Node recovery solution for composable and disaggregated environment
In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a pod manager. The pod manager receives receive a request for composing a target composed-node. The pod manager employs a first set of pooled hardware resources of the computing pod to build the target composed-node. The pod manager determines to reserve a second set of pooled hardware resources of the computing pod for a backup node of the target composed-node. The pod manager determines that the target composed-node has failed. The pod manager employs the second set of pooled hardware resources to build the backup node.
1. A method of managing composed-nodes of a computing pod, comprising:
receiving a request for composing a target composed-node running one or more virtual machines (VMs);
employing a first set of pooled hardware resources of the computing pod to build the target composed-node running the one or more VMs;
determining whether the target composed-node is a critical node;
when the target composed-node is a critical node, reserving a second set of pooled hardware resources of the computing pod for building a backup node, of the target composed-node, that runs the one or more VMs, wherein the first set and second set of pooled hardware resources each are physical hardware components, wherein the first set of pooled hardware resources and the second set of pooled hardware resources are on same computing racks of the computing pod;
determining that the target composed-node has failed;
determining software components of the target composed-node; and
connecting the second set of pooled hardware resources through communication links, including bus links, to build the backup node running the one or more VMs, including installing the software components on the second set of pooled hardware resources.
2. The method of claim 1 , wherein the second set of pooled hardware resources contains less hardware resources than the first set of pooled hardware resources.
3. The method of claim 1 , wherein the target composed-node and the backup node have a same software configuration to provide a same service.
4. The method of claim 1 , wherein the first set of pooled hardware resources and the second set of pooled hardware resources each include: respective pooled compute resources, respective pooled network resources, and respective pooled storage resources.
5. The method of claim 1 , wherein the first set of pooled hardware resources includes first pooled compute resources, first pooled network resources, and first pooled storage resources; wherein the first set of pooled hardware resources includes second pooled compute resources, and second pooled network resources;
wherein the backup node is built by further employing the first pooled storage resources.
6. An apparatus for managing composed-nodes of a computing pod, comprising: a memory; and
at least one processor coupled to the memory and configured to:
receive a request for composing a target composed-node running one or more virtual machines (VMs);
employ a first set of pooled hardware resources of the computing pod to build the target composed-node running the one or more VMs;
determine whether the target composed-node is a critical node;
when the target composed-node is a critical node, reserve a second set of pooled hardware resources of the computing pod for building a backup node, of the target composed-node, that runs the one or more VMs, wherein the first set and second set of pooled hardware resources each are physical hardware components, wherein the first set of pooled hardware resources and the second set of pooled hardware resources are on same computing racks of the computing pod;
determine that the target composed-node has failed;
determine software components of the target composed-node; and
connect the second set of pooled hardware resources through communication links, including bus links, to build the backup node running the one or more VMs and install the software components on the second set of pooled hardware resources.
7. The apparatus of claim 6 , wherein the second set of pooled hardware resources contains less hardware resources than the first set of pooled hardware resources.
8. The apparatus of claim 6 , wherein the target composed-node and the backup node have a same software configuration to provide a same service.
9. The apparatus of claim 6 , wherein the first set of pooled hardware resources and the second set of pooled hardware resources each include: respective pooled compute resources, respective pooled network resources, and respective pooled storage resources.
10. The apparatus of claim 6 , wherein the first set of pooled hardware resources includes first pooled compute resources, first pooled network resources, and first pooled storage resources;
wherein the first set of pooled hardware resources includes second pooled compute resources, and second pooled network resources;
wherein the backup node is built by further employing the first pooled storage resources.
11. A non-transitory computer-readable medium storing computer executable code for managing composed-nodes of a computing pod, comprising code to:
receive a request for composing a target composed-node running one or more virtual machines (VMs);
employ a first set of pooled hardware resources of the computing pod to build the target composed-node running the one or more VMs;
determine whether the target composed-node is a critical node;
when the target composed-node is a critical node, reserve a second set of pooled hardware resources of the computing pod for building a backup node, of the target composed-node, that runs the one or more VMs, wherein the first set and second set of pooled hardware resources each are physical hardware components, wherein the first set of pooled hardware resources and the second set of pooled hardware resources are on same computing racks of the computing pod;
determine that the target composed-node has failed;
determine software components of the target composed-node; and
connect the second set of pooled hardware resources through communication links, including bus links, to build the backup node running the one or more VMs and install the software components on the second set of pooled hardware resources.
12. The non-transitory computer-readable medium of claim 11 , wherein the second set of pooled hardware resources contains less hardware resources than the first set of pooled hardware resources.
13. The non-transitory computer-readable medium of claim 11 , wherein the target composed-node and the backup node have a same software configuration to provide a same service.
14. The non-transitory computer-readable medium of claim 11 , wherein the first set of pooled hardware resources and the second set of pooled hardware resources each include: respective pooled compute resources, respective pooled network resources, and respective pooled storage resources.