VIRTUAL SERVER INFRASTRUCTURE
Standard Performance Evaluation Corporation (SPEC) | September 18, 2021
The Standard Performance Evaluation Corporation’s (SPEC) Virtualization Committee released the SPECvirt Datacenter 2021 benchmark, a new multi-host benchmark for measuring the performance of a scaled-out datacenter. The SPECvirt Datacenter 2021 benchmark uses real-world and simulated workloads to measure the overall efficiency of virtualization solutions and their management environments. The new benchmark complements the existing SPECvirt_sc 2013 server consolidation benchmark, which is designed for a single-host environment.
Today’s datacenters use clusters of servers to ensure reliability, availability, serviceability, and security. Adding virtualization to a clustered solution enhances server optimization, flexibility, and application availability while reducing costs through server and datacenter consolidation. While the SPECvirt Datacenter 2021 benchmark enables analysis of these more complex multi-host environments, it is much easier to use than the SPECvirt_sc 2013 benchmark, providing a single virtual machine (VM) template to set up its harness and workloads. The SPECvirt Datacenter 2021 benchmark supports multiple hypervisor vendor solutions and ships with support for RHV 4.x and vSphere 6.x and 7.x.
“The ongoing evolution of virtualized environments has made it imperative that suppliers and buyers have a fair, vendor-agnostic tool for measuring the performance of solutions that power virtualized multi-host infrastructures,” said David Schmidt, Chair of the SPEC Virtualization Committee. “The SPECvirt Datacenter 2021 benchmark is easy to use and creates an excellent foundation for examining and comparing performance in these complex environments that are increasingly becoming the norm.”
The SPECvirt Datacenter 2021 benchmark provides a methodical way to measure a virtualization platform’s performance in a dynamic virtualized datacenter environment. It models typical, modern-day usage of virtualized infrastructure, such as VM resource provisioning, cross-node load balancing (including management operations such as VM migrations), and VM power on/off. The benchmark exercises datacenter operations under load and dynamically provisions new workload VMs from a preconfigured template or powers on existing VMs. As the load reaches maximum capacity of the cluster, hosts are added to the cluster to measure scheduler efficiency and maximize throughput.
The SPECvirt Datacenter 2021 benchmark feature overview:
Multi-host benchmark – Minimum of four hosts required, scales in increments of four.
Datacenter operations model – Multi-workload benchmark measures performance of hypervisor infrastructure, including how the hypervisor manager controls resources.
VM resource management – Handled by the hypervisor manager, including scheduling policies. Workload VMs powered on or deployed during benchmark.
Ease of use – Single preconfigured template VM to set up harness and workloads. No tuning of guest OS/software necessary.
Five real-world and simulated workloads –
OLTP database, based on HammerDB benchmark
Hadoop/Big Data cluster, based on BigBench benchmark
Simulated departmental mail server
Simulated departmental web server
Simulated departmental collaboration server
SPEC is a non-profit organization that establishes, maintains, and endorses standardized benchmarks and tools to evaluate performance for the newest generation of computing systems. Its membership comprises more than 120 leading computer hardware and software vendors, educational institutions, research organizations, and government agencies worldwide.
VIRTUAL DESKTOP TOOLS
Fungible | June 08, 2022
Fungible Inc., the dynamic composable infrastructure business, today announced the launch of Fungible Storage Cluster® (FSC) 4.1, which adds support for high-performance VMware vSphere settings.
In managing complex and dynamic computational environments, virtual machines give unrivaled flexibility. Storage needs for workloads operating in virtualized environments can vary. Fungible's high-performance all-flash array based on NVMe/TCP is now vSphere certified and available for VMware virtualized environments for demanding applications. Customers can now enjoy the improved management of vSphere paired with the excellent performance of Fungible's Storage Cluster thanks to the newest version (4.1).
Marc Fleischmann, Cloud CTO, VMware said that "NVMe/TCP enables vSphere customers to accelerate their storage performance while leveraging existing investments and lowering complexity. Through collaboration with innovative companies such as Fungible, VMware continues to build a world-class ecosystem of technology partners that offer our customers flexibility and choice to meet their business requirements.”
Customers can use NVMe/TCP to connect FSC storage into their ESXi hosts and obtain what looks to be local storage. Even though it is a shared resource, the resultant performance is essentially comparable to local storage, and the cost advantages mirror the performance benefits.
Eric Burgener, Research Vice President, Infrastructure Systems, Platforms and Technologies at IDC said that “VMware vSphere is the virtualization infrastructure of choice for a variety of mission-critical, performance-sensitive workloads in the data center. As IT organizations deploy more workloads that require accelerated compute and storage, the use of composable, disaggregated infrastructure (CDI) like that available from Fungible will be deployed more often to enable the more efficient use of these types of resources in VMware environments. IDC expects that the CDI market overall will top $4.8 billion by 2025.”
“VMware has long led the drive to improve flexibility and utilization of data center infrastructure. Now with the latest release of our vSphere certified Fungible Storage Cluster, VMware users can further enhance their ability to tune demanding workloads to get the utmost performance and flexibility. Trade-offs of flexibility versus performance are no longer required. Pairing VMware with NVMe/TCP for storage access with our DPU-powered Storage Cluster allows VMware customers to address the performance requirements of today's modern applications.”
Pradeep Sindhu, Co-Founder and CDO of Fungible
FSC may also result in storage cost reductions for vSphere users since its erasure coding offers comprehensive data protection at a lower cost than typical RF1 or RF2 replication. Moreover, Fungible's composable data architecture allows for the flexibility to compose storage to suit current demands and recompose it to adjust to the changing needs, giving exceptional investment protection.
VIRTUAL SERVER MANAGEMENT
Ekinops | November 09, 2020
EKINOPS (Euronext Paris: EKI) (ISIN: FR0011466069), a network access and virtualization specialist, today announces that Swisscom (Bern/CH), a leading ICT company in Switzerland, has selected Ekinops to deliver a new virtualized network solution on uCPE (universal Customer Premises Equipment). The Ekinops innovative solution, part of its Compose software portfolio, will make Swisscom the first in Switzerland to offer an agile branch connectivity solution to enterprise customers, based on virtualization technology, without disrupting existing services. The solution is comprised of the Ekinops fully open NFVi (Network Function Virtualization infrastructure), OneOS6-LIM middleware (Operating System and Local Infrastructure Manager), allowing access to an extensive catalog of certified VNFs (Virtualized Network Functions). This gives Swisscom the flexibility to select any white-box CPE hardware and choose from a range of third-party and Ekinops VNFs, as well as freeing them from vendor lock-in and simplifying supplier management.