Abstract

The Transmission Control Protocol (TCP) plays a critical role in the Internet as it is the protocol used for data transport by most Internet services and applications. With rapid advances in broadband Internet and mobile/wireless networks, current TCPs are increasingly becoming the bottleneck. This work tackles this challenge by developing a novel TCP design called Fast Launch with Agile congeStion Handling (FLASH) that not only achieves improved performance for long TCP flows but also significantly raises the performance of short to medium TCP flows that are far more common in the Internet. We evaluated its long-term and short-term performance over a wide range of network environments, using two emulation platforms (Pantheon and DummyNet) as well as Internet experiments. Compared to two of the leading TCP designs deployed in the Internet, i.e., Cubic and BBR, FLASH consistently achieved higher long-term and short-term bandwidth efficiency. For example, in trace-driven emulated experiments using Poisson traffic with a mean flow size of 1 MB operating at medium link utilization of 27%, FLASH can reduce the flow completion time (FCT) by 36% (vs. Cubic) and 26% (vs. BBR), with mean packet queueing delay of 11.7 ms compared to 3.4 ms (Cubic) and 8.8 ms (BBR). It also maintained good fairness with itself and is competitive against Cubic and BBR sharing the same bottleneck. In addition, FLASH has been tested in two real-world Internet environments. In the cloud-to-cloud experiment, it reduced FCT by 52.9% (vs. Cubic) and 46.6% (vs. BBR), while in the cloud-to-client experiment, it reduced FCT by 31.3% (vs. Cubic) and 12.7% (vs. BBR). FLASH is entirely sender-based and is compatible with current TCP receivers, thereby readily deployable in current Internet servers.

Highlights

  • There is a renewed interest in the Transmission Control Protocol (TCP) [1,2,3,4,5,6,7,8,9,10,11,12] in recent years

  • This motivated us to re-examine current TCP designs on their performance in transferring short to medium flows which are common in many Internet applications that downloads data, e.g., mobile app download/update, image download, or video segment transfer in MPEG-DASH streaming [17]

  • We developed a novel TCP design called Fast Launch with Agile congeStion Handling (FLASH) based on a new approach (i.e., Fast Launch) to rapidly ramp up TCP’s transmission rate at the beginning of a flow while avoiding congestion loss, and a new congestion control algorithm (i.e., Agile congeStion Handler) to achieve high bandwidth utilization while maintaining friendliness towards competing flows

Read more

Summary

INTRODUCTION

There is a renewed interest in the Transmission Control Protocol (TCP) [1,2,3,4,5,6,7,8,9,10,11,12] in recent years. At 100 Mbps, a 1 MB flow could theoretically be transferred in just 80 ms and its performance is dominated by TCP’s startup behavior This motivated us to re-examine current TCP designs on their performance in transferring short to medium flows which are common in many Internet applications that downloads data, e.g., mobile app download/update, image download, or video segment transfer in MPEG-DASH streaming [17]. Our investigations uncovered three performance issues with current leading TCP designs - Cubic [14] and BBR [7], in terms of bandwidth efficiency, friendliness, and congestion loss To tackle these limitations, we developed a novel TCP design called Fast Launch with Agile congeStion Handling (FLASH) based on a new approach (i.e., Fast Launch) to rapidly ramp up TCP’s transmission rate at the beginning of a flow while avoiding congestion loss, and a new congestion control algorithm (i.e., Agile congeStion Handler) to achieve high bandwidth utilization while maintaining friendliness towards competing flows. The rest of the paper is organized as follows: Section II reviews some previous related work; Section III re-examines current TCP designs to demonstrate their limitations; Section IV presents the architecture and design goals of FLASH; Section V presents details of FLASH’s Fast Launch module; Section VI presents details of FLASH’s Agile congeStion Handler; Section VII evaluates FLASH’s performance and compares it to existing TCP designs; Section VIII summarizes the paper and outlines some future work

RELATED WORKS
TCP CONGESTION CONTROL RE-EXAMINED
INITIAL BANDWIDTH PROBING
FAIRNESS AND FRIENDLINESS
CONGESTION LOSS
TCP-FLASH
ARCHITECTURE AND DESIGN GOALS
LINUX IMPLEMENTATION
FAST-LAUNCH
CWND-COMPENSATED BANDWIDTH ESTIMATOR
CWND BOOST
PRACTICAL ISSUES
AGILE CONGESTION HANDLING
PLUGGABLE BANDWIDTH PROBE
CONGESTION HANDLER
CWND LIMITER
PERFORMANCE EVALUATION
BANDWIDTH EFFICIENCY
FLOW COMPLETION TIME
C8: Toronto
CLOUD-TO-CLOUD INTERNET EXPERIMENT
CLOUD-TO-USER INTERNET EXPERIMENT
Findings
VIII. SUMMARY AND FUTURE WORK
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call