Smartsockets: solving the connectivity problems in grid computing
Proceedings of the 16th international symposium on High performance distributed computing
HPDC '08 Proceedings of the 17th international symposium on High performance distributed computing
Creating private network overlays for high performance scientific computing
Proceedings of the ACM/IFIP/USENIX 2007 International Conference on Middleware
Creating private network overlays for high performance scientific computing
MIDDLEWARE2007 Proceedings of the 8th ACM/IFIP/USENIX international conference on Middleware
Characterizing user-level network virtualization: performance, overheads and limits
International Journal of Network Management
Optimizing tunneled grid connectivity across firewalls
AusGrid '09 Proceedings of the Seventh Australasian Symposium on Grid Computing and e-Research - Volume 99
A virtual file system interface for computational grids
EUNICE'10 Proceedings of the 16th EUNICE/IFIP WG 6.6 conference on Networked services and applications: engineering, control and management
IP over P2P: enabling self-configuring virtual IP networks for grid computing
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
A virtual network (ViNe) architecture for grid computing
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
On the use of virtualization and service technologies to enable grid-computing
Euro-Par'05 Proceedings of the 11th international Euro-Par conference on Parallel Processing
Maintaining high performance communication under least privilege using dynamic perimeter control
ESORICS'07 Proceedings of the 12th European conference on Research in Computer Security
A survey of task mapping on production grids
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
This paper describes two systems to recover theInternet connectivity impaired by private networks andfirewalls. These devices cause asymmetry in the Internet,making peer-to-peer computing difficult or evenimpossible. The Condor system is one of those that areseverely impaired by the asymmetry. Compared to normalpeer-to-peer computing applications, Condor has stricterrequirements, which are representative to any gridcomputing. To make Condor seamlessly work acrossprivate networks and over firewalls, we designed andimplemented Dynamic Port Forwarding (DPF) andGeneric Connection Brokering (GCB). Both DPF andGCB satisfy the representative requirements. FurthermoreDPF supports dedicated large clusters very well becauseit is simple, efficient, and highly scalable. On the otherhand, GCB perfectly supports non-dedicated or personalclusters because it is independent to private network orfirewall technologies and does not require anyadministrative power to deploy it. In this paper, wedescribe the implementations of DPF and GCB andanalyze them with respect to performance, deployability,security, and scalability.