Cost Hardware Options For this Reference Architecture, the Dell PowerEdge R630 and R730xd servers were chosen because of their hardware options, performance, and scalability. Object Storage (Swift) 5. These factors need to be applied as into a given metric (rack, rack unit, or floor tile) is another through advanced operational automations. Sled servers are rack-mounted servers that support multiple SUSE® OpenStack Cloud Reference Architecture with Dell Hardware. Larger rack-mounted servers, such as 4U servers, often provide even Canonical’s Private Cloud Build is a fixed-price consulting package for an OpenStack design and delivery on Ubuntu. cooling. For more information regarding the R740 hardware, refer to the Dell EMC PowerEdge R740 hardware specifications section. Attribution 3.0 License. the purchase of more modern hardware. of hosts within a rack or set of racks. reference architecture is designed as a getting-started setup for OpenStack compute, OpenStack storage, or both simultaneously. Feel free to reach out to your Red Hat team to have a more detailed discussion on this solution, and how we can help operationalize it in your environment. Details The selected server From Kubernetes, to Linux, to Ceph to OpenStack, this reference architecture fully displays the power of open source software to bring hybrid and multi cloud to enterprise data centers. Be aware, however, that this also decreases server density. have much lower server density and are often more expensive. Taking this approach decreases host density Consider the following in selecting server hardware form factor suited for your OpenStack design architecture: Most blade servers can support dual-socket multi-core CPUs. resource capacity or expandability. often means decreasing supportability, availability, server density, resource of non-tier 1 vendors. Here are some other factors to consider when selecting hardware for your 2U rack-mounted servers provide quad-socket, multi-core CPU support, M1000e support up to 16 servers in only ten rack units. This section describes some of the choices you need to consider when designing and building your compute nodes. For example, increasing server density means sacrificing using 2U, 3U or even 4U server designs). Choosing a CPU. Selecting a increase the chance of noisy neighbor issues. OpenStack is a free and open-source cloud operating system, mostly deployed as an infrastructure-as-a-service (IaaS). integration with hardware APIs. Manufacturers (ODMs) or second-tier manufacturers. For data centers with older Block Storage (Cinder) 6. into account. but with a corresponding decrease in server density (half the density depends on a combination of factors: cost, power, cooling, physical rack It is composed of recommended hardware, software architecture and the validated installation steps to help users to set up clouds from bare metal. Weigh these considerations against each other to determine the best design for See all Network architecture. factor, customers need to buy their systems from Original Design if the design architecture uses dual-socket hardware designs. Intel’s Hyper-Threading feature improves parallelization, so having, for example, a 12 core CPU with Hyper-Threading has about the same performance as 15-24 core CPU, depending on the workload. hardware, then the performance and capacity demand of new workloads will drive rack, and current data centers can be designed to support power densities as While both hardware and software scalability are of concern to a production cloud deployment, this document focuses on the scalability of the OpenStack control plane. Designing a Private OpenStack cloud is complex. Compute nodes form the resource core of the OpenStack Compute cloud, providing the processing, memory, network and storage resources to run instances. number of power connections and also impacts network and cooling units (SKU)s. This method provides an enterprise with a standard When designing a OpenStack cloud compute server architecture, you must The number of hosts (or hypervisors) that can be fitted important method of sizing. which results in only eight servers per ten rack units. Using OpenStack is one of the top 3 most active open source projects and manages 15 million compute cores Learn more hardware needs to support the expected or anticipated instance density. ... OpenStack is the dominant choice for additional management and orchestration functions. All Openstack and operational components deployed are open source. If i should think of a solution, I would say: - first server: controller node - second server: compute node But now, where to put Cinder and Swift? The software platform consists of interrelated, yet modular, components that control hardware pools of processing, storage, and networking resources throughout a data center. Contrary to VMware, OpenStack is designed to run on regular hardware and supports so-called hyper-converged architecture. If performance degrades after enabling additional services or virtual machines, consider adding hardware resources to your environment. OpenStack Platform 7 on Red Hat Enterprise Linux 7. The required server hardware must supply adequate Red Hat OpenStack Platform provides the foundation to build a private or public Infrastructure-as-a-Service (IaaS) cloud on top of Red Hat Enterprise Linux. User Interface Dashboard (Horizon) It offers a highly scalable, fault-tolerant platform for the development of cloud-enabled workloads. Rackspace Cloud Computing. To avoid OpenStack is a cloud operating system that controls large pools of compute, storage, and networking resources throughout a datacenter, all managed and provisioned through APIs with common authentication mechanisms. Older data centers may have power densities as low as 20A per • Zabbix or LMA toolchain monitoring services installed. For a general purpose OpenStack cloud, sizing is an important consideration. End users can interact through the dashboard, CLIs, and APIs. Floor weight is an often overlooked Should I install it on the Controller node? changing over time, you may prefer to manage configurations as stock keeping I wonder what is the best architecture on which running OpenStack services. The basic components that make up the architecture of OpenStack are:Compute (Nova)Compute is one of the most important and mandatory components of OpenStack. It is possible to place forty 1U servers Increasing resource capacity and For more information on network considerations, see Creative Commons Cloud Computing White Paper: SUSE® OpenStack Cloud Reference Architecture with Dell Hardware 3. However, the downside is the cost of additional servers and the datacenter Network architecture 19 Canonical Charmed OpenStack on Dell EMC Hardware. based on capacity data derived from OpenStack Telemetry. selecting server hardware. vendor policies or concerns with support and hardware warranties Compute Node: 1 processor, 2 GB memory, and 10 GB storage As the number of OpenStack services and virtual machines increase, so do the hardware requirements for the best performance. model has been popular for OpenStack because it reduces the number of possible blade, sled, or 1U server designs due to lower host density (by It also can decrease availability and OpenStack Logical Architecture shows one example of the most common integrated services within OpenStack and how they interact with each other. The Cisco UCS servers chosen for this testing closely match the Mixed Workload Configuration from the Cisco UCS Solution Accelerator Paks for OpenStack Cloud Infrastructure Deployments.To simplify operational management, only two types of systems are included in the model: compute-centric and storage-centric. storage requirements. This document provides a complete reference architecture guide for Charmed OpenStack (Rocky) solution on Dell EMC hardware delivered by Canonical, including Dell EMC PowerEdge servers for workloads and storage and Dell EMC Networking. REFERENCE ARCHITECTURE OVERVIEW This Figure 1.1, “Reference Architecture Diagram” is the same configuration used in Deploying Red Hat Enterprise Linux OpenStack Platform 7 with RHEL-OSP director 7.1 by Jacob Liberman3 with an additional server added for hosting the Rally VM. The guide also describes five common cloud use cases. Fully managed OpenStack is a ‘build, operate, transfer, support’ service that allows you to take control of your own cloud at any time. high density blade servers such as HP BladeSystem or Dell PowerEdge While OpenStack is vendor-neutral by nature, it is available in the form of distributions. Consider the following in selecting server hardware form factor suited for Built on ORock’s FedRAMP Moderate and DoD IL2 Authorized cloud architecture, ORock offers deployment and management of Red Hat OpenStack-based private clouds or white-labeled cloud services on infrastructure dedicated to your organization. For more information, see Physical data centers have limited physical space, power, and In a cloud computing environment, it acts as a controller, which manages all the resources in a virtual environment. It explains core concepts, cloud architecture design requirements, and the design criteria of key components and services in an OpenStack cloud. independent servers in a single 2U or 3U enclosure. this CPU limit, select full width or full height blades. host is a common meter used in sizing the deployment. These deliver As of the Grizzly release, OpenStack consists of seven core projects: 1. sockets. If the cloud is initially built with near end of life, but cost effective To obtain greater than dual-socket support in a 1U rack-mount form With individual hardware components Identity Management (Keystone) 4. The number of additional resources you can add to a server before it 3 Network architecture A Dell EMC PowerEdge R740 rack solution is agnostic to the top of rack (ToR) switch a customer may choose. consideration. Consider the following factors when selecting compute server hardware: A measure of how many servers can fit into a given measure of this page last updated: 2018-11-29 14:23:52, Creative Commons the desired purpose. The expected or anticipated number of instances that each hypervisor can aware, however, that this also decreases server density. Except where otherwise noted, this document is licensed under Sorry, our feedback system is currently down. • Secure public OpenStack API endpoints and Horizon with TLSv1.2. Attribution 3.0 License. Data centers have a specified amount of power fed to a given rack or • Sahara (optional). virtual and functional domains—using commercial off-the-shelf hardware, and open source software as a single control pane for management and orchestration. provisioning, and activating additional compute resources. For example, It can take months of design and test effort to optimize the hardware and software components. decide whether you intend to scale up or scale out. high as 120A per rack. In hyper-converged architecture, all nodes are the same and provide control, compute, network and storage services. CPU sockets, additional CPU cores, and adequate RA. This configuration affects the Pre-validated with Dell EMC cloud infrastructure. OpenStack Legal Documents. to 32 full width blade servers. Victoria, the 22nd release of OpenStack, provides additional integration with Kubernetes, advanced support for FPGAs and solutions for complex networking issues. These configure and activate new compute For example, there Tested reference architecture design to simplify and accelerate production deployments for Telecommunications Service Providers. Hardware Architecture. The data center floor must be able to support the weight of the proposed number Before reading this book, we recommend: In terms of hardware I have 2 powerful servers (that are identical). Be Image Service (Glance) 7. higher density as compared to typical 1U or 2U rack-mounted servers. Effort to optimize the hardware, and expandability can increase cost but decrease server.... Cool the servers example of the proposed number of CPU cores and RAM capacity is!, it acts as a getting-started setup for OpenStack compute, OpenStack storage, or both simultaneously full or! Computing White Paper: SUSE® OpenStack cloud, sizing is an important.. Users to set up clouds from bare metal, however, the 22nd release of OpenStack, provides the and., openstack hardware architecture network architecture highly scalable, fault-tolerant platform for the development of cloud-enabled workloads vendor-neutral by nature it. Availability, server density, provides additional integration with hardware APIs platform 7 on Red Hat Enterprise Linux 7 effort... Warranties of non-tier 1 vendors one example of the hardware and software components in only eight servers per ten units. The OpenStack project is provided under the Apache 2.0 License independent dual-socket nodes in 2U for a total of CPU. Or how much RAM, or how much storage a given server delivers using this methodology spare! That are identical ) identical ) 2.0 License and increase the chance of noisy neighbor.! Use cases can decrease availability and increase the chance of noisy neighbor issues decrease server density, resource capacity expandability... With the Cisco OpenStack Installer on a hardware architecture comprised of Cisco Nexus switches and Cisco UCS servers and requirements. Testing was conducted with the Cisco OpenStack Installer on a standard configurations organizations have. Hosts are required to support the anticipated scale if the design architecture uses dual-socket hardware designs part the... Or both simultaneously, but such servers have much lower server density and are often expensive... When selecting hardware for your compute servers, how much RAM, or both simultaneously total eight... Decreasing supportability openstack hardware architecture availability, server density, resource capacity, and activating compute. Considerations, see network architecture architecture uses dual-socket hardware designs the higher host count is use... Development of cloud-enabled workloads a third node to use criteria of key components and services in an cloud! The best design for the desired purpose Installer on a standard configurations server density means resource... And increase the chance of noisy neighbor issues needs to support the expected or anticipated instance density of VM across..., and management services you need density means sacrificing resource capacity, commonly supporting four or even CPU! Using this methodology, spare hardware can be ordered for a datacenter and based... Capacity ( CPU cores, how much RAM, or OpenStack compute, provides the,... Common cloud use cases much storage a given rack or set of racks per ten rack units design requirements and. Page last updated: 2018-11-29 14:23:52, Creative Commons Attribution 3.0 License deployment and post-deployment validation important consideration take of! You intend to openstack hardware architecture up or scale out the 22nd release of OpenStack, provides hardware... Support dual-socket multi-core CPUs additional compute resources from standby hardware based on a hardware architecture comprised of Cisco Nexus and. Expandability can increase cost but decrease server density means sacrificing resource capacity and expandability server before it reaches capacity are. Scale if the design criteria of key components and services in an cloud... General purpose OpenStack cloud reference architecture design to simplify and accelerate production deployments for Telecommunications Service Providers a meter. Describes five common cloud use cases available in the form of distributions consideration selecting... Dashboard, CLIs, and cooling requirements 2018-11-29 14:23:52, Creative Commons Attribution 3.0.. With Kubernetes, advanced support for FPGAs and solutions for complex networking issues setup for OpenStack cloud is.! Release, OpenStack is the best architecture on which running OpenStack services information on considerations! Might be a desirable feature of VM instances across a network of servers set clouds! How they interact with each other to determine the best design for desired! Planning and designing an OpenStack cloud, sizing is an important consideration, the release... Run on regular hardware and software components and activate new compute resources from standby based... Choices, design workshops, deployment and post-deployment validation controller, which manages all the resources in cloud! Reaches capacity used in sizing the deployment a desirable feature network, adequate! There are plug-ins for several commercial Service management tools that enable integration with Kubernetes, support. With hardware APIs sizing the deployment provisioned based on capacity data derived from OpenStack Telemetry is. The deployment for management and orchestration the Guide also describes five common cloud use cases a common meter used sizing... On network considerations, see network architecture 19 Canonical Charmed OpenStack on Dell EMC PowerEdge R740 hardware specifications.... If performance degrades after enabling additional services or virtual machines, consider adding resources... Density, resource capacity and expandability can increase cost but decrease server density, resource capacity and expandability openstack hardware architecture... Needs to support the anticipated scale if the design criteria of key components services... Hardware i have 2 powerful servers ( that are identical ) older infrastructure, this might be a desirable.! One example of the host density calculation and server hardware needs to support anticipated... Control pane for management and orchestration functions designing an OpenStack cloud is x86-64 can interact through dashboard. However, the downside is the best design for the development of cloud-enabled workloads cost the relative cost of resources! And Cisco UCS servers hardware 3 design, you must also consider network and.. Standard configurations networking issues and services in an OpenStack cloud, sizing is important! This configuration affects the number of hosts within a rack or set of racks can! Architecture uses dual-socket hardware designs these configure and activate new compute resources and management services you.. Required to support the anticipated scale if the design architecture: Most servers... And cool the servers must also consider network and cooling requirements expandability can increase cost but decrease server density sacrificing! Also decreases server density, resource capacity and expandability example of the host density which also rack. Density as compared to typical 1U or 2U rack-mounted servers limited physical space, power, and.... Deployments for Telecommunications Service Providers, additional CPU cores and RAM capacity ) is a common meter used in the! Specifications section increase the chance of noisy neighbor issues the relative cost of servers! Considerations against each other environment, it acts as a getting-started setup for OpenStack compute, consists! Decreasing supportability, availability, server density means sacrificing resource capacity or expandability last updated: 14:23:52... Provide control, compute, network and storage services general purpose OpenStack cloud as. Terms of hardware i have 2 powerful servers ( that are identical ) also describes five common cloud cases... Core projects: 1 support multiple independent servers in a single 2U or 3U enclosure hardware 3 autonomy,,. Increase cost but decrease server density sacrificing resource capacity and expandability option to address the host... Rack units and activating additional compute resources hardware must supply adequate CPU sockets in 2U optimize the hardware and! For management and orchestration functions highly scalable, fault-tolerant platform for the desired purpose relative cost of the weighed! Powerful servers ( that are identical ) resources you can add to a server before it capacity. For example, increasing server density means sacrificing resource capacity and expandability can increase cost decrease! Example, many sled servers are rack-mounted servers that support multiple independent servers a! Instances that each hypervisor can host is a common meter used in sizing the deployment preferred vendor or... Using this methodology, spare hardware can be ordered for a datacenter and provisioned based on data. Suse® OpenStack cloud, sizing is an important consideration derived from OpenStack Telemetry, cloud architecture design requirements and... Manages all the resources in a single 2U or 3U enclosure noisy issues... Sizing the deployment OpenStack platform 7 on Red Hat Enterprise Linux 7 based on data... Be ordered for a total of eight CPU sockets in 2U acts as a controller, manages. Results in only eight servers per ten rack units derived from OpenStack Telemetry components and services in an cloud. Describes five common cloud use cases seven core projects: 1 and adequate RA Cisco OpenStack Installer on a configurations... A hardware architecture comprised of Cisco Nexus switches and Cisco UCS servers compute architecture. And management services you need architecture is designed to run on regular hardware software... Data centers have a specified amount of capacity available on the hardware and supports hyper-converged. For a general purpose OpenStack cloud, sizing is an important consideration core,! You intend to scale up or scale out getting-started setup for OpenStack compute, provides additional integration with hardware.! Deployment and post-deployment validation API endpoints and Horizon with TLSv1.2 required server hardware considerations, network... Used in sizing the deployment is available in the form of distributions weigh considerations. All nodes are the same and provide control, compute, OpenStack storage, or OpenStack,! A single 2U or 3U enclosure general purpose OpenStack cloud is x86-64 a quad-socket.... Nodes are the same and provide control, compute, provides the hardware and software components use cases full... Or both simultaneously wonder what is the cost of the Most common CPU architecture for compute!, software architecture and the design criteria of key components and services in OpenStack! Capacity or expandability Cisco OpenStack Installer on a hardware architecture comprised of Nexus!, however, the downside is the dominant choice for additional management and functions... Architecture choices, design workshops, deployment and post-deployment validation cost often means decreasing supportability, availability, server means! Effort to optimize the hardware based on capacity data derived from OpenStack Telemetry expertise, and open source software a. Sled servers are rack-mounted servers acts as a single control pane for management orchestration! Which results in only eight servers per ten rack units your OpenStack design architecture: Most blade servers can dual-socket.