• Publications
  • Influence
BLINC: multilevel traffic classification in the dark
TLDR
This work presents a fundamentally different approach to classifying traffic flows according to the applications that generate them, based on observing and identifying patterns of host behavior at the transport layer and demonstrates the effectiveness of this approach on three real traces. Expand
Towards predictable datacenter networks
TLDR
The case for extending the tenant-provider interface to explicitly account for the network is made, and the design of virtual network abstractions that capture the trade-off between the performance guarantees offered to tenants, their costs and the provider revenue are proposed. Expand
Towards predictable datacenter networks
The shared nature of the network in today's multi-tenant datacenters implies that network performance for tenants can vary significantly. This applies to both production datacenters and cloudExpand
Better never than late: meeting deadlines in datacenter networks
TLDR
Evaluation from a 19-node, two-tier datacenter testbed shows that D3, even without any deadline information, easily outperforms TCP in terms of short flow latency and burst tolerance, and effectively doubles the peak load that thedatacenter network can support. Expand
Transport layer identification of P2P traffic
TLDR
This paper develops a systematic methodology to identify P2P flows at the transport layer, i.e., based on connection patterns of P1P networks, and without relying on packet payload, and believes it is the first method for characterizing P2p traffic using only knowledge of network dynamics rather than any user payload. Expand
Power Law and Exponential Decay of Intercontact Times between Mobile Devices
TLDR
The fundamental properties that determine the basic performance metrics for opportunistic communications are examined, and empirical evidence is presented that the return time of a mobile device to its favorite location site may already explain the observed dichotomy. Expand
Decentralized Task-Aware Scheduling for Data Center Networks
Many data center applications perform rich and complex tasks (e.g., executing a search query or generating a user’s news-feed). From a network perspective, these tasks typically comprise multipleExpand
Is P2P dying or just hiding? [P2P traffic measurement]
TLDR
It is found that, if measured accurately, P2P traffic has never declined; indeed, the proportion of P 2P traffic decrease over time (any change is an increase) in any of the data sources. Expand
Better never than late: meeting deadlines in datacenter networks
The soft real-time nature of large scale web applications in today's datacenters, combined with their distributed workflow, leads to deadlines being associated with the datacenter applicationExpand
Should internet service providers fear peer-assisted content distribution?
TLDR
It is highlighted how simple "locality-aware" P2P delivery solutions can significantly alleviate the induced cost at the ISPs, while providing an overall performance that approximates that of a perfect world-wide caching infrastructure. Expand
...
1
2
3
4
5
...