Jaehyun Hwang

IA-TCP: A rate based incast-avoidance algorithm for TCP in data center networks

In recent years, the data center networks commonly accommodate applications such as MapReduce and web search that inherently shows the incast communication pattern; multiple workers simultaneously transmit TCP data to a single aggregator. In this environment, the TCP performance is significantly degraded in terms of goodput and query completion time, as a result of the severe packet loss at Top of Rack (ToR) switches. The TCP senders aggressively transmit packets causing throughput collapse even though the network pipe size, i.e., bandwidth-delay product, is extremely small. In this paper, we introduce a novel end-to-end congestion control algorithm called IA-TCP that avoids the TCP incast congestion problem effectively. IA-TCP employs the rate-based algorithm at the aggregator node, which controls both the window size of workers and ACK delay. Through extensive NS-2 simulations, we validate that our algorithm is scalable in terms of the number of workers achieving enhanced goodput and zero timeouts.

Packet scheduling for Multipath TCP

Multipath TCP (MPTCP) has been an emerging transport protocol as it can greatly improve application throughput by utilizing multiple network interfaces at the same time, e.g., both of WiFi and 3G/LTE. While MPTCP is generally beneficial for long-lived flows, it shows worse performance than SPTCP that exploits the best path when the flow size is small, e.g., only hundreds of KB. In this case, it would be better to use only the fastest path since the delay is much more important than network bandwidth in such small data delivery. The problem is that the existing default MPTCP packet scheduler may choose a slow path if the congestion window of the fast path is not available, resulting in a long flow completion time. To avoid this problem, we propose a new MPTCP packet scheduler that freezes the slow path temporarily when the delay difference between the slow and fast paths is significant, so that the small amount of data can be transmitted quickly via the fast path. We implement the proposed scheduler into the MPTCP Linux kernel and evaluate on our testbed and compare to the default packet scheduler. Through the experiments, we confirm that the proposed scheme significantly reduces the flow completion time for short flows.

HAVS: hybrid adaptive video streaming for mobile devices

This paper presents a new Scalable Video Codec (SVC)-based hybrid adaptive video streaming scheme, named HAVS, for mobile devices in wireless environments. The proposed approach takes two existing video streaming technologies, viz., progressive download and adaptive streaming, and switches them in a hybrid manner. To this end, HAVS employs the H.264/SVC encoding scheme, where each video chunk is encoded into one base layer and several enhancement layers. Since clients request the base layer every time a video is streamed, HAVS performs progressive download for the base layer and adaptive streaming for the enhancement layers. Through wireless test-bed experiments, it is demonstrated that the proposed scheme can be easily implemented on mobile devices without any server-side modification. This scheme effectively prevents video freeze thereby providing better quality video streaming than the existing non-hybrid streaming technologies.

Deadline and Incast Aware TCP for cloud data center networks

Abstract Nowadays, cloud data centers have become a key resource to provide a plethora of rich online services such as social networking and cloud computing. The cloud data center applications typically follow the Partition/Aggregate traffic pattern based on a tree-like logical topology, where the aggregator node may gather response data from thousands of worker nodes. One of the key challenges for such applications, however, is to meet the soft real-time constraints. In this paper, we introduce the design and implementation of DIATCP, a new transport protocol that is both deadline-aware and incast-avoidable for cloud data center applications. Prior work achieve deadline awareness by host-based or network-based approaches, but they are either imperfect in meeting their deadlines or have weakness in practical deployment. In contrast, DIATCP is deployed only at the aggregator, which directly controls the peers’ sending rate to avoid incast congestion and, more importantly, to meet the application deadline. This is under the key observation that the aggregator knows the bottleneck link status as well as its workers’ information under the Partition/Aggregate traffic pattern. Through detailed ns-3 simulations and real testbed experiments, we show that DIATCP significantly outperforms the previous protocols in the cloud data center environment.

SVC-based Adaptive Video Streaming over Content-Centric Networking

In recent years, HTTP adaptive streaming (HAS) has attracted considerable attention as the state-of-the-art technology for video transport. HAS dynamically adjusts the quality of video streaming according to the network bandwidth and device capability of users. Content-Centric Networking (CCN) has also emerged as a future Internet architecture, which is a novel communication paradigm that integrates content delivery as a native network primitive. These trends have led to the new research issue of harmonizing HAS with the in-network caching provided by CCN routers. Previous research has shown that the performance of HAS can be improved by using the H.264/SVC(scalable video codec) in the in-network caching environments. However, the previous study did not address the misbehavior that causes video freeze when overestimating the available network bandwidth, which is attributable to the high cache hit rate. Thus, we propose a new SVC-based adaptation algorithm that utilizes a drop timer. Our approach aims to stop the downloading of additional enhancement layers that are not cached in the local CCN routers in a timely manner, thereby preventing excessive consumption of the video buffer. We implemented our algorithm in the SVC-HAS client and deployed a testbed that could run Smooth-Streaming, which is one of the most popular HAS solutions, over CCNx, which is the reference implementation of CCN. Our experimental results showed that the proposed scheme (SLA) could avoid video freeze in an effective manner, but without reducing the high hit rate on the CCN routers or affecting the high video quality on the SVC-HAS client.

Fast Coupled Retransmission for Multipath TCP in Data Center Networks

Multipath TCP (MPTCP) is emerging as a new potential candidate that replaces the existing single-path TCP (SPTCP). One applicable area of MPTCP is cloud data center networks, where multiple paths are often available between servers. However, it is observed that MPTCP may not fully leverage the multiple paths and sometimes perform even worse than SPTCP, especially for time-sensitive short flows in data center networks. To address this challenge, we propose a fast coupled retransmission mechanism for MPTCP. The key observation is that one of the paths is likely to be congested if an out-of-order packet exists even after all data packets have been transmitted. In this case, we forward the data packets from the congested path onto the noncongested path and quickly retransmit them. This mechanism effectively avoids network congestion and, hence, helps reduce the overall flow completion time. We implement the proposed scheme in the Linux kernel and evaluate it on our real data center testbed, and the results show that our proposal significantly outperforms the existing schemes.

FaST: Fine-grained and Scalable TCP for Cloud Data Center Networks

With the increasing usage of cloud applications such as MapReduce and social networking, the amount of data traffic in data center networks continues to grow. Moreover, these appli-cations follow the incast traffic pattern, where a large burst of traffic sent by a number of senders, accumulates simultaneously at the shallow-buffered data center switches. This causes severe packet losses. The currently deployed TCP is custom-tailored for the wide-area Internet. This causes cloud applications to suffer long completion times towing to the packet losses, and hence, results in a poor quality of service. An Explicit Congestion Notification (ECN)-based approach is an attractive solution that conservatively adjusts to the network congestion in advance. This legacy approach, however, lacks scalability in terms of the number of flows. In this paper, we reveal the primary cause of the scalability issue through analysis, and propose a new congestion-control algorithm called FaST. FaST employs a novel, virtual congestion window to conduct fine-grained congestion control that results in improved scalability. Fur-thermore, FaST is easy to deploy since it requires only a few software modifications at the server-side. Through ns-3 simulations, we show that FaST improves the scalability of data center networks compared with the existing approaches.

Eliminating bandwidth estimation from adaptive video streaming in wireless networks

Dynamic Adaptive Streaming over HTTP (DASH) is the state-of-the-art technology for video streaming and has been widely deployed in both wired and wireless environments. However, mobile DASH users often suffer from video quality oscillation and even video freeze in wireless environments, which results in poor user experience. This is mainly because most quality adaptation algorithms in DASH rely highly on bandwidth estimation to adjust the video quality while wireless network bandwidth is unstable in nature and changes frequently according to wireless channel contention and condition. To provide stable performance, even during severe bandwidth fluctuation, this paper proposes the Wireless Quality Adaptation (WQUAD) algorithm, which eliminates bandwidth estimation from quality adaptation. Thanks to the Scalable Video Codec (SVC), the proposed scheme always prioritizes to lower layers over higher ones as long as the play-out buffer is not completely filled by the lower layers. As a result, the client always fills the buffer with the base layers first and then the upper enhancement layers sequentially. This horizontal adaptation is straightforward and does not require any bandwidth estimation. Through NS-2 simulations, we show that WQUAD achieves (i) stable performance, keeping the video quality level with respect to the long-term network bandwidth, (ii) effective video freeze prevention, and (iii) high video quality on average. HighlightsShowed wireless users may suffer from video quality oscillation and freeze.Discussed the behavior of the previous quality adaptation algorithm.Proposed a new algorithm that does not rely on bandwidth estimation.The proposed algorithm reduces video quality oscillation during streaming.The proposed algorithm minimizes the number of video freeze events.

SVC-based hybrid video streaming in mobile CE devices

In this paper, we present a new SVC-based hybrid video streaming scheme for mobile CE devices, which performs progressive download for the base quality of video streams and dynamic adaptive streaming for quality enhancement. Simulation results show that the proposed scheme effectively avoids video freeze, providing better average video quality.

Scalable Congestion Control Protocol Based on SDN in Data Center Networks

On-line data center applications render challenging network latency demands to meet their service level requirements. These applications, however, frequently suffer from increased latency due to the packet loss and queueing delay at the network switches. These are mainly as a result of the momentary massive bursts by the Partition/Aggregation application traffic patterns, which causes incast network congestion at the network switches. In this paper, we propose a scalable congestion control protocol, called SCCP. Our scheme effectively limits the data rate of the TCP senders by leveraging the Software Defined Networking (SDN) switches, so that the total utilization does not exceed the bottleneck link capacity. Furthermore, SCCP can be easily deployed to the existing SDN data center switches by extending the OpenFlow specifications. Our Open vSwitch-based prototype experiments and ns-3 simulations show that SCCP is scalable for up to hundreds of concurrent flows traversing through the data center network switch port.