypervisor; identifying a second memory segment storing a shadow of the hypervisor and hosted by a second node; intercepting, after the failure, a hypervisor access request (HAR) generated by a core of a third node and comprising a physical memory address comprising multiple node identification (ID) bits identifying the first node; modifying the multiple node ID bits of the physical memory address to identify the second node; and accessing a location in the shadow of the hypervisor specified by the physical address of the HAR after the multiple node ID bits are modified.

Claims

1. A method for managing a plurality of nodes hosting a plurality of memory segments, comprising:

identifying a failure of a first node hosting a first memory segment storing a hypervisor;

identifying a second memory segment storing a shadow of the hypervisor and hosted by a second node;

intercepting, after the failure, a hypervisor access request (HAR) generated by a core of a third node and comprising a physical memory address comprising a plurality of node identification (ID) bits identifying the first node;

modifying the plurality of node ID bits of the physical memory address to identify the second node; and

accessing a location in the shadow of the hypervisor specified by the physical address of the HAR after the plurality of node ID bits are modified.

2. The method of claim 1, further comprising:

quiescing, by a dynamic reconfiguration (DR) engine, the hypervisor in response to the failure; and

removing the first node from the plurality of nodes.

3. The method of claim 2, wherein the DR engine is stored in a third memory segment hosted by the third node.

4. The method of claim 2, wherein the DR engine is stored in the second memory segment hosted by the second node.

5. The method of claim 1, wherein the HAR is intercepted by a cache controller in the core, and wherein the plurality of node ID bits of the physical memory address are modified by the cache controller.

6. The method of claim 5, wherein the cache controller is an L2 controller.

7. The method of claim 5, further comprising:

setting a plurality of from_node bits in a control register of the cache controller to identify the first node;

setting a plurality of to_node bits in the control register to identify the second node; and

setting, after identifying the failure, a remap_enable bit in the control register of the cache controller, wherein intercepting the HAR is based on the remap_enable bit.

8. The method of claim 7, further comprising:

generating a comparison by comparing the plurality of node ID bits of the physical memory address to the plurality of from_node bits in the control register,

wherein modifying the plurality of node ID bits of the physical memory address comprises setting, based on the comparison, the plurality of node ID bits to the plurality of to_node bits.

9. The method of claim 1, wherein the core executes a guest operating system using the hypervisor.

10. The method of claim 1, wherein the plurality of destination bits are bits [46:

39] of the physical address.

11. A system comprising:

a first node hosting a first memory segment storing a hypervisor;

a second node operatively connected to the first node and hosting a second memory segment storing a shadow of the hypervisor; and

a third node comprising a core comprising;

a hypervisor access request (HAR) comprising a plurality of node identification (ID) bits identifying the first node; and

a cache controller configured to modify the plurality of node ID bits to identify the second node after a failure of the first node.

12. The system of claim 11, further comprising a third memory segment storing a dynamic reconfiguration (DR) engine configured to:

identify the failure of the first node;

quiesce the hypervisor in response to identifying the failure; and

remove the first node from the plurality of nodes.

13. The system of claim 12, wherein the third node hosts the third memory segment.

14. The system of claim 11, wherein the cache controller is an L2 controller.

15. The system of claim 11, wherein the core further comprises:

a control register comprising a remap_enable bit, a plurality of from_node bits identifying the first node, and a plurality of to_node bits identifying the second node.

16. The system of claim 15, wherein the remap_enable bit, the plurality of from_node bits, and the plurality of to_node bits are set by the DR engine in response to the failure.

17. The system of claim 15, wherein the cache controller is further configured to generate a comparison by comparing the plurality of node ID bits in the physical address with the plurality of from_node bits in the control register, and wherein the control register modifies the plurality of node ID bits, based on the comparison, by setting the plurality of node ID bits to the plurality of to_node bits in the control register.

18. The system of claim 11, wherein the third core executes a guest operating system using the hypervisor.

19. The system of claim 11, wherein the plurality of node ID bits are bits [46:

39] of the physical address.

20. The system of claim of claim 11, wherein the plurality of node ID bits has a cardinality of 8.