International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

Michael R Hines

Bulent Abali

John Alan Bivens

Gokul Bhargava Kandiraju

Mohammad Banikazemi

Jack Lawrence Kouloheris

Kyung D Ryu

Marcio Augusto Silva

James A O'Connor

Lee Nee Helgeson

Dan Edward Poff

Dilma Menezes Da Silva

Bradley W Bishop

Dilma M Da Silva

Hubertus Franke

Makoto Ono

Shmuel Ben-Yehuda

Abel Alkon Gordon

David Breitgand

Amir Epstein

Alexander Glikson

A method, computer program product, and computer system to maintain high availability of a service processor. An embodiment provides program code with a location of a second service processor (the second service processor is communicatively coupled to the first service processor). The program code stops a virtual machine during runtime, including instruction execution and IO operations, where during runtime, the virtual machine executes one or more processes to service and manage computing resources in the distributed computing environment. The program code generates a micro-checkpoint of the virtual machine. The program code resumes the instruction execution of the virtual machine and transmits the micro-checkpoint to a second service processor based on the location and then resumes IO operations. The second service processor utilizes the micro-checkpoint to enable a hypervisor on the second service processor to start a virtual machine on the second service processor.

Microcheckpointing with service processor

Methods and systems for agile load balancing include detecting an increased load for a first primary virtual machine (VM) on a first node that has a plurality of additional primary VMs running on a processor; deactivating one or more of the additional primary VMs, reducing said one or more deactivated VMs to a secondary state, to free resources at the first node for the first primary VM; and activating secondary VMs, located at one or more additional nodes, that correspond to the one or more deactivated VMs, raising said secondary VMs to a primary state. Activation and deactivation through micro-checkpointing may involve nodes of different CPU architectures during transient periods of peak load.

Agile VM load balancing through micro-checkpointing and multi-architecture emulation

A method, system and computer program product are disclosed for recovery in a virtualized environment using remote direct memory access (RDMA). In one embodiment, the method comprises operating a virtual computer system on a physical computer system, and the virtual system maintains in a memory area a record of a state of the virtual system. In this method, when defined error conditions occur on the virtual system, RDMA is used to pull the record of the state of the virtual system from that memory area onto a standby computer. This record on the standby computer is used to re-initialize the virtual computer. Embodiments of the invention provide methods that provide a very fast recovery from a virtual machine fault or error, while requiring much fewer resources than standard approaches. In embodiments of the invention, one spare real computer system can be used for backing up several virtual systems.

Using RDMA for fast system recovery in virtualized environments

A method for providing dynamic resizing of at least one virtual machine in a cloud infrastructure includes steps of: obtaining a measure of resource usage for the virtual machine and/or application performance of an application running on the virtual machine; determining, as a function of prescribed rules relating to resource usage and the measure of resource usage and/or application performance, whether the virtual machine requires resizing; and resizing the virtual machine to dynamically change resource availability for the virtual machine so as to maintain resource usage and/or application performance within prescribed limits defined by the prescribed rules.

Dynamic virtual machine resizing in a cloud computing infrastructure

A method, system and computer program product for checkpointing virtual machines (VMs). The system includes a primary computer hosting a hypervisor and a primary VM. The hypervisor is configured instantiate the primary VM, divide the state of the primary VM into a plurality of memory blocks, and generate an error correction block based on the plurality of memory blocks. The system further includes a plurality of secondary computers. Each of the secondary computers stores a secondary VM and one of either the memory blocks or the error correction block.

Virtual machine distributed checkpointing

A computer implemented method creates a snapshot of a logical volume of a computer. The computer stores a system state of the computer in persistent memory. The computer flushes a cache of the computer. The computer identifies a preceding snapshot. In response to identifying the preceding snapshot, the computer hardens changes occurring after the preceding snapshot. The computer then switches from a first indirection table to a second indirection table.

Instantaneous save/restore of virtual machines with persistent memory

System and method and computer program product implemented for a cloud computing infrastructure that allows a hypervisor to optimize resource allocation in a cloud computing environment by exploiting the application-level performance, O/S system performance, and hypervisor performance information through a reliable and efficient channel.

Resource management using reliable and efficient delivery of application performance information in a cloud computing system

A memory management method in a virtualized computing environment is provided, in which a hypervisor implements at least a virtual machine (VM) over a host machine, wherein a guest operating system (OS) is executed over the VM and an application supporting memory management capabilities is executed over the guest OS. The method comprises invoking a first memory manager (java balloon) implemented by the application to deallocate memory allocated to the application for use by the hypervisor, in response to a request submitted by the hypervisor; and invoking a second memory manager (guest balloon) implemented over the guest operating system to deallocate memory allocated to the guest OS, in response to a request submitted by the hypervisor.

Growing community of inventors

White Plains, NY, United States of America

Michael R Hines