Default TCP Research Articles

UNDERSTANDING THE TRADE-OFF IN TCP'S CUBIC WINDOWS CONGESTION: A COMPREHENSIVE ANALYSIS

This study investigates the difficulties of the CUBIC TCP algorithm, focusing on the trade-off between efficiency and fairness in window congestion control. The CUBIC approach, which was devised to optimize high-bandwidth and long-distance networks, is currently widely used as the default TCP congestion control algorithm in Linux and other systems. Our work investigates the dynamics of CUBIC's window expansion, specifically the interaction between the cubic function and the most recent congestion event. We look at how this interplay impacts the distribution of window widths, throughput, round-trip time (RTT), loss rate, and queue size under different network configurations. Keywords: TCP CUBIC, Window Congestion, Efficiency-Fairness Trade-Off, TCP’s Cubic Function.

Incast Mitigation in a Data Center Storage Cluster Through a Dynamic Fair-Share Buffer Policy

Incast is a phenomenon when multiple devices interact with only one device at a given time. Multiple storage senders overflow either the switch buffer or the single-receiver memory. This pattern causes all concurrent-senders to stop and wait for buffer/memory availability, and leads to a packet loss and retransmission-resulting in a huge latency. We present a software-defined technique tackling the many-to-one communication pattern-Incast-in a data center storage cluster. Our proposed method decouples the default TCP windowing mechanism from all storage servers, and delegates it to the software-defined storage controller. The proposed method removes the TCP saw-tooth behavior, provides a global flow awareness, and implements the dynamic fair-share buffer policy for end-to-end I/O path. It considers all I/O stages (applications, device drivers, NICs, switches/routers, file systems, I/O schedulers, main memory, and physical disks) while achieving the maximum I/O throughput. The policy, which is part of the proposed method, allocates fair-share bandwidth utilization for all storage servers. Priority queues are incorporated to handle the most important data flows. In addition, the proposed method provides better manageability and maintainability compared with traditional storage networks, where data plane and control plane reside in the same device.

Stability and performance analysis of Compound TCP with the Exponential-RED and the Drop-Tail queue policies

Abstract The analysis of transport protocols, along with queue management policies, forms an important aspect of performance evaluation for the Internet. In this article, we study Compound TCP (C-TCP), the default TCP in the Windows operating system, along with the Exponential-RED (E-RED) queue policy and the widely used Drop-Tail queue policy. We consider queuing delay, link utilization and the stability of the queue size as the performance metrics. We first analyse the stability properties of a nonlinear model for C-TCP coupled with the E-RED queue policy. We observe that this system, in its current form, may be difficult to stabilize as the feedback delay gets large. Further, using an exogenous and non-dimensional parameter, we show that the system loses local stability via a Hopf bifurcation, which gives rise to limit cycles. Employing Poincaré normal forms and the center manifold theory, we outline an analytical framework to characterize the type of the Hopf bifurcation and to determine the orbital stability of the emerging limit cycles. Numerical examples, stability charts and bifurcation diagrams complement our analysis. We also conduct packet-level simulations, with E-RED and Drop-Tail, in small and large buffer-sizing regimes. With large buffers, E-RED can achieve small queue sizes compared with Drop-Tail. However, it is difficult to maintain the stability of the E-RED policy as the feedback delay gets large. On the other hand, with small buffers, E-RED offers no clear advantage over the simple Drop-Tail queue policy. Our work can offer insights for the design of queue policies that can ensure low latency and stability.

A new Linux based TCP congestion control mechanism for long distance high bandwidth sustainable smart cities

People, systems, and things in the cities generate large amount of data which is considered to be the most scalable asset of any smart city. Linux users are rapidly increased in last few years, and many large multinational organizations are deploying long distance high bandwidth (LDHB) cloud networks for centralizing the data from various smart cities on a central location. TCP is responsible for reliable communication of data in these cloud networks. For reliability communication among various smart cities, a number of TCP congestion control mechanisms have been developed in the past. TCP Compound, TCP Fusion, and TCP CUBIC are the default TCP congestion control mechanisms for Microsoft Windows, Sun Solaris, and Linux operating systems respectively. The response function of TCP CUBIC is higher than the response function of Standard TCP, which is a trademark congestion control mechanism. As a result, TCP CUBIC does not behave friendly with Standard TCP in LDHB cloud networks. The Congestion Window (cwnd) reduction and growth of TCP CUBIC is very aggressive, which causes high packet loss rate and unfair share of available link bandwidth among competing flows from various smart cities. The aim of this research is to design a new TCP congestion control mechanism for Linux operating system to achieve maximum performance in LDHB cloud networks being used by smart cities. In this paper, congestion control module for slow start (CCM-SS) is designed by increasing the lower boundary limit of cwnd size in slow start phase of communication. Congestion control module for loss event (CCM-LE) is designed by increasing the cwnd reduction rate at each packet loss event and finally Advance Response Function for TCP CUBIC (ARFC) is proposed to design a new congestion control mechanism for Linux operating system. NS-2 is used to compare the performance of TCP CUBIC* with TCP CUBIC in short distance high bandwidth (SDHB) and long distance high bandwidth (LDHB) cloud networks. Results show that TCP CUBIC* has outperformed in LDHB networks, at least by a factor of 18% as compared to TCP CUBIC.

Stability and Performance Analysis of Compound TCP With REM and Drop-Tail Queue Management

We study Compound TCP (C-TCP), the default TCP in the Windows operating system, with Random Exponential Marking (REM) and the widely used Drop-Tail queue policy. The performance metrics we consider are stability of the queue size, queuing delay, link utilization, and packet loss. We analyze the following models: 1) a nonlinear model for C-TCP with Drop-Tail and small buffers; 2) a stochastic variant of REM along with C-TCP; and 3) the original REM proposal as a continuous-time nonlinear model with delayed feedback. We derive conditions to ensure local stability and show that variations in system parameters can induce a Hopf bifurcation, which would lead to the emergence of limit cycles. With Drop-Tail and small buffers, the Compound parameters and the buffer size both play a key role in ensuring stability. In the stochastic variant of REM, larger thresholds for marking/dropping packets can destabilize the system. With the original REM proposal, using Poincare normal forms and the center manifold analysis, we also characterize the type of the Hopf bifurcation. This enables us to analytically verify the stability of the bifurcating limit cycles. Packet-level simulations corroborate some of the analysis. Some design guidelines to ensure stability and low latency are outlined.

TCP Congestion Avoidance Algorithm Identification

The Internet has recently been evolving from homogeneous congestion control to heterogeneous congestion control. Several years ago, Internet traffic was mainly controlled by the traditional RENO, whereas it is now controlled by multiple different TCP algorithms, such as RENO, CUBIC, and Compound TCP (CTCP). However, there is very little work on the performance and stability study of the Internet with heterogeneous congestion control. One fundamental reason is the lack of the deployment information of different TCP algorithms. In this paper, we first propose a tool called TCP Congestion Avoidance Algorithm Identification (CAAI) for actively identifying the TCP algorithm of a remote Web server. CAAI can identify all default TCP algorithms (e.g., RENO, CUBIC, and CTCP) and most non-default TCP algorithms of major operating system families. We then present the CAAI measurement result of about 30 000 Web servers. We found that only 3.31%-14.47% of the Web servers still use RENO, 46.92% of the Web servers use BIC or CUBIC, and 14.5%-25.66% of the Web servers use CTCP. Our measurement results show a strong sign that the majority of TCP flows are not controlled by RENO anymore, and a strong sign that the Internet congestion control has changed from homogeneous to heterogeneous.

An Experimental Investigation of the Impact of Mobile IPv6 Handover on Transport Protocols

Mobile IPv6 is the current IETF standard for end host mobility management in the Internet. In order to provide a transparent location management, Mobile IPv6 operates in two different modes. In the first mode, mobile node incoming packets are tunneled to the node current location via the home network. In the second mode, traffic is exchanged directly between the mobile node and its communicating peers. In this paper, we evaluate the performance of these two modes on a real test bed. We first analytically model the Mobile IPv6 handover. Afterwards, we empirically assess its impact on transport protocols in general and more specifically on TCP CUBIC, the default TCP implementation in the current Linux kernel since version 2.6.19. We demonstrate that this TCP implementation induces high handover latency as it was not designed to be deployed in a dynamic environment.

Dual decomposition method for optimal and fair congestion control in Ad Hoc networks: Algorithm, implementation and evaluation

For the design of a more efficient congestion control algorithm to optimize the resource allocation in Ad Hoc networks, the notion of the link’s interference set is introduced to represent the contention relationship among flows in Ad Hoc networks, which is the fundamental difference from the contention relationship among flows in Internet. And the congestion control problem is formulated as a nonlinear optimization problem with the capacity constraint of the link’s interference set. Then, based on the dual decomposition method, this problem is decomposed into many subproblems, which can be solved independently in a parallel fashion at each source/link, and builds the Dual Decomposition based Optimal and Fair Congestion Control framework ( D 2 OFC 2 ) to coordinate their source allocation among flows. Considering the synchronous implementation is difficult in realistic environment, the asynchronous implementation of D 2 OFC 2 is presented. To deploy the practical protocol of D 2 OFC 2 , three deployment techniques are proposed: Queue Size Estimation method (QSE), Neighbor Set Approximation method (NSA), and Extensive HELLO message-based Piggybacking (EHP).The MATLAB-based simulation results illustrate that D 2 OFC 2 can approach the globally optimal solution even in asynchronous environment. The NS2-based simulation results demonstrate that D 2 OFC 2 outperforms default TCP and ATCP to achieve an efficient and fair resource allocation in Ad Hoc networks under three scenarios, including chain topology, grid topology, and random topology.

Enhancing TCP for networks with guaranteed bandwidth services

In this paper, we consider TCP based applications with bandwidth guarantees , but can also benefit from any additional best-effort service offered by the network. Through simulations we show that default TCP cannot offer such applications the ideal throughput – the aggregate throughput of the reserved bandwidth and the best effort bandwidth. To illustrate the reasons for its degraded performance, we study TCP’s congestion window adaptation and self-clocking mechanisms in detail. Based on the insights obtained from the study, we propose an adaptation of TCP called GTCP that employs changes to TCP’s congestion control mechanisms to provide applications the optimal aggregate throughput of best-effort and reserved bandwidth. Compared with TCP, GTCP does not involve any additional implementation overhead, and only the sender need to be changed (the receiver remains to be a default TCP implementation). Through simulations and experiments over the Internet we show that GTCP achieves significantly better performance than default TCP in the target environment.

Optimal congestion control algorithm for ad hoc networks: Penalty function-based approach

In this paper, based on the inherent characteristic of the contention relation between flows in ad hoc networks, we introduce the notion of the link’s interference set, extend the utility maximization problem representing congestion control in wireline networks to ad hoc networks, apply the penalty function approach and the subgradient method to solve this problem, and propose the congestion control algorithm Penalty function-based Optical Congestion Control (POCC) which is implemented in NS2 simulator. Specifically, each link transmits periodically the information on its congestion state to its interference set; the session at each source adjusts the transmission rate based on the optimal tradeoff between the utility value and the congestion level which the interference set of the links that this session goes though suffers from. MATLAB-based simulation results showed that POCC can approach the globally optimal solution. The NS2-based simulation results showed that POCC outperforms default TCP and ATCP to achieve efficient and fair resource allocation in ad hoc networks.

ATP: a reliable transport protocol for ad hoc networks

Existing works have approached the problem of reliable transport in ad hoc networks by proposing mechanisms to improve TCP's performance over such networks, In this paper, we show through detailed arguments and simulations that several of the design elements in TCP are fundamentally inappropriate for the unique characteristics of ad hoc networks. Given that ad hoc networks are typically stand-alone, we approach the problem of reliable transport from the perspective that it is justifiable to develop an entirely new transport protocol that is not a variant of TCP. Toward this end, we present a new reliable transport layer protocol for ad hoc networks called ATP (ad hoc transport protocol). We show through ns2-based simulations that ATP outperforms default TCP as well as TCP-ELFN and ATCP.

Optimizing transport protocol parameters for large scale PC cluster and its evaluation with parallel data mining

Recently, PC clusters have come to be studied intensively for large scale parallel computers of the next generation. ATM technology is a strong candidate as a de facto standard of high speed communication networks. Therefore, an ATM-connected PC cluster is a promising platform from the cost/performance point of view, as a future high performance computing environment. Data intensive applications, such as data mining and ad hoc query processing in databases, are considered very important for massively parallel processors, as well as for conventional scientific calculations. Thus, investigating the feasibility of applications on an ATM-connected PC cluster is meaningful. In this paper, an ATM-connected PC cluster consisting of 100 PCs is reported, and characteristics of a transport layer protocol for the PC cluster are evaluated. Point-to-point communication performance is measured and discussed, when a TCP window size parameter is changed. Parallel data mining is implemented and evaluated on the cluster. Retransmission caused by cell loss at the ATM switch is analyzed, and parameters of retransmission mechanism suitable for parallel processing on the large scale PC cluster are clarified. Default TCP protocol cannot provide good performance, since a lot of collisions happen during all-to-all multicasting executed on the large scale PC cluster. Using TCP parameters with the proposed optimization, performance improvement is achieved for parallel data mining on 100 PCs.