Changes between Version 5 and Version 6 of Internal/Operations


Ignore:
Timestamp:
Jun 13, 2006, 8:21:16 PM (18 years ago)
Author:
faiyaz
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • Internal/Operations

    v5 v6  
    88The ORBIT Testbed consists of 416 nodes, 26 Servers, and 45 ethernet switches.  Nodes, servers, and switches are grouped into ORBIT resources which are referred to as "grid", and "sb1" through "sb8".  The grid consists of the 400 nodes, a server that acts as a console, and 30 switches that are seperated into control, data, and CM networks.  The eight sandboxes consist of 2 nodes, a console server, and a switch which aggregates all three networks.
    99
    10 Each resource is connected to the ORBIT back-end via the control, data, and CM networks.  Each network of each resource is a seperate subnet following RFC 1981 and all route back to a Cisco PIX 515E Firewall apliance. Each subnet is connected to individual DMZ interfaces on the firewall and, therefore, has a set of security rules governing all traffic to and from each network.  The firewall is configured to allow traffic from the external login machines to the ORBIT resources.  Traffic generated on one resource will be blocked at the firewall if it's destination is in another resource.  The purpose of this is the logical seperation of control planes for each resource;  one user's experiment cannot interfere with that of another.
     10Each resource is connected to the ORBIT back-end via the control, data, and CM networks.  Each network of each resource is a seperate subnet following RFC 1981 and all route back to a Cisco PIX 515E Firewall apliance. Each subnet is connected to individual DMZ interfaces on the firewall and, therefore, has a set of security rules governing all traffic to and from each network.  The firewall is configured to allow traffic from the external login machines to the ORBIT resources.  Traffic generated on one resource will be blocked at the firewall if it's destination is in another resource.  The purpose of this is the logical seperation of control planes for each resource;  one user's experiment cannot interfere with that of another.  Similarly, since all resources share the same backend, the firewall will not allow an experimenter direct access to any of the backend servers or its services.  Manipulation of services during an experiment can either be done via the nodehandler or through webservices.
    1111
    1212The Control network is comprised of 10 discrete switches on the grid, and shared switches on the sandboxes.  Its purpose is to allow remote access to the nodes via ssh as well as provide a back channel for nodehandler communication and measurments collection.