Junichi Funasaka

A study on primary path switching strategy of SCTP

As a variety of communication devices emerging, we can easily install two or more communication interfaces on a PC or a PDA and make a multi-home environment. To utilize this multi-home environment effectively, SCTP (stream control transmission protocol) has been proposed and standardized. Extending functions of the original SCTP, a strategy which can adapt SCTP to real-time communications has been proposed. However, the typical existing strategy has not enough considered the switching conditions from the viewpoint of transmission delay, so there is room to improve them. In this paper, we clarify the drawbacks of the existing strategy and their influences on the performance. Then, we propose a new strategy of path switching to reduce the delay and to increase the amount of data successfully delivered. The effect of the proposed strategy is discussed and confirmed through experimental evaluations.

A parallel downloading method of coping with variable bandwidth

As a lot of programs and contents such as movie files are being delivered via the Internet, and copies are often stored in distributed servers in order to reduce the load on the original servers, to ease network congestion, and to decrease response time. To retrieve an object file, existing methods simply select one or more servers. Such methods divide a file into equal pieces whose size is determined a priori. This approach is not practical for networks that offer variable bandwidth. In order to more utilize variable bandwidth, we propose an adaptive downloading method We evaluate it by experiments conducted on the Internet. The results show that the new method is effective and that it will become an important network control technology for assurance.

TCP performance analysis on asymmetric networks composed of satellite and terrestrial links

As the Internet users increase, asymmetric networks which provide asymmetric bandwidth or delay for the uplink and downlink have become a great attraction. However asymmetric networks which use both terrestrial and satellite links at the same time have not been adequately investigated. Therefore, this paper proposes a new formula for TCP performance evaluation for the asymmetric networks. Using this evaluation formula, we calculate the throughput of TCP Reno over the asymmetric networks taking slow start into account. The calculation results are compared with the following: (1) the value based on an existing theoretical formula, (2) the outputs of simulation by NS (Network Simulator), and (3) the experimental results using VSAT (Very Small Aperture Terminal) satellite communication system for satellite links and the Internet for terrestrial links. As a result, it is shown that the new formula is more precise than the one already proposed.

Parallel Downloading Using Variable Length Blocks for Proxy Servers

The parallel downloading is one of the technologies which fetch a file at high speed. This technology retrieves each divided piece from a different server in parallel. On the other hand, we have proposed a proxy server which distributes the most recent files. As the technology that combines those, we have proposed a proxy server which gets the most recent files at high speed by using the parallel downloading technology. When this proxy server retrieves pieces, it must buffer them because of unordered arrivals so that it can provide a client with them in order. After that, the pieces are reordered and sent to a client. However, this proxy server has the problem that the buffer might become too big. We proposed in our previous study a substitution download method which alleviate the buffer growth, while it generates redundant traffic in some cases because of asynchronous retrieval of fixed sized blocks. In order to solve the problem, we propose a parallel downloading method for proxy servers using variable length blocks. The block size is determined dynamically according to the network condition so that the occupied buffer space shrinks. In this paper, we compare the proposed parallel downloading using variable length blocks to the existing method using fixed length blocks by simulation experiments. As a result, it is confirmed that our proposal reduces the redundant traffic and the buffer size required for proxy systems compared to the existing method without degrading the download time. This proposal which absorbs the difference in performance among servers is one of the key technologies for network assurance.

Improvements on block size control method for adaptive parallel downloading

Although the traditional downloading programs usually select one server and retrieves a file from the server, it is more practical to select more servers (e.g. mirror servers) and to fetch different parts of a file from the servers in parallel from the point of view of downloading time and fault-tolerance of network service. We have already proposed an adaptive parallel downloading method, which enables us to stabilize and accelerate the downloading time even in the network environments with various bandwidths. Since we found a little room for improvement in the method, this paper describes an improved method. The new method has the following features: (1) independence of the number of mirror servers and (2) introduction of request pipelining into parallel downloading. Based on practical experiments from the viewpoint of downloading speed and stability of downloading time, we confirm that the improved method is more effective than the previous methods. There is a possibility that the improved method become one of the most important network control technologies for network assurance.

Effect of SCTP Multistream Function Applied to Parallel Downloading

Parallel Downloading, which divides a file into many pieces and assigns each piece to one of the servers which store the file, has been proposed and reported to achieve high speed file retrieval from many servers in parallel. The conventional method which adopts TCP as a transport protocol has a problem that its performance deteriorates in the network where packet losses frequently occur at the data-link layer. To address this issue, we have researched a parallel downloading method which uses SCTP instead of TCP as a transport protocol and focuses on its multistream feature. It is believed that the multistream function is a promising technique to alleviate the effect of packet loss problems in ubiquitous networks including wireless networks. We discuss how to realize the effective parallel downloading method using SCTP multistream and evaluate it. Here, we use only one server to simplify the problem. In this paper, on the network with various condition described by delay and loss rate, we conducted simulation experiments using various combination of parameters such as the number of concurrent requests, that of streams, and the division number. As a result, characteristics on parallel downloads using SCTP multistream have been clarified.

PFTPD: an FTP proxy system to assure the freshness of files

As more software is being developed and distributed via the Internet, the number of accesses to file servers, such as FTP servers or WWW servers, is increasing. To reduce concentrated access to the original file server, mirror servers which have the same directories and files as the original server stores have been introduced. However, inconsistency among mirror servers and the original server is often observed because of transfer latency, traffic congestion on the network, and management policy of the mirror servers. Hence, we develop an intermediate FTP proxy server system PFTPD (Proxy FTP Daemon) which guarantees the freshness of files as well as dispersal of the access concentrated on the original FTP server. We found that the proposed system can disperse accesses to the mirror servers with a little overhead. This technology can assure that files are the latest version and adapt to heterogeneous network environments such as the Internet.

A Control Method of Guaranteeing Throughput for TCP Communication Considering Handover over WLAN

In wireless LAN environments, the frequency of handover has been increased by the rapid spread of mobile devices such as smartphones and tablets. In such environments, streaming applications such as video feeds, are quite common and have high bandwidth (throughput) requirements. Here, QoS is an important metric for assurance of network quality. QoS-TCP has been proposed as one of the techniques for guaranteeing the throughput, it controls only the terminal. In this study, we treat TCP-AV as one of the typical QoS-TCPs. However, TCP-AV was originally developed for wired networks. It has difficulty in guaranteeing adequate throughput in a wireless LAN environment because it does not consider handover. Given the frequency of handover in wireless LAN environments, (1) we modify the parameters of TCP-AV, and (2) we propose advertise window size control by an access point (AP). Simulation results show that the method proposed herein, which uses both (1) and (2), can attain the necessary throughput, unlike the original TCP-AV approach.

Timeout Reduction Method for Multistream Segmented Download Using PR-SCTP

As wireless links have spread over the world, we often download large files on lossy networks. However, unnecessary strict order guarantee of TCP with single stream results in performance degradation on lossy networks. Therefore, a segmented download method which uses SCTP multistream has been proposed to address the issue. Since the existing research evaluated the method only with simulation experiments, we conduct intensive experiments with real machines. Furthermore, we propose a timeout reduction method using both PR-SCTP that retransmits the lost packet for a limited time and SCTP multistream. Our approach does not change the timeout policy of SCTP but requests the lost data as a part of application layer protocol. As a result, we show that the proposed method yields at most 10% and 30% higher performance for 5% and 10% packet loss rates than the conventional methods, respectively. Our proposal can constitute one of the assurance technologies which sustain higher throughput even on lossy networks.

SCTP performance improvement for reliable End-to-end communication in ad hoc networks

When ubiquitous networks pervade in future, applications such as file transfer and web browsing will be used also on ad-hoc networks. End-to-end reliable communication is necessary for these applications, and TCP has usually been used as a transport protocol. However, it is known that the performance of fairness and transfer rate decreases when TCP is used on ad hoc networks. Particularly, multi-connection flows of TCP have danger of unfair communication among all flows sharing a wireless link. Then, we pay attention to the multistream mechanism of SCTP to improve unfair communication of TCP multi-connection. SCTP can manage multiple data streams in one association by using the multi-stream mechanism. The performance of reliable transport protocols such as TCP and SCTP easily suffers from frequent route failures and contention on the wireless channel. To improve the problem for mobile ad hoc networks, we propose a scheme which adds the mechanism of Fixed RTO and dynamic delayed SACK to SCTP (shortly, the proposal). And, we evaluated the proposal by a network simulator QualNet.