Microsoft Technology Licensing, LLC

Other

Microsoft Cororation

Microsoft Corporation

Rene Antonio Vega

Eric P Traut

Matthew Douglas Hendel

John Te-Jui Sheu

Galen Clyde Hunt

Robert M Fries

Robert Victor Welland

Bassam Tabbara

Aamer Hydrie

Anders Bertil Vinberg

Geoffrey Hugh Outhred

John M Parchem

Rob M Mensching

Andrew Ernest Nicholas

Eric Joseph Winner

Jeffrey A Woolsey

Bryan M Willman

Forrest Curtis Foltz

Kevin Grealish

Adrian J Oney

Edwin R Lassettre

Landy Wang

Ernest S Cohen

Sharvil A Nanavati

Shuvabrata Ganguly

Mike Neil

Jacob Kappeler Oshins

Arun Upadhyaya Kishan

Thomas Fahrig

Bradley Post

Ellsworth Davis Walker

Yau Ning Chin

Manish Chablani

Eric J Horvitz

Ashvinkumar J Sanghvi

Raymond W McCollum

John Andrew Starks

Vij Rajarajan

Nathan T Lewis

Efstathios Papaefstathiou

David C James

Vitaly Voloshin

Bruce Wayne Copeland

Michael Joseph Healy

John H Wilson

Mazhar Naveed Mohammed

Jonathan C Hardwick

Aaron Sebastian Giles

Rajagopalan Badri Narayanan

Anand Lakshminarayanan

Angel Calvo

Zhengkai Kenneth Pan

Kevin D J Grealish

Andrei Warkentin

Lawrence Ralph Cleeton

David S Bailey

Joy Ganguly

Rich Yampell

Harold L Cochrane

Przemek Pardyak

Model-based virtual system provisioning includes accessing a model of a workload to be installed on a virtual machine of a system as well as a model of the system. A workload refers to some computing that is to be performed, and includes an application to be executed to perform the computing, and optionally includes the operating system on which the application is to be installed. The workload model identifies a source of the application and operating system of the workload, as well as constraints of the workload, such as resources and/or other capabilities that the virtual machine(s) on which the workload is to be installed must have. An installation specification for the application is also generated, the installation specification being derived at least in part from the model of the workload and the model of the virtual system.

Model-based virtual system provisioning

One or more virtual processors can be added or removed from a virtual machine based on CPU pressure measured within the virtual machine. In addition to the foregoing, CPU pressure can also be used to determine whether to remove a virtual processor from a virtual machine, which may cause the computer system to consume less power. In the alternative, virtual processors can be parked and/or unparked in order to reduce the amount of power consumed by the virtual machine. In addition, virtual processors can be forcibly parked during a migration operation.

Virtual processor allocation techniques

Various aspects are disclosed herein for attenuating spin waiting in a virtual machine environment comprising a plurality of virtual machines and virtual processors. Selected virtual processors can be given time slice extensions in order to prevent such virtual processors from becoming de-scheduled (and hence causing other virtual processors to have to spin wait). Selected virtual processors can also be expressly scheduled so that they can be given higher priority to resources, resulting in reduced spin waits for other virtual processors waiting on such selected virtual processors. Finally, various spin wait detection techniques can be incorporated into the time slice extension and express scheduling mechanisms, in order to identify potential and existing spin waiting scenarios.

Efficient detection and response to spin waits in multi-processor virtual machines

Efficient power management of a system with virtual machines is disclosed. In particular, such efficient power management may enable coordination of system-wide power changes with virtual machines. Additionally, such efficient power management may enable coherent power changes in a system with a virtual machine monitor. Furthermore, such efficient power management may enable dynamic control and communication of power state changes.

Efficient power management of a system with virtual machines

A catch-up mode that runs a virtual programmable interrupt timer faster than a nominal rate to prevent time loss in a virtual machine can be implemented. If time loss is determined, a catch-up mode can be initiated to cause increased firings, beyond a nominal rate, of the programmable interrupt timer to adjust the clock of the virtual machine to the clock of the host system. The virtual programmable interrupt timer can also be readjusted to a predetermined nominal rate when the time loss in the guest operating system is determined approximately within a predetermined tolerance range. The catch-up mode can be monitored to avoid 'interrupt storms' on the virtual machine. The virtual programmable interrupt timer can be altered by the guest operating system to accommodate different operating systems.

Changing frequency of a virtual programmable interrupt timer in virtual machines to control virtual time

Various mechanisms are disclosed for improving the operational efficiency of a virtual translation look-aside buffer (TLB) in a virtual machine environment. For example, one mechanism fills in entries in a shadow page table (SPT) and additionally, speculatively fills in other entries in the SPT based on various heuristics. Another mechanism allows virtual TLBs (translation look-aside buffers) to cache partial walks in a guest page table tree. Still another mechanism allows for dynamic resizing of the virtual TLB to optimize for run-time characteristics of active workloads. Still another mechanism allows virtual machine monitors (VMMs) to support legacy and enlightened modes of virtual TLB operation. Finally, another mechanism allows the VMM to remove only the stale entries in SPTs when linking or switching address spaces. All these mechanisms, together or in part, increase the operational efficiency of the virtual TLB.

Operational efficiency of virtual TLBs

The present invention is directed to making a guest operating system aware of the topology of the subset of host resources currently assigned to it. At virtual machine boot time a Static Resource Affinity Table (SRAT) will be used by the virtualizer to group guest physical memory and guest virtual processors into virtual nodes. Thereafter, in one embodiment, the host physical memory behind a virtual node can be changed by the virtualizer as necessary, and the virtualizer will provide physical processors appropriate for the virtual processors in that node.

Systems and methods for exposing processor topology for virtual machines

Various operations are disclosed for improving the operational efficiency of a virtual translation look-aside buffer (TLB) in a virtual machine environment. For example, operations are disclosed that allow for determination of whether present entries in shadow page tables (SPTs) are stale by comparing shadowed guest page table (GPT) entries against snapshots taken when the entries were cached. Other operations are disclosed that allow a virtual machine monitor (VMM) to access shadow page table trees (SPTTs) by walking trees in software or in hardware. Still other operations are disclosed allowing the VMM to use a hash table to relate GVA ranges to SPTs that map them, thus significantly reducing the cost of having to walk each SPTT in order to invalidate desired GVA(s). And, finally, operations are disclosed allowing the VMM to determine global GVA ranges by checking a bitmap, when invalidating global GVAs.

Reduction of operational costs of virtual TLBs

Growing community of inventors

Kirkland, WA, United States of America

Rene Antonio Vega