vCPU Servers

a vcpu server https //docs ionos com/cloud/support/general information/glossary of terms#vcpu that you create is a new virtual machine (vm) https //docs ionos com/cloud/support/general information/glossary of terms#virtual machine vm provisioned and hosted in one of 's physical data centers a vcpu server behaves exactly like physical servers https //docs ionos com/cloud/compute services/compute engine/vcpu server#availability zones and you can use them either standalone or with other products you can create and configure your vcpu server https //docs ionos com/cloud/support/general information/glossary of terms#vcpu visually using the dcd https //docs ionos com/cloud/support/general information/glossary of terms#dcd interface for more information, see set up a vcpu server https //docs ionos com/cloud/compute services/compute engine/how tos/set up vcpu however, the creation and management of a vcpu server can be easily automated through the api, and our custom made tools like sdks https //docs ionos com/cloud/support/general information/glossary of terms#sdk note vcpu servers operate in single or multi threaded modes, depending on the underlying hardware your vcpu server's operating system exposes a single physical core with hyper threading technology as two distinct “logical cores” that process separate threads each individual cpu of a windows machine is considered a socket by the system vcpu servers add a new dimension to your computing experience these servers are configured with virtual cpus and distributed among multiple users sharing the same physical server the performance of your vcpu server relies on various factors, including the underlying cpu of the physical server, vm configurations, and the current load on the physical server our data center dashboard (dcd) https //docs ionos com/cloud/support/general information/glossary of terms#data center designer dcd lets you closely monitor your cpu utilization and other essential metrics through the monitoring manager note starting april 1, 2025, during the managed kubernetes node pool creation, apart from dedicated core server type, users can now also choose vcpu server for more information, see manage node pools https //docs ionos com/cloud/containers/managed kubernetes/how tos/management of node pools boot options for each vcpu server, you can select to boot from a virtual cd rom/dvd drive or a storage device ( hdd https //docs ionos com/cloud/support/general information/glossary of terms#hdd or ssd https //docs ionos com/cloud/support/general information/glossary of terms#ssd ) using any operating system on the platform the only requirement is the use of kvm virtio drivers for more information on how to install virtio drivers in windows, see install windows virtio drivers https //docs ionos com/cloud/backup and storage/block storage/how tos/install windows virtio drivers provides several ready to boot images with current versions of linux operating systems availability zones secure your data, enhance reliability, and set up high availability scenarios by deploying your vcpu servers and storage devices across multiple availability zones https //docs ionos com/cloud/support/general information/glossary of terms#availability zone allowing you to deploy your shared vcpu instances in different geographic regions assigning different availability zones ensures that vcpu servers or storage devices reside on separate physical resources at this helps ensure high availability and fault tolerance for your applications, as well as providing low latency connections to your target audience for example, a vcpu server or a storage device assigned to availability zone 1 resides on a different resource than a vcpu server or storage device assigned to availability zone 2 you have the following availability zone options zone 1 zone 2 a auto (default; our system automatically assigns an availability zone upon provisioning) nic multi queue to significantly enhance a virtual machine's (vm's) https //docs ionos com/cloud/support/general information/glossary of terms#virtual machine vm network performance, nic multi queue https //docs ionos com/cloud/network services/vdc networking/nic multi queue distributes network traffic by assigning multiple queues to the vm based on its cpu cores, which prevents input or output (i/o) bottlenecks and reduces latency this results in improved throughput and is critical for applications that require high network bandwidth, such as databases and high performance computing workloads for more information on enabling it for your vm, see enable nic multi queue https //docs ionos com/cloud/network services/vdc networking/nic multi queue#nic multi queue live vertical scaling (lvs) if the capacity of your virtual data center (vdc) https //docs ionos com/cloud/support/general information/glossary of terms#virtual data center vdc no longer matches your requirements, you can still increase or decrease your resources after provisioning upscaling resources allows you to change the resources of a vcpu server without restarting it, permitting you to add ram or nics https //docs ionos com/cloud/support/general information/glossary of terms#nic ("hot plug") to it while it is running this change allows you to react to peak loads quickly without compromising performance after uploading, you can define the properties of your images before applying them to new storage volumes the settings must be supported by the image, otherwise, they will not work as expected after provisioning, you can change the settings directly on the storage device, which will require a restart of the vcpu server the types of resources that you can scale without rebooting will depend on the operating system of your vcpu server https //docs ionos com/cloud/compute services/compute engine/vcpu server#availability zones since kernel 2 6 25, linux has lvo modules installed by default, but you may have to activate them manually depending on the derivative virtio https //docs ionos com/cloud/support/general information/glossary of terms#virtio drivers are optimized for virtual environments and provide direct access to underlying hardware for images, the supported properties are already preset without restarting the vcpu server, its resources can be scaled as follows upscaling cpu, ram, nics, storage volumes downscaling nics, storage volumes scaling up is the increase or speed up of a component to handle a larger load the goal is to increase the number of resources that support an application to achieve or maintain accurate performance scaling down means reducing system resources, whether or not you have used the scaling up approach without restarting the vcpu server, only upscaling is possible vcpu server features vcpu server provides the following features flexible resource allocation provides you with presets, which are recommended vcpu to ram configurations for your virtual machines furthermore, this option empowers you to add or remove compute resources flexibly to meet your specific needs the robust compute engine platform supports the vcpu servers, ensuring seamless integration additionally, the features offered by the compute engine platform remain accessible for utilization with vcpu servers virtualization technology enables efficient and secure isolation between different vms, ensuring the performance of one vm does not impact the others reliable performance and computing capabilities make it suitable for a wide range of applications the underlying infrastructure is optimized to provide reliable cpu performance, ensuring your applications run smoothly easy management via the intuitive data center designer you can easily create, modify, and delete vcpu servers, monitor their usage, and adjust the resources according to your needs vcpu server benefits vcpu server provides the following benefits cost effective vcpu server helps reduce costs when compared to major hyperscalers with similar resource configurations this makes it an ideal choice for small to medium sized businesses or individuals with budget constraints scalability with the vcpu server, you have the flexibility to scale your computing resources up or down based on your requirements this ensures that you can meet the demands of your applications without overprovisioning or paying for unused resources reliability and availability 's infrastructure ensures high availability and reliability by distributing resources across multiple physical servers, minimizes the impact of hardware failures, providing a stable and resilient environment for your applications easy setup setting up the vcpu server is straightforward the dcd and api offer controls for provisioning and configuring vcpu servers, allowing you to get up and running quickly limitations of vcpu servers this section lists the limitations of vcpu servers cpu family of a vcpu server cannot be chosen at the time of creation and cannot be changed later vcpu server configurations are subject to the following components minimum maximum vcpu 1 vcpu 60 vcpus ram 0,25 gb ram 230 gb ram nics and storage 0 pci connectors 24 pci connectors cd rom 0 cd roms 2 cd roms additional ram sizes are available on request to increase the ram size, contact your sales representative or support https //docs ionos com/cloud/support/general information/contact information ram sizes because the working memory (ram) size cannot be processed during the initial configuration, a newly provisioned vcpu server with more than 8 gb of ram may not start successfully when created from the windows images live vertical scaling linux supports the entire scope of live vertical scaling, whereas windows is limited to cpu scaling furthermore, it is not possible to use lvs to reduce storage size after provisioning