Ilpo Järvinen

Harsh RED: Improving RED for Limited Aggregate Traffic

A bottleneck router typically resides close to the edge of the network where the aggregate traffic is often limited to a single or a few users only. With such limited aggregate traffic Random Early Detection (RED) on the bottleneck router is not able to properly respond to TCP slow start that causes rapid increase in load of the bottleneck. This results in falling back to tail-drop behavior or, at worst, triggers the RED maximum threshold cutter that drops all packets causing undesired break for all traffic that is passing through the bottleneck. We explain how TCP slow start, ACK clock and RED algorithm interact in such a situation, and propose Harsh RED (HRED) to properly address slow start in time. We perform a simulation study to compare HRED behavior to that of FIFO and RED with recommended parameters. We show that HRED avoids tail-drop and the maximum threshold cutter, has smaller queues, and provides less bursty drop distribution.

Experimental evaluation of alternative congestion control algorithms for Constrained Application Protocol (CoAP)

The wide range of IoT applications creates a demand for various types of communication. While both types of communication, unreliable and reliable, are important, it is crucial to extend scalable congestion control in the Internet to cover IoT communication also. Constrained Application Protocol (CoAP), a web transfer protocol for constrained devices and networks proposed by Internet Engineering Task Force (IETF), has optional reliability based on retransmission timeout (RTO) together with exponential RTO backoff to implement a simple basic congestion control mechanism. While the CoAP basic congestion control is simple, it is relatively conservative and potentially inefficient. Hence, there is a need for a more efficient congestion control alternative and CoCoA has been proposed as an option. In this paper we experimentally evaluate the efficiency and scalability of alternative congestion control algorithms for CoAP, including CoCoA and two TCP-based mechanisms. Our results show that while all the alternatives are scalable, they are more aggressive than the default congestion control mechanism of CoAP resulting in more efficient operation particularly at higher congestion level(s).

Combating Packet Reordering in Vertical Handoff Using Cross-Layer Notifications to TCP

In this paper we propose an enhancement to the TCP sender algorithm to combat packet reordering that may occur due to a vertical handoff from a slow to a fast access link. The proposed algorithm employs cross-layer notifications regarding the changes in the access link characteristics. Our algorithm avoids unnecessary retransmissions by dynamically changing the dupthresh value according to the bandwidth and delay of the old and new access links involved in the handoff. In addition it uses DSACK information to infer that there are no congestion-related losses and selects proper values for cwnd and ssthresh after the handoff. Simulation results show that the unnecessary retransmissions caused by packet reordering in a vertical handoff can be effectively minimized over a wide range of bandwidth and delay ratios of the access links. In addition, our algorithm is effective in reducing the congestion-related packet losses due to a decrease in bandwidth-delay product (BDP) after a handoff.

Evaluating CoDel, PIE, and HRED AQM techniques with load transients

In the past, networks have been mainly optimized for good system throughput but recently achieving low delay has also gained notable traction. Active Queue Management (AQM) has long been recognized necessary for operating Internet routers with shorter standing queues but only limited deployment has occurred. The recent interest in AQM has resulted in new AQM proposals. In this paper we evaluate CoDel (Controlled Delay) and PIE (Proportional Integral controller Enhanced), both being new AQM proposals, and compare the performance against an aggressive RED (Random Early Detection) variant called HRED (Harsh RED). We focus on AQM behavior during load transients typically occurring at the network edge with the common traffic types of today such as Web transactions. We discover that CoDel auto-tuning does not scale well with the load. With the high-end delays experienced, HRED is better than PIE and CoDel when more than a few simultaneous flows share the bottleneck.

Is CoAP Congestion Safe

A huge number of Internet of Things (IoT) devices are expected to be connected to the Internet in the near future. The Constrained Application Protocol (CoAP) has been increasingly deployed for wide-area IoT communication. It is crucial to understand how the specified CoAP congestion control algorithms perform. We seek an answer to this question by performing an extensive evaluation of the existing IETF CoAP Congestion Control proposals. We find that they fail to address congestion properly, particularly in the presence of a bufferbloated bottleneck buffer. We also fix the problem with a few simple modifications and demonstrate their effectiveness.

Gazing Beyond Horizon: The Predict Active Queue Management for Controlling Load Transients

Active Queue Management (AQM) is used by routers to limit queue build-up by reacting pro-actively to incipient congestion and modern AQM algorithms attempt to keep queuing latency at a low level. However, current AQM algorithms have hard time to correctly manage load transients, resulting in delay spikes. They suffer from a horizon problem that prevents a router from acquiring a complete picture of the traffic load by simply measuring its current queuing, because the distribution of the load over the end-to-end path keeps some of the load inducing packets out of the view of the router. Inability to know the RTTs of the flows going through the router makes it also challenging for the AQM algorithm to use a proper measurement interval for load calculation as it does not know what that interval should be. In this paper we tackle the horizon problem and RTT uncertainty that together complicate accurate load estimation for AQM algorithms. We propose a new AQM algorithm that not only determines the current load but also predicts the load into the near future. The prediction enables our algorithm to respond timely even to rapid load transients such as those due to TCP Slow Start. Our simulation results show that our algorithm achieves low queuing, whereas PIE and CoDel-based AQM algorithms struggle to limit queuing with small RTTs and with large RTTs react too early lengthening flow completion times.

SLACP: A Novel Link-Layer Protocol for Wireless WANs

In this paper, we discuss the design details of a TCP/IP- friendly link-layer protocol with novel design to improve TCP performance on network paths involving a Wireless Wide-Area Network (WWAN) link. Our link layer protocol utilizes a new hybrid error-recovery mechanism combining Automatic Repeat reQuests (ARQ) and Forward Error Correction (FEC) in a way that keeps the residual packet-error rate at a very low level and minimizes the additional delay due to ARQ at the same time. The protocol supports several QoS classes by implementing several logical channels over a single physical link and by allowing each channel to be configured with QoS parameters and error control strategy that best suit to the IP traffic directed over the channel. We analyze the error recovery behavior of the protocol using packet traces from our experiments with the real implementation of the protocol and evaluate the protocol performance and the effectiveness of the QoS support in emulated wireless link environments. The results show significant TCP performance improvement and that the QoS approach supports delay-sensitive traffic effectively.