Design & Build

Data Center Solution-Primer: Using CloudPlex for Scaling the Virtual Data Center

by on ‎10-15-2012 01:03 PM - edited on ‎04-09-2014 04:47 PM by pmadduru (1,079 Views)

Synopsis: Primer about using Brocade's CloudPlex architecture with Brocade VCS Fabric with Brocade VDX Switches and partner virtualization and storage when building virtual data centers.

 

Contents

 

Summary 

A challenge for data center architects and designers is how to meet the mixed performance demands of a diverse set of business applications when they are deployed on virtual infrastructure. Disparate workloads such as business analytics with large data sets, aka, “Big Data”, back office applications with high rates of transaction performance (e.g., CRM, ERP, financial OLTP systems), virtual desktop infrastructure (VDI), and the newest Web 2.0 applications create a wide range of network performance requirements that are complex, challenging to design and can require expensive time-consuming test and validation phases prior to deployment.

 

CloudPlex from Brocade is a scale-out architecture to simplify virtual data centers and cloud computing services.

 

As shown in the CloudPlex architecture diagram CloudPlex creates virtual pools of compute, network and storage resources using an open architecture with server and storage choice.Virtualization removes the physical link between applications and the server, storage and network equipment. While this improves utilization, simplifies disaster recovery and increases availability for traditional client/server applications as well as the growing number of Web 2.0 applications, it has added complexity, particularly for the data center network.

 

The CloudPlex solution has a uniform scale-out architecture for servers, storage and networking so virtualization can deliver rapid deployment, automatic load balancing, live migration of workloads and data, and built-in high-availability. A modular architecture based on building blocks simplifies design, lowers the cost of scaling and reduces design and management complexity. reducing both first cost and total cost of ownership. Eliminating infrastructure "friction" allows rapid deployment of new applications and non-disruptive scale-up/scale-down of application resources as workloads vary during the application life-cycle.

 

 

Solution Framework

The figure below shows the virtualization model delivered by the CloudPlex architecture.

CloudPlex_Framework.jpg

   CloudPlex Framework (click to enlarge)

 

CloudPlex assembles physical resources into virtual resource pools (compute, network and storage). A key component is a "transport network" that ensures uniform bandwidth and latency between all physical devices with built-in high availability and self-configuration. Fabrics provide exactly this set of properties. Brocade provides two design blocks for the fabric transport, Brocade VCS Fabric for Ethernet and IP traffic and Brocade SAN fabrics for Fibre Chanel storage traffic. The CloudPlex architecture helps customers build a simple to manage fabric transport interconnecting all physical infrastructure in a virtual data center.

 

CloudPlex is a modular architecture so scalability extends from a single rack up to multiple active/active data centers with long distance WAN connectivity as shown in the figure below.

 

CloudPlex_ModularScaling.jpg

   CloudPlex Modular Scalability (click to enlarge)

 

Server virtualization clusters running tens of workloads per node and multiple thousands of workloads per cluster need to move any workload across server, storage and network resource pools as resource demands dictate at any scale. Storage clusters have similar requirements when data migrates within the cluster. This complicates operations and management if the physical network is not virtualization aware. CloudPlex integrates network policies within the fabric control plane. When orchestration software configures a virtual machine, network policies are automatically created, updated and migrated to the fabric control plane. Fabrics abstract the physical devices so they appear as a single virtual switch allowing policies to be set at the virtual switch layer so fabric services can ensure all physical switches in the fabric have the same policies. This eliminates manual reconfiguration of multiple switches and ports as workloads and storage migrate inside resource pools.

 

CloudPlex designs are based on reusable templates. Each larger scale template includes the smaller template extending it to the next level of scalability. This minimizes changes to already deployed infrastructure simplifying configuration and management. The reference below provides more details about how to use CloudPlex templates to design scalable virtual infrastructure: from a single rack to multiple active/active data centers.

 

References

 

Partners

CloudPlex partners include server and storage partners and virtualization software partners. Working with Brocade, these companies integrate their respective products and technology leveraging the CloudPlex architecture.

 

EMC_vspex-half-box.jpg

EMC VSPEX    

(Click to Access EMC content)

Accelerate your journey to the cloud with EMC VSPEX Proven Infrastructure. VSPEX is a set of complete virtualization solutions, proven by EMC and delivered to you by your trusted reseller. Designed for flexibility and validated to ensure interoperability and fast deployment, VSPEX gives you the power to choose the technology in your solution while removing the complexity and risk that typically comes with designing, integrating and deploying a best-of-breed solution. With VSPEX, private cloud computing is more accessible than ever.

HDS_UnifiedComputingSystem.jpg

Hitachi Data Systems UCP

(Click to access HDS content)

Hitachi Unified Compute Platform (UCP) is a family of completely integrated and flexible reference solutions. Each UCP solution has been specifically configured for immediate deployment and to run top tier infrastructure applications without over-purchasing or provisioning unnecessary equipment. Each custom-built solution has its entire solution stack certified. No more compatibility issues or accusations by different vendors’ technical support.

Fujitsu_dynamic_infrastructure_products.jpg

Fujitsu Dynamic Infrastructures

(Click to access Fujitsu content)

With the Dynamic Infrastructures portfolio, Fujitsu created a unique and comprehensive offering of IT products, datacenter- and office solutions, Infrastructure-as-a-Service and Managed Infrastructure services. This complete offering enables customers to make the most beneficial choices for their overall enterprise IT Infrastructure architecture and to select the most effective way to leverage alternative sourcing and delivery models at any time and around the globe. That is why Fujitsu calls it: Dynamic Infrastructures.

 

CloudPlex Templates

CloudPlex can be applied across a wide range of scales starting with a single rack all the way to dual active/active data center configurations at continental distances. This flexibility is achieved from a modular architecture of building blocks that can be assembled into repeatable templates. Each smaller template becomes a reusable block at the next step up in scale so redesign is avoided greatly reducing cost, risk and time to scale-up a CloudPlex design.

 

Single Rack

This use case integrates the server, storage an network infrastructure into resource pools and makes them available to virtualization hypervisors and management platforms. For availability and resiliency, two top-of-rack (ToR) VDX 67xx switches are used, connected together to form a two-node VCS Fabric cluster as shown below. This configuration can start small with 24 or 60 port fixed switch configurations using ports-on-demand to license only the ports needed. As the rack scales-up by adding more servers and storage, more VDX ports can be licensed for cost-effective scaling up to the full capacity of a single rack.

 

Template_SingleRack.jpg

   CloudPlex Single Rack Template (click to enlarge)

 

Refer to the CloudPlex Design Guide for more information about the single rack template.

 

References

 

Multiple Rack

This template scales out the single rack template extending the two-node ToR VCS Fabric into a multi-switch fabric extending the VCS Fabric across multiple racks. Relying on Brocade ISL Trunks, this template supports different fabric topologies: leaf/spine, collapsed spine and stacked. This flexibility in network topology is a hallmark of VCS Fabric technology. Plug-and-play configuration of the fabric simplifies deployment as network policies and MAC address tables are automatically inherited when a new switch is added to a VCS Fabric. The figure below shows the multiple rack template for a leaf/spine topology.

 

Template_Multirack.jpg

  CloudPlex Multiple Rack Template (click to enlarge)

 

Refer to the CloudPlex Design Guide for more information about the single rack template.

 

References

 

Multiple Fabric

This template is used when multiple VCS Fabrics are deployed. Release notes for NOS define the maximum tested limits for a VCS Fabric including total number of switches per fabric. It may be desirable to limit the diameter of a single fabric to fewer switches than the maximum. Often, there are customer environmental factors that limit the scale of a single fabric, for example, the desire to limit application tiers a separate fabric for easier administration and assurance of meeting SLAs. Whatever the reason, in larger environments, multiple fabrics will exist and traffic needs to be forwarded efficiently between fabrics without going through the core. The figure below shows the multiple fabric template.

 

Template_MultiVCSFabric.jpg

   CloudPlex Multiple Fabric Template (click to enlarge)

 

Refer to the CloudPlex Design Guide for more information about the single rack template.

 

References

 

Virtual Data Center

This adds a data center core template to the previous multiple fabric template. As shown in the figure, the aggregation fabric can scale-out by adding multiple VDX 8770 switches and multiple leaf fabrics can be deployed to scale-out the the number of edge devices. The datacenter core routes traffic between the datacenter network, the internet and the WAN. It could also connect to a campus/LAN environment as is commonly the case in healthcare, education, banking and retail. This template can be used when designing a private cloud data center.

 

Template_VirtualDataCenter.jpg

  CloudPlex Virtual Datacenter(click to enlarge)

 

 

Refer to the CloudPlex Design Guide for more information about the single rack template.

 

References

 

Global Data Centers

This template extends the virtual data center template. It uses a datacenter interconnect template that is an extension of the data center core template shown in the multiple fabric template. Virtualization can be used in multiple data centers to improve resource utilization and simplify disaster recovery. Where live migration of workloads is critical and latency is acceptable, this template can be used to design a dual active/active data center architecture. This option provides active/active replication of application state and storage between two data centers and can support live migration of running applications between servers in a stretched cluster (provided distances between the data centers meet the maximum latency restriction on live migration), recovery of applications after an unplanned outage and rerouting of client connections to the lowest latency site with global server load balancing.

 

 

Template_GlobalDatacenters.jpg

   CloudPlex Active/Active Datacenter Template (click to enlarge)

 

 

Refer to the CloudPlex Design Guide for more information about the single rack template.

 

References

 

Contributors