Changes between Version 1 and Version 2 of OpenFlow/DeploymentSummary


Ignore:
Timestamp:
12/15/11 13:12:43 (12 years ago)
Author:
Josh Smift
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • OpenFlow/DeploymentSummary

    v1 v2  
    1515|| Clemson    || HP !ProCurve J8693A 3500yl-48G ||
    1616||            ||                                ||
    17 || GA Tech    || HP !ProCurve                   ||
     17|| GA Tech    || HP !ProCurve 5400              ||
    1818||            ||                                ||
    1919|| Indiana    || HP !ProCurve 3500              ||
    … …  
    3737Sites typically use !FlowVisor to slice their !OpenFlow switches between multiple experiments. Different sites are running their !FlowVisor on a variety of hardware (including in VMs); Stanford currently recommends that a !FlowVisor server should have at least 3 GB of RAM and at least two CPUs. Fast disks also help, as !FlowVisor (as of 0.8.1) can be I/O intensive. These requirements may increase for larger scale deployments.
    3838
    39 It's also advantageous to have a robust control network interface to !FlowVisor. Stanford currently recommends two gigabit interfaces, one to communicate with switches ("upstream") and one to communicate with controllers ("downstream"), if your network design permits. If your upstream and downstream traffic need to share an interface, it might be prudent to have a 10 GB NIC.
     39It's also advantageous to have a robust control network interface to !FlowVisor. Stanford currently recommends two gigabit interfaces, one to communicate with switches ("downstream") and one to communicate with controllers ("upstream"), if your network design permits. If your upstream and downstream traffic need to share an interface, it might be prudent to have a 10 GB NIC.