Intelligent checkpoint page server for containers
A checkpoint server for containers is disclosed. The checkpoint server generates checkpoint images of running containers or of warmed-up containers. These checkpoint images are restored such that the order in which memory pages are accessed can be recorded or logged. During a restore operation to a host, the memory pages are transmitted in accordance with the page order log. The container can then begin serving requests before all of the memory pages have been transmitted to the host.
1. A method, comprising:
generating a checkpoint image of a container running in a simulation environment;
storing the checkpoint image in a storage;
restoring the checkpoint image into the simulation environment;
operating the restored checkpoint image as a container in the simulation environment;
recording memory-page accesses performed by the container running in the simulation environment in an order page log, wherein the order page log is associated with the checkpoint image;
restoring the checkpoint image from the storage to a host, wherein memory pages associated with the checkpoint image are transmitted in an order specified in the order page log.
2. The method of claim 1 , further comprising receiving a container image from a source and storing the container image in a container repository.
3. The method of claim 2 , wherein the container running in the simulation environment corresponds to the container image stored in the container repository.
4. The method of claim 1 , further comprising generating the checkpoint image when the running container is warmed-up and ready to serve requests.
5. The method of claim 1 , further comprising generating the checkpoint image by dumping contents of a memory of the container as memory pages, metadata associated with the container, and network connections into the checkpoint image.
6. The method of claim 5 , further comprising starting the restored container on the host when the metadata is loaded, wherein the memory pages are lazy loaded based on the order page log.
7. The method of claim 6 , further comprising starting the restored container on the host before all of the memory pages in the checkpoint image have been received at the host.
8. The method of claim 1 , further comprising receiving a request from the host for a memory-page that is out of order with respect to the order page log.
9. The method of claim 8 , further comprising updating the order page log based on the request from the host.
10. The method of claim 1 , further comprising storing checkpoint images for disaster recovery.
11. A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
generating a checkpoint image of a container running in a simulation environment;
storing the checkpoint image in a storage;
restoring the checkpoint image into the simulation environment;
operating the restored checkpoint image as a container in the simulation environment;
recording memory-page accesses performed by the container running in the simulation environment in an order page log, wherein the order page log is associated with the checkpoint image;
restoring the checkpoint image from the storage to a host, wherein memory pages associated with the checkpoint image are transmitted in an order specified in the order page log.
12. The non-transitory storage medium of claim 11 , the operations further comprising receiving a container image from a source and storing the container image in a container repository.
13. The non-transitory storage medium of claim 12 , wherein the container running in the simulation environment corresponds to the container image stored in the container repository.
14. The non-transitory storage medium of claim 11 , the operations further comprising generating the checkpoint image when the running container is warmed-up and ready to serve requests.
15. The non-transitory storage medium of claim 11 , the operations further comprising generating the checkpoint image by dumping contents of a memory of the container as memory pages, metadata associated with the container, and network connections into the checkpoint image.
16. The non-transitory storage medium of claim 15 , the operations further comprising starting the restored container on the host when the metadata is loaded, wherein the memory pages are lazy loaded based on the order page log.
17. The non-transitory storage medium of claim 16 , the operations further comprising starting the restored container on the host before all of the memory pages in the checkpoint image have been received at the host.
18. The non-transitory storage medium of claim 11 , the operations further comprising receiving a request from the host for a memory-page that is out of order with respect to the order page log.
19. The non-transitory storage medium of claim 18 , the operations further comprising updating the order page log based on the request from the host.
20. The non-transitory storage medium of claim 11 , the operations further comprising storing checkpoint images for disaster recovery.