Abstract: In a virtualized computer system in which a guest operating system runs on a virtual machine of a virtualized computer system, a computer-implemented method of providing the guest operating system with direct access to a hardware device coupled to the virtualized computer system via a communication interface, the method including: (a) obtaining first configuration register information corresponding to the hardware device, the hardware device connected to the virtualized computer system via the communication interface; (b) creating a passthrough device by copying at least part of the first configuration register information to generate second configuration register information corresponding to the passthrough device; and (c) enabling the guest operating system to directly access the hardware device corresponding to the passthrough device by providing access to the second configuration register information of the passthrough device.

Abstract: A source virtual machine (VM) hosted on a source server is migrated to a destination VM on a destination server without first powering down the source VM. After optional pre-copying of the source VM's memory to the destination VM, the source VM is suspended and its non-memory state is transferred to the destination VM; the destination VM is then resumed from the transferred state. In one embodiment, the source VM memory is either paged into the destination VM on demand, or is transferred asynchronously by pre-copying and write-protecting the source VM memory, and then later transferring only the modified pages after the destination VM is resumed. In one embodiment, the source and destination servers share common storage, in which the source VM's virtual disk is stored; this avoids the need to transfer the virtual disk contents.

Abstract: An elastic filesystem for temporary data provides storage space for virtual machines (VMs) in a distributed computing system. The filesystem redirects accesses to virtual disks in VMs to a common pool file. The system provides performance and storage efficiency at least on par with local, direct attached virtual disks, while providing a single pool of shared storage that is provisioned and managed independently of the VMs. The system provides storage isolation between VMs storing temporary data in that shared pool. Also, storage space for temporary data may be allocated on demand and reclaimed when no longer needed, thereby supporting a wide variety of temporary space requirements for different Hadoop jobs.

Abstract: A virtualization platform provides fault tolerance for a primary virtual machine by continuously transmitting checkpoint information of the primary virtual machine to a collector process, such as a backup virtual machine. The virtualization platform includes virtual devices configured to keep track of state changes, for example, by using state flags or saving copies of prior state data. The virtualization platform generates incremental checkpoints by querying the virtual devices, which return state data based on whether the virtual devices have changed state since a prior checkpoint operation.

Abstract: A virtual machine (VM) runs on system hardware, which includes a physical network interface device that enables transfer of packets between the VM and a destination over a network. A virtual machine monitor (VMM) exports a hardware interface to the VM and runs on a kernel, which forms a system software layer between the VMM and the system hardware. Pending packets (both transmit and receive) issued by the VM are stored in a memory region that is shared by, that is, addressable by, the VM, the VMM, and the kernel. Rather than always transferring each packet as it is issued, packets are clustered in the shared memory region until a trigger event occurs, whereupon the cluster of packets is passed as a group to the physical network interface device. Optional mechanisms are included to prevent packets from waiting too long in the shared memory space before being transferred to the network.

Abstract: A distributed computing application is described that provides a highly elastic and multi-tenant platform for Hadoop applications and other workloads running in a virtualized environment. Data and compute nodes are separated into different virtual machines (VM). Compute VMs are used to launch containers from different tenants. Compute VMs are organized in pools of hot spare VMs that are immediately available for launching a container and executing a task, and pools of cold spare VMs. Each compute VM may include a mounted network filesystem provided by a node manager to share intermediate outputs across VMs executing on the same host.

Abstract: A pumping system frame assembly for use in supporting a horizontal pumping system on a platform includes a central body assembly, a motor plate connected to the central body assembly and a plurality of platform support assemblies connected to the central support member. The central body assembly includes a central support member that has an upper face and a pair of side rails connected to the upper face. In particularly preferred embodiments, each of the pair of side rails extends downward from the upper face at approximately a 45 degree angle.

Abstract: Embodiments maintain high availability of software application instances in a fault domain. Subordinate hosts are monitored by a master host. The subordinate hosts publish heartbeats via a network and datastores. Based at least in part on the published heartbeats, the master host determines the status of each subordinate host, distinguishing between subordinate hosts that are entirely inoperative and subordinate hosts that are operative but partitioned (e.g., unreachable via the network). The master host may restart software application instances, such as virtual machines, that are executed by inoperative subordinate hosts or that cease executing on partitioned subordinate hosts.

Abstract: A method for restarting a virtual machine in a virtual computing system having a plurality of hosts and a resource scheduler for the plurality of hosts includes writing a placement request for the virtual machine to a shared channel that is accessible by the resource scheduler. The method further includes reading a placement result from the shared channel, wherein the placement result is generated by the resource scheduler responsive to the placement request; and restarting the virtual machine in accordance with the placement result.

Abstract: Selecting a master node in a group of computing nodes. Computing nodes exchange suitability messages, candidate messages, and master messages to indicate the state of each node. A deterministic algorithm based on scores and timings is executed by each computing node to encourage each node to select the same master node.

Abstract: A source virtual machine (VM) hosted on a source server is migrated to a destination VM on a destination server without first powering down the source VM. After optional pre-copying of the source VM's memory to the destination VM, the source VM is suspended and its non-memory state is transferred to the destination VM; the destination VM is then resumed from the transferred state. The source VM memory is either paged into the destination VM on demand, or is transferred asynchronously by pre-copying and write-protecting the source VM memory, and then later transferring only the modified pages after the destination VM is resumed. The source and destination servers preferably share common storage, in which the source VM's virtual disk is stored; this avoids the need to transfer the virtual disk contents.

Abstract: A method for conveying a data packet received from a network to a virtual machine instantiated on a computer system coupled to the network, and a medium and system for carrying out the method, is described. In the method, a guest receive pointer queue of a component executing in the virtual machine is inspected in order to identify a location in a guest receive packet data buffer that is available to receive packet data. Data from the data packet received from the network is copied into the guest receive packet data buffer at the identified location. A standard receive interrupt is raised in the virtual machine. Thus, the kernel places the data packet received from the network into a memory space accessible to the virtual machine without any intervention by a virtual machine monitor component of the virtualization software.

Abstract: A suction chamber for use in a horizontal fluid pumping system is supported by a fixed vertical bracket, which is attached to a platform. The suction chamber is positioned between a motor and a pump in the horizontal pumping system. The pumping system may also include a thrust bearing chamber positioned between the motor and the suction chamber. The pumping system may also include a bearing chamber adapter positioned between the thrust bearing chamber and the suction chamber. The suction chamber has a suction chamber pump end and a suction chamber motor end. The suction chamber enables both motor-end seal removal and pump-end seal removal. In both motor end seal removal and pump end seal removal, the suction chamber of the invention remains connected to the vertical bracket. The pumping system may also include an integrated lifting device connected to the vertical bracket to lift the thrust bearing assembly.

Abstract: To generate a checkpoint for a virtual machine (VM), first, while the VM is still running, a copy-on-write (COW) disk file is created pointing to a parent disk file that the VM is using. Next, the VM is stopped, the VM's memory is marked COW, the device state of the VM is saved to memory, the VM is switched to use the COW disk file, and the VM begins running again for substantially the remainder of the checkpoint generation. Next, the device state that was stored in memory and the unmodified VM memory pages are saved to a checkpoint file. Also, a copy may be made of the parent disk file for retention as part of the checkpoint, or the original parent disk file may be retained as part of the checkpoint. If a copy of the parent disk file was made, then the COW disk file may be committed to the original parent disk file.