International Business Machines Corporation

Ben-Ami Yassour

Shmuel Ben-Yehuda

Orit Luba Wasserman

Abel Alkon Gordon

Shmuel Ben Yehuda

Gregory Brian Pruett

Theodore Brian Vojnovich

Andrew Boyce McNeill, Jr

Gregory William Dake

Anthony Nicholas Liguori

Ofer Biran

Srirama Mandyam Krishnakumar

Eric Richard Kern

Leah Shalev

Michael Edward Factor

Richard Edwin Harper

Zorik Machulsky

Scott Neil Dunham

Joseph Edward Bolan

Kalman Zvi Meth

Martin Tross

Yariv Aridor

Nadav Yosef Har'el

Avishay Traeger

Eran Borovik

Kenneth Bruce MacKenzie

Martin J Tross

Orit (Luba) Wasserman

Bruce Kenneth Mackenzie

Systems and methods for optimizing operation of a physical device in a virtualized computing environment are provided. The method comprises monitoring instructions issued by an application running on a virtual machine's (VM) operating system, wherein the VM is hosted by a hypervisor providing access to a physical device connected to a virtualized computing environment; wherein a device driver supported by the operating system issues one or more instructions to an emulated device supported by the hypervisor to control the physical device according to the issued instructions, wherein the emulated device's registers are implemented in memory of the hypervisor and the instructions issued by the device driver are stored in said registers, wherein the hypervisor handles the instructions, in response to learning that the instructions are stored in said registers.

Virtual device emulation via hypervisor shared memory

A method of address translation in a computing system providing direct memory access (DMA) by way of one or more remote memory management units (MMUs) is provided. The method comprises intercepting a request for a first DMA operation forwarded by a first device to a second device; and translating a guest address included in the request to a first address according to a mapping referencing a memory frame in a memory of the second device. A local MMU increments a first reference count indicating number of active DMA operations directed to the memory frame and a second reference count indicating number of remote MMUs that have mapped the memory frame.

Direct memory access in a computing environment

A para-virtualization method is provided. The method comprises implementing a virtual machine (VM) for guest software running on first host software. In response to a privileged instruction, the guest software causes a first VM exit. If the first host software is not running directly on hardware, the privileged instruction is managed without causing a second VM exit. Otherwise, the privileged instruction is managed normally.

Para-virtualization in a nested virtualization environment using reduced number of nested VM exits

A method of handling an event occurring in a nested virtualization computing environment is provided, wherein N hypervisors are executed nestedly, with a first hypervisor running at level zero (L0) directly over a host machine, and other hypervisors nestedly running at levels L1 to Ln, respectively. The method comprises trapping an event generated by software running at level Ln; determining a hypervisor x at level Lx designated for handling the trapped event; and wherein the hypervisor x emulates features needed for performing the trapped event for the software running at the level Ln.

Multilevel support in a nested virtualization environment

A computer implemented method for handling events in a multi-core processing environment is provided. The method comprises handling an event by a second application running on a second core, in response to determining that the event is initiated by a first application running on a first core; and running a third application on the first core, while the first application is waiting for the event to be handled by the second application.

Efficient multi-core processing of events

In accordance with one embodiment, a method of nesting a second virtual machine (VM) on a first VM running on a physical machine is provided. The method comprises receiving a first instruction from the physical machine, wherein the first instruction originates from the first VM, wherein a first control structure is associated with the first VM, and wherein a second control structure is associated with the second VM; creating a secondary control structure based on the second control structure associated with the second VM; providing the first instruction and the secondary control structure to the physical machine, wherein the physical machine executes the first instruction according to information included in the secondary control structure; and updating the secondary control structure to correspond to current state or execution environment of the physical machine.

Multiple layers of virtualization in a computing system

Methods, apparatus, and products for managing virtual addresses of blade servers in a data center are disclosed that include storing by a blade server management module ('BSMM'), in non-volatile memory of a blade server, a parameter block, the parameter block including one or more virtual addresses for communications adapters of the blade server and one or more action identifiers, each action identifier representing a type of address modification; detecting, by a basic input-output system ('BIOS') module of the blade server upon powering on the blade server, the parameter block; and modifying, by the BIOS module of the blade server in dependence upon the one or more action identifiers of the parameter block, an address of at least one communications adapter of the blade server.

Managing virtual addresses of blade servers in a data center

A method for managing memory in a nested virtualization environment is provided. The method comprises implementing a first virtual machine (VM) for a first software such that a first guest memory is allocated to the first software; maintaining a first data structure to translate one or more memory addresses in the first guest memory to corresponding memory addresses in a physical memory; maintaining a second data structure to translate one or more memory addresses in the second guest memory to corresponding memory addresses in the physical memory. The first software implements a second VM for a second software such that a second guest memory is allocated to the second software and maintains a third data structure to translate one or more memory addresses in the second guest memory to corresponding memory addresses in the first guest memory.

Memory management in a nested virtualization environment

Failover of blade servers in a data center including powering off a failing blade server by a system management server through a blade server management module ('BSMM') managing the failing blade server, the failing blade server characterized by a machine type, one or more network addresses, and one or more storage addresses, the addresses being virtual addresses; identifying, by the system management server from a pool of standby blade servers, a replacement blade server, the replacement blade server managed by a BSMM; assigning, by the system management server through the BSMM managing the replacement blade server, the one or more network addresses and the one or more storage addresses of the failing blade server to the replacement blade server, including enabling in the replacement blade server the assigned addresses; and powering on the replacement blade server by the system management server through the BSMM managing the replacement blade server.

Failover of blade servers in a data center

Power and redundancy management policies are applied individually to the tiers of redundant servers of an application service such that power is reduced while maintaining a high level of system availability. Servers which are determined to be relatively inactive are moved to a free pool. Certain servers of the free pool are maintained in a hot standby state, while others are powered-off or set to operate in a low power mode. During times of high load, the servers in the hot standby state can be provisioned quickly into the application service.

Automated power control policies based on application-specific redundancy characteristics

A computer-implemented framework and method for managing application complexes comprising multiple tiers of servers, where servers in a common tier run an identical application and servers in different tiers run different applications, and all the servers work together to provide a specific service, the application complex being definable via an application complex type. The framework has a plugin interface adapted for connection to the framework of a plugin in respect of each application complex type, the plugin encapsulating a relationship between disparate resources composing the respective application complex type and respective characteristics of said resources. A user interface in the framework provides general tasks that are independent of operational semantics of the application complex and is responsive to user operations for interfacing with the framework for defining an instance of the application complex and allowing the user to populate the application complex with servers.

Growing community of inventors

Haifa, Israel

Ben-Ami Yassour