Abstract: A system and method for dynamically adjusting the amount of memory allocated to a virtual machine includes generating, by a memory resizing system, a current memory usage profile for the virtual machine. The memory resizing system and the virtual machine are part of a virtual computing system and the current memory usage profile is generated by mapping, as a function of time, memory usage information from the virtual machine. The system and method also include computing an upper baseline based upon a peak memory usage in the current memory profile, updating an initial memory allocation of the virtual machine based upon the upper baseline and a predetermined threshold for obtaining an initial revised memory allocation, determining a moving average of memory usage from a historical memory usage profile, and updating the initial revised memory allocation based upon the moving average of memory usage for obtaining a final revised memory allocation.

Abstract: A method of determining an optimal host machine to place a virtual machine in a virtualization environment is described. The virtualization environment includes a first rack of host machines and a second rack of host machines, where a first host machine of the first rack of host machines is designated as a leader node. The method includes receiving a request to launch a second virtual machine configured to communicate with a first virtual machine. The method includes identifying, from the first rack of host machines and the second rack of host machines, a cluster of host machines. The method includes computing, for each host machine of the cluster, an aggregate network bandwidth consumed by the host machine. The method includes selecting a host machine from the cluster based on the aggregate network bandwidth computed for the selected host machine. The method includes launching the second virtual machine on the selected host machine.

Abstract: The disclosure relates to a method of switching data sources during a rolling upgrade of a leader-based distributed service. In at least one implementation, the method includes establishing, at a computing device in a cluster of devices in a network, a watch for notification of completion of a rolling upgrade on all devices in the cluster; restarting the computing device on completion of the rolling upgrade; switching, at the computing device, from a first data source to a second data source once the rolling upgrade is complete on all devices in the cluster; if the computing device is a leader device in the cluster, migrating tasks from the first data source to the second data source after completion of the rolling upgrade; and if the computing device is a non-leader device in the cluster, determining if task migration to the second data source is done and, when done, sending a store object to the second data source.

Abstract: A system and method for dynamically adjusting the amount of memory allocated to a virtual machine includes generating, by a memory resizing system, a current memory usage profile for the virtual machine. The memory resizing system and the virtual machine are part of a virtual computing system and the current memory usage profile is generated by mapping, as a function of time, memory usage information from the virtual machine. The system and method also include computing an upper baseline based upon a peak memory usage in the current memory profile, updating an initial memory allocation of the virtual machine based upon the upper baseline and a predetermined threshold for obtaining an initial revised memory allocation, determining a moving average of memory usage from a historical memory usage profile, and updating the initial revised memory allocation based upon the moving average of memory usage for obtaining a final revised memory allocation.

Abstract: A method of determining an optimal host machine to place a virtual machine in a virtualization environment is described. The virtualization environment includes a first rack of host machines and a second rack of host machines, where a first host machine of the first rack of host machines is designated as a leader node. The method includes receiving a request to launch a second virtual machine configured to communicate with a first virtual machine. The method includes identifying, from the first rack of host machines and the second rack of host machines, a cluster of host machines. The method includes computing, for each host machine of the cluster, an aggregate network bandwidth consumed by the host machine. The method includes selecting a host machine from the cluster based on the aggregate network bandwidth computed for the selected host machine. The method includes launching the second virtual machine on the selected host machine.

Abstract: The disclosure relates to a method of switching data sources during a rolling upgrade of a leader-based distributed service. In at least one implementation, the method includes establishing, at a computing device in a cluster of devices in a network, a watch for notification of completion of a rolling upgrade on all devices in the cluster; restarting the computing device on completion of the rolling upgrade; switching, at the computing device, from a first data source to a second data source once the rolling upgrade is complete on all devices in the cluster; if the computing device is a leader device in the cluster, migrating tasks from the first data source to the second data source after completion of the rolling upgrade; and if the computing device is a non-leader device in the cluster, determining if task migration to the second data source is done and, when done, sending a store object to the second data source.