Category Archives : Virtual Machines



General availability of new Azure disk sizes and bursting

Today marks the general availability of new Azure disk sizes, including 4, 8, and 16 GiB on both Premium and Standard SSDs, as well as bursting support on Azure Premium SSD Disks.

To provide the best performance and cost balance for your production workloads, we are making significant improvements to our portfolio of Azure Premium SSD disks. With bursting, even the smallest Premium SSD disks (4 GiB) can now achieve up to 3,500 input/output operations per second (IOPS) and 170 MiB/second. If you have experienced jitters in disk IOs due to unpredictable load and spiky traffic patterns, migrate to Azure and improve your overall performance by taking advantage of bursting support.

We offer disk bursting on a credit-based system. You accumulate credits when traffic is below the provisioned target and you consume credit when traffic exceeds it. It can be best leveraged for OS disks to accelerate virtual machine (VM) boot or data disks to accommodate spiky traffic. For example, if you conduct a SQL checkpoint or your application issues IO flushes to persist the data, there will be a sudden increase of writes against the attached disk. Disk bursting will give you the headroom to accommodate the expected and unexpected change in




Azure Dedicated Host: New capabilities and benefits

Late last year, we’ve announced the general availability of Azure Dedicated Hosts. This blog provides an update regarding the new and recently added capabilities since we introduced Azure Dedicated Hosts in preview.

Azure Dedicated Host provides a single-tenant physical server to run your Azure Virtual Machines for Windows Server and Linux. With Azure Dedicated Host, you can address specific compliance requirements while increasing visibility and control over your underlying infrastructure.

What’s new Save costs with Azure Dedicated Hosts reservations

We recently introduced the ability for you to purchase Azure reservations for Dedicated Hosts. You are now able to reduce costs by buying Azure Dedicated Hosts reservations. The reservation discount is applied automatically to the number of running dedicated hosts that match the reservation scope and attributes. You don’t need to assign a reservation to a specific dedicated host to get the discounts. You may also delete and create hosts and have the reservation apply to the hosts already deployed at any given time.

The Azure Dedicated Hosts pricing page contains the complete list of Dedicated Hosts SKUs, their CPU information, and various pricing options including Azure reservations discounts.

Azure Dedicated Host SKUs, unlike Azure Virtual Machines, are defined based on




Microsoft is expanding the Azure Stack Edge with NVIDIA GPU preview

We’re expanding the Microsoft Azure Stack Edge with NVIDIA T4 Tensor Core GPU preview during the GPU Technology Conference (GTC Digital). Azure Stack Edge is a cloud-managed appliance that brings Azure’s compute, storage, and machine learning capabilities to the edge for fast local analysis and insights. With the included NVIDIA GPU, you can bring hardware acceleration to a diverse set of machine learning (ML) workloads.

What’s new with Azure Stack Edge

At Mobile World Congress in November 2019, we announced a preview of the NVIDIA GPU version of Azure Stack Edge and we’ve seen incredible interest in the months that followed. Customers in industries including retail, manufacturing, and public safety are using Azure Stack Edge to bring Azure capabilities into the physical world and unlock scenarios such as the real-time processing of video powered by Azure Machine Learning.

These past few months, we’ve taken our customers’ feedback to make key improvements and are excited to make our preview available to even more customers today.

If you’re not already familiar with Azure Stack Edge, here are a few of the benefits:

Azure Machine Learning: Build and train your model in the cloud, then deploy it to the edge for FPGA or




Microsoft powers transformation at NVIDIA’s GTC Digital Conference

The world of supercomputing is evolving. Work once limited to high-performance computing (HPC) on-premises clusters and traditional HPC scenarios, is now being performed at the edge, on-premises, in the cloud, and everywhere in between. Whether it’s a manufacturer running advanced simulations, an energy company optimizing drilling through real-time well monitoring, an architecture firm providing professional virtual graphics workstations to employees who need to work remotely, or a financial services company using AI to navigate market risk, Microsoft’s collaboration with NVIDIA makes access to NVIDIA graphics processing units (GPU) platforms easier than ever.

These modern needs require advanced solutions that were traditionally limited to a few organizations because they were hard to scale and took a long time to deliver. Today, Microsoft Azure delivers HPC capabilities, a comprehensive AI platform, and the Azure Stack family of hybrid and edge offerings that directly address these challenges.

This year during GTC Digital, we’re spotlighting some of the most transformational applications powered by NVIDIA GPU acceleration that highlight our commitment to edge, on-prem, and cloud computing. Registration is free, so sign up to learn how Microsoft is powering transformation.

Visualization and GPU workstations

Azure enables a wide range of visualization workloads, which are critical




Announcing the general availability of Azure Monitor for virtual machines

Today we’re announcing the general availability of Azure Monitor for virtual machines (VMs), which provides an in-depth view of VM performance trends and dependencies. You can access Azure Monitor for VMs from the Azure VM resource blade to view details about a single VM, from the Azure Virtual Machine Scale Sets (VMSS) resource blade to view details about a single VM scale set, and from Azure Monitor to understand compute issues at scale.

Azure Monitor for VMs brings together key monitoring data about your Windows and Linux VMs, allowing you to:

Troubleshoot guest-level performance issues and understand trends in VM resource utilization. Determine whether back-end VM dependencies are connected properly and which clients of a VM may be affected by any issues the VM is having. Discover VM hotspots at scale based on resource utilization, connection metrics, performance trends, and alerts. Performance

Performance views are powered by Log Analytics, and offer powerful aggregation and filtering capabilities including “Top N” VM sorting and searching across subscriptions and regions, aggregation of VM metrics (such as average memory) across all VMs in a resource group across regions, percentiles of performance values over time, and breakdown and selection of VM Scale Set instances.





Power your Azure GPU workstations with flexible GPU partitioning

Today we’re sharing the general availability of NVv4 virtual machines in South Central US, East US, and West Europe regions, with additional regions planned in the coming months. With NVv4, Azure is the first public cloud to offer GPU partitioning built on industry-standard SR-IOV technology.

NVv4 VMs feature AMD’s Radeon Instinct MI25 GPU, up to 32 AMD EPYC™ 7002-series vCPUs with clock frequencies up to 3.3 GHz, 112 GB of RAM, 480 MB of L3 cache, and simultaneous multithreading (SMT).

Pay-As-You-Go pricing for Windows  deployments is available now. One- and three-year Reserved Instance and Spot Pricing for NVv4 VMs will be available on April 1. Support for Linux will be available soon.

Affordable, modern GPU powered virtual desktops in the cloud

As enterprises look to the cloud to provide virtual desktops and workstations in a secure way to a highly mobile workforce, they face the significant challenge of managing cost and performance while meeting user experience expectations. Traditionally, public clouds offered virtual machines with one or more GPUs, which are best suited for the most GPU intensive workloads that required the full power and resources of a GPU. But for the regular knowledge worker profile, a full GPU could be




Plan migration of physical servers using Azure Migrate

At Microsoft Ignite, we announced new Microsoft Azure Migrate assessment capabilities that further simplify migration planning. In this post, I will talk about how you can plan migration of physical servers. Using this feature, you can also plan migration of virtual machines of any hypervisor or cloud. You can get started right away with these features by creating an Azure Migrate project or using an existing project.

Previously, Azure Migrate: Server Assessment only supported VMware and Hyper-V virtual machine assessments for migration to Azure. At Ignite 2019, we added physical server support for assessment features like Azure suitability analysis, migration cost planning, performance-based rightsizing, and application dependency analysis. You can now plan at-scale, assessing up to 35K physical servers in one Azure Migrate project. If you use VMware or Hyper-V as well, you can discover and assess both physical and virtual servers in the same project. You can create groups of servers, assess by group and refine the groups further using application dependency information.

While this feature is in preview, the preview is covered by customer support and can be used for production workloads. Let us look at how the assessment helps you plan migration.

Azure suitability analysis





Azure HBv2 Virtual Machines eclipse 80,000 cores for MPI HPC

HPC-optimized virtual machines now available

Azure HBv2-series Virtual Machines (VMs) are now generally available in the South Central US region. HBv2 VMs will also be available in West Europe, East US, West US 2, North Central US, Japan East soon.

HBv2 VMs deliver supercomputer-class performance, message passing interface (MPI) scalability, and cost efficiency for a variety of real-world high performance computing (HPC) workloads, such as CFD, explicit finite element analysis, seismic processing, reservoir modeling, rendering, and weather simulation.

Azure HBv2 VMs are the first in the public cloud to feature 200 gigabit per second HDR InfiniBand from Mellanox. HDR InfiniBand on Azure delivers latencies as low as 1.5 microseconds, more than 200 million messages per second per VM, and advanced in-network computing engines like hardware offload of MPI collectives and adaptive routing for higher performance on the largest scaling HPC workloads. HBv2 VMs use standard Mellanox OFED drivers that support all RDMA verbs and MPI variants.

Each HBv2 VM features 120 AMD EPYC™ 7002-series CPU cores with clock frequencies up to 3.3 GHz, 480 GB of RAM, 480 MB of L3 cache, and no simultaneous multithreading (SMT). HBv2 VMs provide up to 340 GB/sec of memory bandwidth, which is 45-50




Burst 4K encoding on Azure Kubernetes Service

Burst encoding in the cloud with Azure and Media Excel HERO platform.

Content creation has never been as in demand as it is today. Both professional and user-generated content has increased exponentially over the past years. This puts a lot of stress on media encoding and transcoding platforms. Add the upcoming 4K and even 8K to the mix and you need a platform that can scale with these variables. Azure Cloud compute offers a flexible way to grow with your needs. Microsoft offers various tools and products to fully support on-premises, hybrid, or native cloud workloads. Azure Stack offers support to a hybrid scenario for your computing needs and Azure ARC helps you to manage hybrid setups.

Finding a solution

Generally, 4K/UHD live encoding is done on dedicated hardware encoder units, which cannot be hosted in a public cloud like Azure. With such dedicated hardware units hosted on-premise that need to push 4K into the Azure data center the immediate problem we face is a need for high bandwidth network connection between the encoder unit on-premise and Azure data center. In general, it’s a best practice to ingest into multiple regions, increasing the load on the network connected between the




MSC Mediterranean Shipping Company on Azure Site Recovery, “ASR worked like magic”

Today’s Q&A post covers an interview between Siddharth Deekshit, Program Manager, Microsoft Azure Site Recovery engineering and Quentin Drion, IT Director of Infrastructure and Operations, MSC. MSC is a global shipping and logistics business, our conversation focused on their organization’s journey with Azure Site Recovery (ASR). To learn more about achieving resilience in Azure, refer to this whitepaper.

I wanted to start by understanding the transformation journey that MSC is going through, including consolidating on Azure. Can you talk about how Azure is helping you run your business today?

We are a shipping line, so we move containers worldwide. Over the years, we have developed our own software to manage our core business. We have a different set of software for small, medium, and large entities, which were running on-premises. That meant we had to maintain a lot of on-premises resources to support all these business applications. A decision was taken a few years ago to consolidate all these business workloads inside Azure regardless of the size of the entity. When we are migrating, we turn off what we have on-premises and then start using software hosted in Azure and provide it as a service for our subsidiaries. This new