Vmware, Inc.

Timothy P Mann

Rajesh Venkatasubramanian

Andrei Warkentin

Arunachalam Ramanathan

Venkata Subhash Reddy Peddamallu

Frederick Joseph Jacobs

Sowgandh Sunil Gadi

Ganesha Shanmuganathan

Mukund Gunti

Anne Holler

Minwen Ji

Umit Rencuzogullari

Alok Kumar Gupta

Limin Wang

Tahir Mobashir

Carl Alan Waldspurger

David A Dunn

Cyprien Laplace

Alexander Fainkichen

Boris Weissman

Haoqiang Zheng

John R Zedlewski

Qasim Ali

Sunil Kumar Kotian

Ramesh Dharan

Doug Covelli

Rajit S Kambo

Jared McNeill

Stephen Muckle

Karthik Ramachandra

Michael Craig

Disclosed are various examples of provisioning a data processing unit (DPU) management operating system using a capsule. A management hypervisor installer executed on a host device receives a listing DPU device from a baseboard management controller (BMC). A preinstalled DPU management operating system image is identified for a DPU device from the listing, and is wrapped with a capsule that specifies the capsule as a DPU management operating system image capsule. A server component provides the DPU management operating system image capsule at a particular URI, and the URI is transmitted to the BMC.

Provisioning DPU management operating systems using firmware capsules

Techniques for migrating virtual machines (VMs) in the presence of uncorrectable memory errors are provided. According to one set of embodiments, a source host hypervisor of a source host system can determine, for each guest memory page of a VM to be migrated from the source host system to a destination host system, whether the guest memory page is impacted by an uncorrectable memory error in a byte-addressable memory of the source host system. If the source host hypervisor determines that the guest memory page is impacted, the source host hypervisor can transmit a data packet to a destination host hypervisor of the destination host system that includes error metadata identifying the guest memory page as being corrupted. Alternatively, if the source host hypervisor determines that the guest memory page is not impacted, the source host hypervisor can attempt to read the guest memory page from the byte-addressable memory in a memory exception-safe manner.

Managing the migration of virtual machines in the presence of uncorrectable memory errors

A method of creating a new page table structure after first stage boot operations has completed but before handoff to a hypervisor occurs. Firmware page tables are reused and copied to a region of memory by a first-stage bootloader while the firmware is running, processed to have an expected multi-stage page table structure and desired access rights, and copied again to another region of memory by the first-stage bootloader after the first-stage bootloader has completed its booting operations and after the firmware has been quiesced.

Constructing a UEFI bootloader handoff address space for a physical machine hosting virtual machines

A computer system is securely booted by executing a boot firmware to locate a boot loader and verify the boot loader using a first key that is associated with the boot firmware. Upon verifying the boot loader, computer system executes the boot loader to verify a system software kernel and a secure boot verifier using a second key that is associated with the boot loader. The secure boot verifier is then executed to verify the remaining executable software modules to be loaded during boot using a third key that is associated with the secure boot verifier. During boot, state data files of the computer system are mounted in a namespace that is isolated from the namespaces in which the executable software modules are mounted.

Secure booting of computer system

A computer system is securely booted by executing a boot firmware to locate a boot loader and verify the boot loader using a first key that is associated with the boot firmware. Upon verifying the boot loader, computer system executes the boot loader to verify a system software kernel and a secure boot verifier using a second key that is associated with the boot loader. The secure boot verifier is then executed to verify the remaining executable software modules to be loaded during boot using a third key that is associated with the secure boot verifier and a fourth key that is associated with a user of the computer system.

A method of re-mapping memory regions for firmware run-time services to a virtual address space of a kernel executed on a processor, includes the steps of selecting a re-mapping policy for re-mapping the memory regions for the firmware run-time services, creating a new mapping according to the selected re-mapping policy, and making a call to an application programming interface exposed by the firmware to apply the new map and re-map the memory regions for the firmware to the virtual address space of the kernel.

Intelligent UEFI run-time services address space management

A method of reducing power consumption of a server cluster of host systems with virtual machines executing on the host systems is provided. The method includes recommending host system power-on when there is a host system whose utilization is above a target utilization, and recommending host system power-off when there is a host system whose utilization is below the target utilization. Recommending host system power-on includes calculating impact of powering on a standby host system with respect to reducing the number of highly-utilized host systems in the server cluster. Recommending host system power-off includes calculating impact of powering off a host system with respect to decreasing the number of less-utilized host systems in the server cluster.

Reducing power consumption in a server cluster

Systems and techniques are described for power-aware scheduling. One of the techniques includes monitoring execution of a plurality of groups of software threads executing on a physical machine, wherein the physical machine comprises a physical hardware platform that includes a plurality of processor packages having a plurality of package power states, wherein the plurality of package power states includes an independent package power state; obtaining a respective independent power state measure for each of the processor packages, wherein the independent power state measure provides a measure of a percentage of time the processor package spends in the independent package power state; and adjusting an allocation of the plurality of groups of software threads across the plurality of processor packages based in part on the independent power state measures for the packages.

Power-aware scheduling

A method of reducing power consumption of a server cluster of host systems with virtual machines executing on the host systems is disclosed. The method includes recommending host system power-on when there is a host system whose utilization is above a target utilization, and recommending host system power-off when there is a host system whose utilization is below the target utilization. Recommending host system power-on includes calculating impact of powering on a standby host system with respect to reducing the number of highly-utilized host systems in the server cluster. The impact of powering on is calculated by simulating moving some virtual machines from highly utilized host systems to the standby host system being recommended to be powered on. Recommending host system power-off includes calculating impact of powering off a host system with respect to decreasing the number of less-utilized host systems in the server cluster. The impact of powering off is calculated by simulating moving all virtual machines from the host system, which is being recommended to be powered-off, to less -utilized host systems.

A sponge process, for example within a driver in a guest operating system, is associated in a virtual computer system with each virtual processor in one or more virtual machines. When timer interrupts become backlogged, for example because a virtual machine is temporarily descheduled to allow other virtual machines to run, and upon occurrence of a trigger event, a conventional interrupt is disengaged and catch-up interrupts are instead directed into an appropriate one of the sponge processes. The backlogged timer interrupts are thus delivered without unfairly attributing descheduled time to whatever processes happened to be running while the catch-up interrupts are delivered, and without violating typical guest operating system timing assumptions.

Method and system for improving the accuracy of timing and process accounting within virtual machines

A virtual computer system includes multiple timer emulators for emulating multiple virtual timers in a virtual machine (VM). A time coordinator keeps track of an apparent time that is provided to the multiple timer emulators for presentation to the VM through the virtual timers. In particular, the time coordinator ensures that timer events generated by the multiple timer emulators are presented to the VM in an appropriate sequence and with substantially appropriate relative apparent times. Also, when guest software reads a count from a virtual timer, the time coordinator ensures that the apparent time presented to the guest software is substantially consistent with the apparent times represented by preceding and succeeding timer events. When the apparent time falls behind the real time of the physical computer system, the time coordinator speeds up the apparent time until it catches up to the real time.

Method and apparatus for emulating multiple virtual timers in a virtual computer system when the virtual timers fall behind the real time of a physical computer system

Growing community of inventors

Palo Alto, CA, United States of America

Timothy P Mann