Instant recovery as an enabler for uninhibited mobility between primary storage and secondary storage
In accordance with some aspects of the present disclosure, a non-transitory computer readable medium is disclosed. In some embodiments, the non-transitory computer readable medium includes instructions that, when executed by a processor, cause the processor to receive, from a workload hosted on a host of a cluster, first I/O traffic programmed according to a first I/O traffic protocol supported by a cluster-wide storage fabric exposed to the workload as being hosted on the same host. In some embodiments, the workload is recovered by a hypervisor hosted on the same host. In some embodiments, the non-transitory computer readable medium includes the instructions that, when executed by the processor, cause the processor to adapt the first I/O traffic to generate second I/O traffic programmed according to a second I/O traffic protocol supported by a repository external to the storage fabric and forward the second I/O traffic to the repository.
1. A non-transitory computer readable medium comprising instructions that, when executed by a processor, cause the processor to:
recover, by a hypervisor hosted on a host, a workload to run on the host of a cluster comprising a plurality of hosts, the cluster including a virtual disk controller which virtualizes storage resources of the cluster as a storage fabric, wherein the hypervisor recovers the workload before all workload data is retrieved from an external repository;
attach the external repository to the recovered workload as a virtual disk, wherein the external repository is external to the storage fabric, and wherein the external repository is not virtualized by the virtual disk controller;
receive a request including first I/O traffic according to a first I/O traffic protocol from the recovered workload, the request specifying the virtual disk as a recipient;
translate the request to be compatible with the external repository to include second I/O traffic according to a second I/O traffic protocol; and
forward the translated request to the repository, while maintaining availability of the recovered workload.
2. The non-transitory computer readable medium of claim 1 , wherein the request includes I/O traffic protocol that is a hyperconverged infrastructure (HCI) native protocol specific to communication between the hypervisor and the virtual disk controller on the host.
3. The non-transitory computer readable medium of claim 1 , wherein the translated request includes at least one of: Network File System (NFS), Server Message Block (SMB), or Simple Storage Service (S3).
4. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the processor to identify whether a read request can be serviced locally in a cache associated with the virtual disk controller before adapting and forwarding the read request to the repository.
5. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the processor to:
create a child virtual disk mapped to a parent virtual disk that is backed by the repository; and
absorb write requests in the request locally in the child virtual disk.
6. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the processor to migrate data from the repository to the storage fabric while maintaining the availability of the workload.
7. The non-transitory computer readable medium of claim 1 , wherein the virtual disk controller exposes the storage fabric to the workload through a native interface that enables the workload to interact with the virtual disk controller as if it were a direct-attached storage controller.
8. A system comprising:
a cluster including a plurality of hosts sharing a cluster-wide storage fabric;
a hypervisor running on a host in the cluster;
a virtual disk controller running on the host that virtualizes storage resources of the storage fabric;
a workload recovered by the hypervisor and running on the host; and
a processor configured to:
recover, by the hypervisor, the workload before all workload data is retrieved from an external repository;
attach the external repository to the recovered workload as a virtual disk, wherein the external repository is external to the storage fabric, and wherein the external repository is not virtualized by the virtual disk controller;
receive a request including first I/O traffic according to a first I/O traffic protocol from the recovered workload, the request specifying the virtual disk as a recipient;
translate the request to be compatible with the external repository to include second I/O traffic according to a second I/O traffic protocol; and
forward the translated request to the repository while maintaining availability of the recovered workload.
9. The system of claim 8 , wherein the request includes I/O traffic protocol that is a hyperconverged infrastructure (HCI) native protocol specific to communication between the hypervisor and the virtual disk controller on the host.
10. The system of claim 8 , wherein the translated request includes at least one of: Network File System (NFS), Server Message Block (SMB), or Simple Storage Service (S3).
11. The system of claim 8 , wherein the processor is further configured to identify whether a read request can be serviced locally in a cache associated with the virtual disk controller before adapting and forwarding the read request to the repository.
12. The system of claim 8 , wherein the processor is further configured to:
create a child virtual disk mapped to a parent virtual disk that is backed by the repository; and
absorb write requests in the request locally in the child virtual disk.
13. The system of claim 8 , wherein the processor is further configured to migrate data from the repository to the storage fabric while maintaining the availability of the workload.
14. The system of claim 8 , wherein the virtual disk controller is configured to expose the storage fabric to the workload through a native interface that enables the workload to interact with the virtual disk controller as if it were a direct-attached storage controller.
15. A method comprising:
recovering, by a hypervisor hosted on a host, a workload to run on the host of a cluster comprising a plurality of hosts, the cluster including a virtual disk controller which virtualizes storage resources of the cluster as a storage fabric, wherein the hypervisor recovers the workload before all workload data is retrieved from an external repository;
attaching the external repository to the recovered workload as a virtual disk, wherein the external repository is external to the storage fabric, and wherein the external repository is not virtualized by the virtual disk controller;
receiving a request including first I/O traffic according to a first I/O traffic protocol from the recovered workload, the request specifying the virtual disk as a recipient;
translate the request to be compatible with the external repository to include second I/O traffic according to a second I/O traffic protocol; and
forward the translated request to the repository, while maintaining availability of the recovered workload.
16. The method of claim 15 , wherein the request includes I/O traffic protocol that is a hyperconverged infrastructure (HCI) native protocol specific to communication between the hypervisor and the virtual disk controller on the host, and wherein the translated request includes at least one of: Network File System (NFS), Server Message Block (SMB), or Simple Storage Service (S3).
17. The method of claim 15 , further comprising identifying whether a read request can be serviced locally in a cache associated with the virtual disk controller before adapting and forwarding the read request to the repository.
18. The method of claim 15 , further comprising:
creating a child virtual disk mapped to a parent virtual disk that is backed by the repository; and
absorbing write requests in the request locally in the child virtual disk.
19. The method of claim 15 , further comprising migrating data from the repository to the storage fabric while maintaining the availability of the workload.
20. The method of claim 15 , wherein the virtual disk controller exposes the storage fabric to the workload through a native interface that enables the workload to interact with the virtual disk controller as if it were a direct-attached storage controller.