Shadow live migration over a smart network interface card
A smart network interface card in an information handling system monitors a local host memory associated with a computer resource for an update to a memory page in the local host memory. After the update to the memory page, the smart network interface card copies the memory page to its memory. The smart network interface card sets a watchdog timer to detect a failure in an the information handling system that hosts the computer resource and if the failure is detected, then the smart network interface card migrates the computer resource from its to another information handling system.
1. A method comprising:
subsequent to enabling asynchronous replication of a local host memory, monitoring, by a processor of an information handling system, the local host memory for an update to a memory page in the local host memory, wherein the local host memory is associated with a computer resource;
subsequent to the update to the memory page, copying the memory page to a memory associated with a smart network interface card;
setting a watchdog timer to detect a failure in the information handling system that hosts the computer resource; and
if the failure is detected, then coordinating with another smart network interface card in another information handling system and migrating the computer resource from the memory associated with the smart network interface card to another memory associated with the other smart network interface card in the other information handling system.
2. The method of claim 1 , wherein the copying of the memory page includes copying machine states associated with the computer resource.
3. The method of claim 1 , wherein the copying of the memory page is performed over a peripheral component interconnect-express interface.
4. The method of claim 1 , wherein the smart network interface card has a power domain distinct from another power domain of the information handling system.
5. The method of claim 1 , further comprising:
caching, by the smart network interface card, a latest memory copy of the computer resource.
6. The method of claim 1 , further comprising:
directly accessing, by the smart network interface card, the local host memory via a compute express link.
7. The method of claim 1 , wherein the computer resource is a virtual machine.
8. An information handling system, comprising:
a watchdog timer configured to detect a failure in the information handling system; and
a processor configured to:
subsequent to enablement of asynchronous replication of a local host memory, monitor the local host memory for an update to a memory page in the local host memory, wherein the local host memory is associated with a computer resource;
subsequent to the update to the memory page, copy the memory page to a memory associated with a smart network interface card; and
if the failure is detected by the watchdog timer, then coordinate with another smart network interface card in another information handling system and migrate the computer resource from the memory associated with the smart network interface card to another memory associated with the other smart network interface card in the other information handling system.
9. The information handling system of claim 8 , wherein to copy the memory page includes to copy machine states associated with the computer resource.
10. The information handling system of claim 8 , wherein to copy of the memory page is performed over a peripheral component interconnect-express interface.
11. The information handling system of claim 8 , wherein the smart network interface card has a power domain distinct from another power domain of the information handling system.
12. The information handling system of claim 8 , wherein the smart network interface card caches a latest memory copy of the computer resource.
13. The information handling system of claim 8 , wherein the smart network interface card has direct access to the local host memory via a compute express link.
14. The information handling system of claim 8 , wherein the computer resource is a container.
15. A non-transitory computer-readable medium including code that when executed causes a processor to perform a method, the method comprising:
subsequent to enabling asynchronous replication of a local host memory, monitoring the local host memory of an information handling system for an update to a memory page in the local host memory, wherein the local host memory is associated with a computer resource;
subsequent to the update to the memory page, copying the memory page to a memory associated with a smart network interface card;
setting a watchdog timer to detect a failure in the information handling system that hosts the computer resource; and
if the failure is detected, then coordinating with another smart network interface card in another information handling system and migrating the computer resource from the memory associated with the smart network interface card to another memory associated with the other smart network interface card in the other information handling system.
16. The non-transitory computer-readable medium of claim 15 , wherein the copying of the memory page includes copying machine states associated with the computer resource.
17. The non-transitory computer-readable medium of claim 15 , wherein the copying of the memory page is performed over a peripheral component interconnect-express interface.
18. The non-transitory computer-readable medium of claim 15 , wherein the smart network interface card has a power domain distinct from another power domain of the information handling system.
19. The non-transitory computer-readable medium of claim 15 , wherein the smart network interface card caches a latest memory copy of the computer resource.
20. The non-transitory computer-readable medium of claim 15 , wherein the smart network interface card has direct access to the local host memory via a compute express link.