Abstract: At a first compute instance run on a virtualization host, a local instance scaling manager is launched. The scaling manager determines, based on metrics collected at the host, that a triggering condition for redistributing one or more types of resources of the first compute instance has been met. The scaling manager causes virtualization management components to allocate a subset of the first compute instance's resources to a second compute instance at the host.

Abstract: At a first compute instance run on a virtualization host, a local instance scaling manager is launched. The scaling manager determines, based on metrics collected at the host, that a triggering condition for redistributing one or more types of resources of the first compute instance has been met. The scaling manager causes virtualization management components to allocate a subset of the first compute instance's resources to a second compute instance at the host.

Abstract: At a first compute instance run on a virtualization host, a local instance scaling manager is launched. The scaling manager determines, based on metrics collected at the host, that a triggering condition for redistributing one or more types of resources of the first compute instance has been met. The scaling manager causes virtualization management components to allocate a subset of the first compute instance's resources to a second compute instance at the host.

Abstract: At a virtualization host which includes an instance partitioning controller, a set of resources is allocated to a compute instance by a virtualization manager. The first compute instance does not include another virtualization manager. In response to a communication from the controller, the virtualization manager allocates a subset of the resources to a child compute instance launched at the virtualization host. An application is executed within the child compute instance.

Abstract: At a first compute instance run on a virtualization host, a local instance scaling manager is launched. The scaling manager determines, based on metrics collected at the host, that a triggering condition for redistributing one or more types of resources of the first compute instance has been met. The scaling manager causes virtualization management components to allocate a subset of the first compute instance's resources to a second compute instance at the host.

Abstract: At a virtualization host which includes an instance partitioning controller, a set of resources is allocated to a compute instance by a virtualization manager. The first compute instance does not include another virtualization manager. In response to a communication from the controller, the virtualization manager allocates a subset of the resources to a child compute instance launched at the virtualization host. An application is executed within the child compute instance.

Abstract: Methods and apparatus for virtual machine (VM) load monitoring in provider network environments. A VM load monitor system may be used to offload the processing of VM load data from the execution environment of a VM host device. A VM load monitor may be implemented as a dedicated programmable hardware device on or attached to a host device that is external to the execution environment of the host device, thus freeing host device resources (e.g., processors, memory, etc.) for use by the VMs executing on the host device. The VM load monitor may make VM management decisions for the host device (e.g. launch VM decisions, migrate VM decisions, etc.) based on analysis of resource load data (e.g. network, memory, and/or processor load data) collected from the VMs (or groups of VMs) executing on the host device.