Abstract: Various embodiments of the present technology generally relate to systems and methods for providing a resource distribution engine. In an example, a method includes identifying, by an instance management service, a request from a cluster orchestrator to acquire computing resources associated with deployment of an application. The method may also include determining, by the instance management service, markets containing reclaimable resources suitable for the computing resources, and performing, by a resource distribution engine of the instance management service, a resource distribution process to determine a resource distribution of the reclaimable resources within the markets. The resource distribution of the reclaimable resources may include a distribution of instance type of the reclaimable resources across the markets. The method may also include securing, by the instance management service, the reclaimable resources identified by the resource distribution as provisioned reclaimable resources.

Abstract: The disclosure describes a node management service that dynamically adjusts node capacity in orchestration platforms. The service leverages an extended resource definition to reflect the increased resource needs during the startup phase of workloads, then reallocates these resources once the workload transitions to steady-state operation. Workloads are provisioned with both a native resource request and an extended resource request to cover initialization spikes. Once initialization completes, the node management service updates the node's metadata to increase available extended resource capacity, thereby freeing up headroom for future deployments.

Abstract: The disclosure describes a node management service that groups pods based on an impact of the available instance pool. The node management service identifies a request group associated with a scale-up request to scale up a cluster of compute nodes to host pods in the request group. The node management service iteratively determines to add pods to the request group until an impact of a next pod on a pool of available nodes exceeds a threshold. The node management service sends a request to a distributor to distribute the pods in the request group to one or more nodes obtained from the pool of available nodes.

Abstract: The disclosure describes a node management service that determines to deploy a primary workload to a new instance in a compute cluster. The node management service projects an allocatable capacity for the new instance based on historical capacity data. The allocatable capacity is the amount of compute resources available for running the primary workload in the new instance after deployment of a supporting workload to the new instance. The node management service associates the primary workload with the new instance upon determining that the projected allocatable capacity is sufficient for running the primary workload.

Abstract: Various embodiments of the present technology generally relate to systems and methods for providing a resource distribution engine. In an example, a method includes identifying, by an instance management service, a request from a cluster orchestrator to acquire computing resources associated with deployment of an application. The method may also include determining, by the instance management service, markets containing reclaimable resources suitable for the computing resources, and performing, by a resource distribution engine of the instance management service, a resource distribution process to determine a resource distribution of the reclaimable resources within the markets. The resource distribution of the reclaimable resources may include a distribution of instance type of the reclaimable resources across the markets. The method may also include securing, by the instance management service, the reclaimable resources identified by the resource distribution as provisioned reclaimable resources.