Publicidad

Virtualización en la Red del Data Center - Extreme Networks

AEC Networks
12 de Mar de 2010
Publicidad

Más contenido relacionado

Publicidad
Publicidad

Virtualización en la Red del Data Center - Extreme Networks

  1. Evolution of Computing Environments Evolution timeline Mainframe Mini Computer Personal Computer Cloud computing Network and Communications Infrastructure © 2009 Extreme Networks, Inc. All rights reserved. Page
  2. “ Four Pillars” Solution Automated Customized Program & Application Integration XML - enabled Infrastructure Open APIs Physical Bandwidth and Performance Fixed and Modular Platforms Robust and Flexible Stacking Efficient Integration with VM Platforms Heterogeneous (Best of Breed) support for Virtual Machines Scalable Application Awareness & Support Provision 1,000s of Switches across Multiple Sites Reduce Network Tiers User Generated Scripts 1G  10G  40G  100G EPICenter ® single pane of glass VEPA Network Topology Network Profiles for VMs Automated Configuration © 2009 Extreme Networks Inc. All rights reserved. Page © 2009 Extreme Networks, Inc. All rights reserved. Value to the Data Center
  3. Complete Data Center Switching Portfolio DATA CENTER ACCESS Summit X650 8900-series modules Robust switching portfolio from Edge to Data Center with single operating system across product families to deliver highly resilient and highly scalable networks Summit X480 Summit X450a SCALABLE DATA CENTER CORE 8900-xl series modules EPICenter ® Summit ® Fixed Configuration BlackDiamond ® 8800 Chassis 1 Gigabit 10 Gigabit 10/100 – 10 Gigabit SummitStack™ ExtremeXOS ® Page © 2009 Extreme Networks, Inc. All rights reserved. NEW NEW
  4. Virtual Machine Explosion Page © 2009 Extreme Networks, Inc. All rights reserved. VMs (100 per) VMs (32 per) VMs (8 per)
  5. Extreme Networks: “Four Pillars” Solution Automated Customized Program & Application Integration XML - enabled Infrastructure Open APIs Physical Bandwidth and Performance Fixed and Modular Platforms Robust and Flexible Stacking Efficient Integration with VM Platforms Heterogeneous (Best of Breed) support for Virtual Machines Scalable Application Awareness & Support Provision 1,000s of Switches across Multiple Sites Reduce Network Tiers User Generated Scripts 1G  10G  40G  100G EPICenter ® single pane of glass VEPA Network Topology Network Profiles for VMs Automated Configuration Page © 2009 Extreme Networks, Inc. All rights reserved. Value to the Data Center
  6. Thank You Page © 2009 Extreme Networks, Inc. All rights reserved.
  7. © 2009 Extreme Networks, Inc. All rights reserved.

Notas del editor

  1. Extreme Networks ® has developed a network infrastructure solution that will accommodate the evolving technology landscape in the data center. This solution will allow users to migrate from a traditional or “physical” infrastructure to a virtual one without forcing a certain technology, or operating methodology on the user. This approach applies to Enterprises and hosting centers of any scale. © 2009 Extreme Networks, Inc. All rights reserved.
  2. The Data Center has become the new computer. Enterprise and service providers are looking to enable the ability to simply submit jobs and provision applications on the fly with no consideration of server capacity, memory or even location. Blade servers, rack servers, multi-core processors are virtualization are enabling a high degree of consolidation in the data center. These technologies have led to a much greater computational density in the server, rack and data center. As a result, Enterprises have been able to greatly reduce the number of and physical footprint of their data center locations. It is vary common for enterprises today to look to host their data centers in a two or three locations as opposed to 10 or greater. Efficient power management is becoming key. Costs of power are increasing and the new high density data centers are drawing more power and cooling. Governments around the world are putting caps in place as governments look to reduce carbon emissions. Data centers looking to optimize power consumption by automating power management in the Data Center, an example of this is moving to follow the moon models due to lower power costs at night. There are many similarities between enterprise and managed hosted with enterprise data center looking more like service providers having application level SLAs with internal departments. The immediate opportunity is for virtualization – storage solutions are 18 months away. © 2009 Extreme Networks, Inc. All rights reserved.
  3. With the advent of blade switches and soft switches in the hypervisor, we are seeing a blurring of the network edge in the data center, The traditional switching model of 2 or 3 tier networks where the edge is where switching begins has been replaced by the addition of 1 or 2 tiers of switching in the server. This model has greatly increased the complexity of switching in the data center both in terms of number of switches in the network, but also in terms of complexity of switching in the Data Center. Ability to configure and manage different virtual switches is an issue. Today, no standards exist for virtual switches. Each vendor has their own set of functionalities and capabilities. The challenge is how to have all these network layers, and different vendors co-exist, not just in data center, but even within a single server. © 2009 Extreme Networks, Inc. All rights reserved.
  4. The other issue that is created by the inclusion of switches in the server, either are a virtual switch or a blade switch, is who has responsibility for configuration and management of the switch in the server,. Traditionally, the ownership was with the networking group, but now that line has blurred. This blurring of the line between the server and the network can lead to an increase in the likelihood of errors and more complicated maintenance troubleshooting between the server and networking groups. This blurring of the line between the server and the network has created a shift in the control and management of networking level functions in the network. © 2009 Extreme Networks, Inc. All rights reserved.
  5. VM mobility is one of the biggest promises of virtualization. Disaster and site recovery processes count on the ability to dynamically move workloads. Resiliency and fault tolerance count heavily on this dynamic capability as well. The ability to provision new workloads dynamically relies on being able to move workloads around. Yet networks are static. Traditionally, network configurations were set up and rarely changed. As networks become dynamic, that changes and there is a requirement for the network to become dynamic. By this we mean, VM mobility requires the network configuration (VLAN, QoS, ACLs, etc) to dynamically follow the virtual machine as it moves through the network. © 2009 Extreme Networks, Inc. All rights reserved.
  6. We have broken our solution down into four pillars. You can think of these as phases of implementation for users. The leftmost pillar we call “Physical”. This is really the physical network where most users are today. As this physical network is the foundation for all virtualization it is incredibly important that this infrastructure be robust, easy to manage and scalable. Based upon this physical infrastructure, we move to a virtualized infrastructure which for us is a series of software modules that are loaded into ExtremeXOS ® . The second pillar – the first phase of virtualization we call “Efficient” From here we move through several phases of virtualization. The second pillar we call “efficient”. This is where the efficiencies of virtualization are realized through the network. The third pillar we call “Scalable”. This is where we provide dramatic scale in terms of number of switches and virtual machines that we support as well as moving to a highly scalable VEPA based architecture to support switching of the virtual machines in the network as opposes to on the server. The final is “Automated and Customized” This is where we provide a model for users to customize their environment and automate routine tasks that can be very time consuming at scale. We’ll address these in more detail in the next 30 minutes, but we wanted to put this framework up so that things will fit into context. © 2009 Extreme Networks, Inc. All rights reserved.
  7. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  8. One way we have enabled the simplification of the data center network is to reduce the number of tiers required to support these highly virtualized environments. With our “Direct Attach” model, we are able to reduce the complexity and number of network tiers by 1 or two tiers based on the configuration deployed. This architecture can greatly reduce cost, power and cabling and as well as increase performance in the network. The architecture leverages our BlackDiamond ® 8900-series modules that utilize the MRJ21 connector for high density data center environments. © 2009 Extreme Networks, Inc. All rights reserved.
  9. We have enabled the data center product family to be able to dynamically manage virtualization in the network. We use EPICenter ® , our management platform, to provide Hypervisor management integration and coordination as well as inventory of VMs, and future security functions. This VM aware capability enables us to tightly and dynamically mange virtualization moves and the associated virtual port profile moves (VPP) within the network – enabling a highly efficient and automated virtualization environment where the network and the virtual machines are tightly integrated. © 2009 Extreme Networks, Inc. All rights reserved.
  10. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  11. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  12. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  13. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  14. Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  15. Page Extreme Networks Confidential and Proprietary. © 2010 Extreme Networks Inc. All rights reserved.
  16. Today’s architecture includes having switching done at the virtual switch level. This architecture enables virtualization today, but there is a move within the industry to move the networking functionality back to the network. The industry is working on a standard called VEPA (Virtual Ethernet Port Adapter.) This standard allows switching to be moved back to the network. This has multiple benefits including reducing complexity, taking the switching burden off of the server, increasing security and removing the organizational complexity introduced by the virtual switch. © 2009 Extreme Networks, Inc. All rights reserved.
  17. Given the big push towards green and escalating cost of power, the network infra is an important part of the power equation. $1 in power consumes $2 in cooling BlackDiamond ® 8800 series consumes 1/3 of some of the competitors. Further ability to reduce power during off peak hours using customizable profiles. Profiles are essentially scripts that based on Time of day can turn off power to blades or ports on a stackable Allows data centers to truly follow the moon and be more power efficient © 2009 Extreme Networks, Inc. All rights reserved.
  18. The Extreme Networks ® product family is designed from the ground up to support automation and customization in the data center. We have a single operating system that runs across the product family. This single operating system has a standard XML API and SDK for easy integration as well as scripting capability (widgets) that enable easy automation of routine tasks. The product family also includes EPICenter ® , a management platform for managing and configuring the entire product portfolio. The platform also supports the ability to add loadable modules to the network to enable various functionality and capabilities. © 2009 Extreme Networks, Inc. All rights reserved.
  19. We have broken our solution down into four pillars. You can think of these as phases of implementation for users. The leftmost pillar we call “Physical”. This is really the physical network where most users are today. As this physical network is the foundation for all virtualization it is incredibly important that this infrastructure be robust, easy to manage and scalable. Based upon this physical infrastructure, we move to a virtualized infrastructure which for us is a series of software modules that are loaded into ExtremeXOS ® . The second pillar – the first phase of virtualization we call “Efficient” From here we move through several phases of virtualization. The second pillar we call “efficient”. This is where the efficiencies of virtualization are realized through the network. The third pillar we call “Scalable”. This is where we provide dramatic scale in terms of number of switches and virtual machines that we support as well as moving to a highly scaleable VEPA based architecture to support switching of the virtual machines in the network as opposes to on the server. The final is “Automated and Customized” This is where we provide a model for users to customize their environment and automate routine tasks that can be very time consuming at scale. © 2009 Extreme Networks, Inc. All rights reserved.
  20. © 2009 Extreme Networks, Inc. All rights reserved.
  21. © 2009 Extreme Networks, Inc. All rights reserved.
Publicidad