GIT-CERCS-06-01
Zhongtang Cai, Vibhore Kumar, Karsten Schwan,
IQ-Paths: Self-regulating Data Streams across Network Overlays
Overlay networks have been shown useful for improving the delivery of
network and processing resources to applications, in part due to their ability
to use alternate or parallel network paths and computational resources. This
paper presents IQ-Paths, a set of techniques and their middleware realization
that implement self-regulating data streams for data-intensive distributed
applications. Self-regulation is based on (1) the dynamic and continuous
assessment of the quality of each overlay path, (2) the use of online network
monitoring and statistical analyses that provide probabilistic guarantees about
available path bandwidth, loss rate, and RTT, and (3) a packet routing and
scheduling algorithm that dynamically schedules data packets to different
overlay paths in accordance with their available bandwidths. Additional aspects
of IQ-Paths are its predictive statistical bandwidth guarantees and the
fact that packet scheduling across different overlay paths is governed
by application-level specifications of stream utility. An example is to send
control data across links that offer strong guarantees for future bandwidth
vs. mapping other data across less guaranteed paths. Experimental results
presented in this paper use IQ-Paths to better handle the different kinds of
data produced by (1) distributed multimedia applications with desired QoS
guarantees and (2) data-driven or interactive high performance codes with
user-defined utility requirements.