Engineers from La Salle-URL share the latest news and projects in the field of network solutions in telematic engineering.

05 April 2016 | Posted by Redacción Data Center

Services in a data center

Hey folks! How you doing?

Today we are presenting a new important part of our datacenter design. We are going to talk about services.

There are a lot of services in a bank by which people have the possibility to access to their emails, bank accounts, applications of the bank and so on. These services need to be run somewhere and this means using servers. Time ago, it was necessary to run one service per device, so imagine the amount of machines were necessary to deploy all services in a data center. It was a waste of money, time consumption (in order to configure every server with its service running) and also using more space (the more services were necessary to run, the more servers and space was necessary). I will not go in depth in this topic as Aleix has explained in the post before.

So merely I will focus in servers. In our bank data center requirements we talked about using DELL as our supplier for servers. Surfing the net and in this case seeking in DELL's website, we have found some interesting solutions that DELL is providing to his/her customers. These are PowerEdge C4130 rack server and PowerEdge C6320 rack server. Is necessary to choose one of them. We have been comparing both solutions and finally we have reached to something.

The solution which best fits our bank data center requirements has been the PowerEdge C6320 rack server. Why this one and not the other one? Indeed is easy to explain.

First, a quick look on the technical specifications:

grafica_jeeP

As you can see C6230 has better features, such as network controller speed, more socket servers, more memory and something very interesting, embedded hypervisor. Very helpful in order to manage everything more easily. Moving forward, we are looking for something which will optimize compute performance because a bank is always growing. This imply the necessity to manage complexities of growing and maintaining an hyperscale, high-performance and cloud computing data center environments. This means:

Performance and efficiency

With PowerEdge C6320 servers is possible to use:

  • Next-generation Intel® Xeon® E5-2600 v4 processors with increased core counts over prior E5-2600 v3 models, supporting up to 512GB of memory per server node for a total of 2TB of memory in a highly dense and modular 2U solution.
  • Integrated Dell Remote Access Controller (iDRAC8) with Lifecycle Controller, cost optimized in C6320, to provide stable, efficient server management in physical, virtual, local and remote environments.

Maximum flexibility

Save space and meet changing workloads by providing the right mix of processor performance, node options and energy efficiency with up to four independent sleds (server nodes) and flexible HDD assignments in one 2U chassis.

  • Up to 44 cores per node, 176 core per chassis
  • Up to 24 x 2.5" or 12 x 3.5" SAS, SATA or SSD hot-plug drives per chassis
  • Dual hot-plug, high-efficiency 1400W and 1600W power supplies
  • Optional Integrated SATA DOM (64GB) boot device frees up valuable hard drive space for your data
  • One x16 PCIe 3.0 slot and one x8 PCIe 3.0 mezzanine slot per 1U sled
  • Integrated LOM: 2x 10GbE (SFP+)

Enhance productivity

Easily manage PowerEdge C6320 servers by automating routine lifecycle management tasks It is possible to manage everything with these tools:

  • OpenManage Essentials
  • Dell’s integrations for BMC BladeLogic
  • Microsoft System Center
  • VMware vCenter

These enable us to streamline operations within our existing IT management environment.

Easing management tasks

The iDRAC with Lifecycle Controller offers a complete set of server management features – including configuration, OS deployment, firmware updates, health monitoring and maintenance – that work regardless of operating system state or the presence of a hypervisor.

Hyperscale environments

Harness the C6320’s hyperscale capabilities for demanding performance and workload-intensive environments.

  • HPC — Implement high-performance, low-latency, massively parallel computing for dense clusters that need high scalability with maximum performance per U.
  • Analytics and big data — Support large-scale data analysis with a maximum compute-density footprint and the ability to tailor server configurations to changing workloads.
  • Cloud — Substantial scalability and density help allow cloud and hosting providers reduce capital expenses and maximize operational performance per sq. ft./per watt.
  • Web 2.0 — Match your server infrastructure to large web-hosting workloads and help eliminate over-provisioning with high scalability and flexible rapid-configuration options.

Thanks to all these features we think this is the best device and configuration for our bank data center.

If you have any question regarding this, don't hesitate and ask to us.

In the next posts we will show you more about our design and other interesting topics related to how to build a data center.

Share

Add new comment

CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
4 + 4 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.