Reliable Server Pooling

Total Page:16

File Type:pdf, Size:1020Kb

Reliable Server Pooling Reliable Server Pooling Evaluation, Optimization and Extension of a Novel IETF Architecture DISSERTATION to obtain the academic grade doctor rerum naturalium (dr. rer. nat.) in Computer Science Submitted to the Faculty of Economics Institute for Computer Science and Business Information Systems University of Duisburg-Essen by Dipl.-Inform. Thomas Dreibholz born on 29.09.1976 in Bergneustadt, Germany President of the University of Duisburg-Essen: Prof. Dr. Lothar Zechlin Dean of the Faculty of Economics: Prof. Dr. Hendrik Schroder¨ Reviewers: 1. Prof. Dr.-Ing. Erwin P. Rathgeb 2. Prof. Dr. Klaus Echtle Submitted on: November 28, 2006 Date of Disputation: March 07, 2007 ii Selbstandigkeitserkl¨ arung¨ Hiermit erklare¨ ich, die vorliegende Arbeit selbstandig¨ ohne fremde Hilfe verfaßt und nur die angege- bene Literatur und Hilfsmittel verwendet zu haben. Thomas Dreibholz November 28, 2006 iii iv Abstract The Reliable Server Pooling (RSerPool) architecture currently under standardization by the IETF RSerPool Working Group is an overlay network framework to provide server replication and ses- sion failover capabilities to applications using it. These functionalities as such are not new, but their combination into one generic, application-independent framework is. Initial goal of this thesis is to gain insight into the complex RSerPool mechanisms by performing experimental and simulative proof-of-concept tests. The further goals are to systematically validate the RSerPool architecture and its protocols, provide improvements and optimizations where necessary and propose extensions if useful. Based on these evaluations, recommendations to implementers and users of RSerPool should be provided, giving guidelines for the tuning of system parameters and the appropriate configuration of application scenarios. In particular, it is also a goal to transfer insights, optimizations and extensions of the RSerPool protocols from simulation to reality and also to bring the achievements from research into application by supporting and contributing relevant results to the IETF’s ongoing RSerPool standardization process. To achieve the described goals, a prototype implementation as well as a simulation model are designed and realized at first. Using a generic application model and appropriate performance met- rics, the performance of RSerPool systems in failure-free and server failure scenarios is systematically evaluated in order to identify critical parameter ranges and problematic protocol behaviour. Improve- ments developed as result of these performance analyses are evaluated and finally contributed into the standardization process of RSerPool. Keywords: Reliable Server Pooling, Evaluation, Optimization, Extension v vi Acknowledgements This thesis is the result of my work as research associate in the Computer Networking Technology Group of the Institute for Experimental Mathematics at the University of Duisburg-Essen. At this point, I would like to express my acknowledgement to everybody having supported me during my RSerPool research. In particular, I would like to thank my primary advisor, Erwin P. Rathgeb, for his support of my RSerPool research and this thesis, as well as my secondary advisor Klaus Echtle for his thesis review. Furthermore, I would like to express my special thanks to my former colleague Andreas Jungmaier for his great cooperation in the SCTPLIB/SOCKETAPI project (which is the basis of my RSPLIB prototype), as well as Michael Tuxen¨ from the Munster¨ University of Applied Sciences for his support of the RSPLIB project and our IETF standardization contributions. Furthermore, I would like to thank my student assistants Sebastian Rohde (for writing the initial version of the Demonstration System GUI for the RSPLIB prototype) and Jobin Pulinthanath (for application testing, as well as drawing a lot of my hand-written RSerPool sketches using the DIA drawing program). In addition, I would also like to thank the Siemens ICN Information and Communication Networks department for supporting my RSerPool project during its first three years, as well as the Deutsche Forschungsgemeinschaft (DFG) for sponsoring the project for another four years. Finally, I would like to thank my father Ernst Gunter¨ Dreibholz and my mother Annelore Dreib- holz for the years of encouragement and support. vii viii Contents Contents ix 1 Introduction 1 1.1 Motivation ........................................ 1 1.2 Scope and Related Work ................................ 1 1.2.1 Availability ................................... 2 1.2.2 Load Balancing ................................. 2 1.2.3 Fault Tolerance ................................. 3 1.2.4 Reliable Server Pooling ............................ 3 1.3 Goals of this Thesis ................................... 4 1.4 Organization of this Thesis ............................... 5 2 Networking Basics 7 2.1 The OSI and TCP/IP Networking Models ....................... 7 2.2 The Standardization of Network Protocols ....................... 9 2.3 The Network Layer ................................... 9 2.3.1 IP Version 4 ................................... 10 2.3.2 IP Version 6 ................................... 10 2.4 The Transport Layer .................................. 11 2.4.1 UDP ...................................... 11 2.4.2 TCP ....................................... 12 2.4.3 SCTP ...................................... 12 2.4.3.1 Introduction ............................. 12 2.4.3.2 Packet Format ............................ 12 2.4.3.3 Association Establishment ...................... 13 2.4.3.4 Multi-Homing ............................ 15 2.4.3.5 Congestion Control ......................... 15 2.4.3.6 User Data Transport ......................... 15 2.4.3.7 Extensions .............................. 16 2.5 Summary ........................................ 17 3 Reliable Server Pooling 19 3.1 Introduction ....................................... 19 3.2 The Requirements for RSerPool ............................ 20 3.3 The RSerPool Architecture ............................... 21 3.4 A Migration Path for Legacy Applications ....................... 23 ix 3.5 The Protocol Stack ................................... 23 3.6 The Application Scenarios ............................... 24 3.6.1 Telephone Signalling .............................. 25 3.6.2 Session Initiation Protocol (SIP) ........................ 26 3.6.3 IP Flow Information Export (IPFIX) ...................... 27 3.6.4 Load Balancing ................................. 27 3.6.5 Real-Time Distributed Computing ....................... 28 3.6.5.1 Requirements ............................ 29 3.6.5.2 Applicability of RSerPool ...................... 29 3.6.6 Mobility Support for SCTP ........................... 29 3.6.7 Other Application Scenarios .......................... 30 3.7 The RSerPool Components ............................... 31 3.7.1 Registrar .................................... 31 3.7.1.1 Announces .............................. 32 3.7.1.2 Pool Management .......................... 32 3.7.1.3 Pool Monitoring ........................... 33 3.7.1.4 Server Selection and Failure Reporting ............... 35 3.7.1.5 Handlespace Audit and Handling of PR Failures .......... 35 3.7.2 Pool Element .................................. 35 3.7.3 Pool User .................................... 36 3.8 The Protocol Design .................................. 37 3.9 The Aggregate Server Access Protocol ......................... 38 3.9.1 Overview .................................... 38 3.9.2 Pool Element Functionality .......................... 39 3.9.2.1 Registration and Reregistration ................... 39 3.9.2.2 Monitoring .............................. 42 3.9.2.3 Deregistration ............................ 42 3.9.3 Pool User Functionality ............................ 43 3.9.3.1 Handle Resolution .......................... 43 3.9.3.2 Failure Report ............................ 44 3.9.4 Automatic Configuration Functionality .................... 44 3.9.5 Session Layer Functionality .......................... 45 3.9.5.1 Data Channel and Control Channel ................. 45 3.9.5.2 ASAP Cookies ............................ 46 3.9.5.3 ASAP Business Cards ........................ 48 3.10 The Endpoint Handlespace Redundancy Protocol ................... 49 3.10.1 Overview .................................... 49 3.10.2 Automatic Configuration ............................ 49 3.10.2.1 The ENRP Presence Message .................... 49 3.10.2.2 Dynamic and Static Peer Table Configuration ........... 51 3.10.2.3 Maintaining Connections to Peer Registrars ............ 52 3.10.2.4 Obtaining the Peer Table from Peer Registrars ........... 52 3.10.3 Registrar Initialization ............................. 54 3.10.4 Handle Update ................................. 55 3.10.5 Handlespace Audit and Synchronization .................... 56 3.10.6 Takeover Procedure ............................... 57 3.11 The Pool Member Selection Policies .......................... 59 x 3.11.1 Basics ...................................... 60 3.11.2 Non-Adaptive Policies ............................. 60 3.11.2.1 Round Robin and Weighted Round Robin ............. 60 3.11.2.2 Random and Weighted Random ................... 61 3.11.3 Adaptive Policies ................................ 61 3.11.3.1 Least Used .............................. 61 3.11.3.2 Priority Least Used ......................... 61 3.12 The Mechanisms for Service Reliability and Availability ............... 62 3.12.1 Failure Model .................................
Recommended publications
  • Overview and Evaluation of the Server Redundancy and Session Failover Mechanisms in the Reliable Server Pooling Framework∗
    International Journal On Advances in Internet Technology, vol 2 no 1, year 2009, http://www.iariajournals.org/internet_technology/ 1 Overview and Evaluation of the Server Redundancy and Session Failover Mechanisms in the Reliable Server Pooling Framework∗ Thomas Dreibholz, Erwin P. Rathgeb University of Duisburg-Essen, Institute for Experimental Mathematics Ellernstrasse 29, 45326 Essen, Germany fdreibh,[email protected] Abstract cations world, where availability is ensured by redundant links and devices [2] – there had not been any generic, stan- The number of availability-critical Internet applications dardized approaches for the availability of Internet-based is steadily increasing. To support the development and op- services. Each application had to realize its own solution eration of such applications, the IETF has recently defined a and therefore to re-invent the wheel. This deficiency – once new standard for a common server redundancy and session more arisen for the availability of SS7 (Signalling System failover framework: Reliable Server Pooling (RSerPool). No. 7) services over IP networks – had been the initial mo- The basic ideas of the RSerPool framework are not entirely tivation for the IETF RSerPool WG to define the Reliable new, but their combination into a single, resource-efficient Server Pooling (RSerPool) framework. The basic ideas of and unified architecture is. Service availability achieved by RSerPool are not entirely new (see [3, 4]), but their combi- the redundancy of servers directly leads to the issues of load nation into one application-independent framework is. distribution and load balancing, which are both important Server redundancy [5] leads to the issues of load distri- for the performance of RSerPool systems.
    [Show full text]
  • SCTP and Reliable Server Pooling a Practical Exercise
    Dr. Thomas Dreibholz Computer Networking Technology Group Institute for Experimental Mathematics Ellernstraße 29, 45326 Essen, Germany T +49-201-183-7637 v +49-201-183-7673 k [email protected] June 8, 2010 Z http://www.iem.uni-due.de/∼dreibh SCTP and Reliable Server Pooling A Practical Exercise SAMPLE SOLUTION Abstract The intention of this exercise is to obtain basic knowledge of the SCTP protocol [Ste07] and the configuration and application of Reliable Server Pooling (RSerPool) [LOTD08, Dre07, DR08b]. This exercise covers SCTP association setup, data transport, association teardown and multi-homing as well as setting up an RSerPool scenario with the protocols ASAP [SXST08a], ENRP [XSS+08] and example applications. Contents 1 Lab Setup and Preparations2 2 The SCTP Protocol2 2.1 Preparations..........................................2 2.2 Association Setup and Data Transmission..........................3 2.3 Multi-Homing.........................................6 2.4 Association Teardown.....................................6 3 The Reliable Server Pooling Framework7 3.1 Setting Up a Basic Scenario.................................7 3.2 Keeping an Overview of the Scenario............................8 3.3 Automatic Configuration...................................9 3.4 Pool Management....................................... 11 3.5 Server Selection........................................ 17 3.6 Session Layer......................................... 18 3.7 ENRP Handlespace Synchronization............................. 19 4 Application of Reliable
    [Show full text]
  • Introducing TCP &
    Introducing TCP & UDP Internet Transport Layers (C) Herbert Haas 2005/03/11 TCP/IP Protocol Suite BootP Application SMTP HTTP FTP Telnet DNS DHCP SNMP etc. Presentation ( M I M E ) Session Routing Protocols OSPF BGP TCP UDP Transport (User Datagram RIP EGP (Transmission Control Protocol) Protocol) IP (Internet Protocol) Network ICMP ARP RARP Link IP Transmission over ATM IEEE 802.2 X.25 FR PPP Physical RFC 1483 RFC 1042 RFC 1356 RFC 1490 RFC 1661 2005/03/11 2 TCP/UDP and OSI Transport Layer 4 Layer 4 Protocol = TCP (Connection-Oriented) Layer 4 Protocol = UDP (Connectionless) IP Host A IP Host B TCP/UDP Connection (Transport-Pipe) 4 4 M M Router 1 Router 2 2005/03/11 3 TCP Facts (1) Connection-oriented layer 4 protocol Carried within IP payload Provides a reliable end-to-end transport of data between computer processes of different end systems Error detection and recovery Sequencing and duplication detection Flow control RFC 793 (C) Herbert Haas 2005/03/11 4 TCP Facts (2) Application's data is regarded as continuous byte stream TCP ensures a reliable transmission of segments of this byte stream Handover to Layer 7 at "Ports" OSI-Speak: Service Access Point (C) Herbert Haas 2005/03/11 5 Port Numbers Using port numbers TCP (and UDP) can multiplex different layer-7 byte streams Server processes are identified by Well known port numbers : 0..1023 Controlled by IANA Client processes use arbitrary port numbers >1023 Better >8000 because of registered ports (C) Herbert Haas 2005/03/11 6 Registered Ports For proprietary server
    [Show full text]
  • The Software Modeling and Implementation of Reliable Server Pooling and RSPLIB
    The Software Modeling and Implementation of Reliable Server Pooling and RSPLIB Xing Zhouy, Thomas Dreibholz∗, Martin Becke∗, Jobin Pulinthanath∗, Erwin P. Rathgeb∗ and Wencai Duy yHainan University, College of Information Science and Technology Renmin Avenue 58, 570228 Haikou, Hainan, China fzhouxing,[email protected] ∗University of Duisburg-Essen, Institute for Experimental Mathematics Ellernstrasse 29, 45326 Essen, Germany fdreibh,becke,jp,[email protected] Abstract—With the growing complexity of software applica- tions, there is an increasing demand for solutions to distribute workload into server pools. Grid Computing provides powerful – but also highly complex – mechanisms to realize such tasks. Also, there is a steadily growing number of downtime-critical applica- tions, requiring redundant servers to ensure service availability in case of component failures. To cope with the demand for server redundancy and service availability, the IETF has recently standardized the lightweight Reliable Server Pooling (RSerPool) framework, which is a com- mon architecture for server pool and session management. In this paper, we first introduce the concept of RSerPool and then present the modeling thoughts of RSPLIB and the underlying general groupware design. Based on RSPLIB, we will illustratively show how to easily develop applications on top of RSerPool. We will also offer an application evaluation example for a proof- Figure 1. A Multi-Homed SCTP Association of-concept setup to distribute ray-tracing computation workload into a compute pool.1 Keywords: Reliable Server Pooling, RSPLIB, Service Avail- ability, Software Modeling, Implementation this means the limitation is to a single administrative domain and only takes care of pool and session management – but I.
    [Show full text]
  • Reliable Server Pooling Based Workload Offloading with Mobile
    Reliable Server Pooling Based Workload Offloading with Mobile Edge Computing: A Proof-of-Concept∗ Thomas Dreibholza, Somnath Mazumdarb Abstract In recent times, mobile broadband devices have become almost ubiquitous. However, battery-powered devices (such as smartphones), have limitations on energy consumption, computation power and storage space. Cloud computing and Mobile Edge Computing (MEC) can provide low- latency compute and storage services at the vicinity of the user, MEC in particular due to the upcoming 5G networks. However, the complexity lies in how to simply and efficiently realise MEC services, with the auxiliary public (multi-)cloud resources? In this paper, we propose a proof-of-concept for us- ing Reliable Server Pooling (RSerPool) as a light-weight layer of managing resource pools and handling application sessions with these pools. Our ap- proach is simple, efficient, has low overhead and is available as open source. Here, we demonstrate the usefulness of our approach by measuring in a test setup, with a 4G testbed connected to MEC and public multi-cloud resources. aSimula Metropolitan Centre for Digital Engineering c/o OsloMet { storbyuniversitetet Pilestredet 52, 0167 Oslo, Norway. [email protected] bDepartment of Digitalization, Copenhagen Business School, Howitzvej 60, 2000 Frederiksberg, Denmark. [email protected] ∗ This work has been supported by the European Community through the 5G- VINNI project (grant no. 815279) within the H2020-ICT-17-2017 research and inno- vation program. Parts of this work have also been funded by the Research Council of Norway under project number 208798/F50. The authors would like to thank Ann Edith Wulff Armitstead for her comments.
    [Show full text]
  • Flow Routing Rk  G O Multi-Streaming N W I M
    Towards the Future Internet A Survey of Challenges and Solutions in Research and Standardization 60 60 24 29 Internet Protocol Version 6 (IPv6) C Stream Control Transmission Protocol (SCTP) C RF RF Features of IPv6 Features of the SCTP Transport Protocol: p ‒ Simple header for efficient processing ‒ Reliable u t e e h n S ‒ Sufficient number of addresses -> better distribution for efficient routing ‒ Connection-oriented t o is ti a n TP er C n o S e P i ‒ Flow Label for easy flow identification -> Quality of Service ‒ Message-oriented t g C t T ex f a n o i ‒ Built-in security: IPsec is mandatory c Security: o s m s o A Challenges for Upper Layers: fr ‒ 4-way handshake on v6 ti IP ra o ig t ‒ Support for IPv6 and IPv4 (dual-stack) -> Migration Path M v4 ‒ Immune against flooding attacks IP ‒ Handling of multiple addresses -> Multi-Homing Path Redundancy by Multi-Homing g ‒ Handling of prefix changes -> Mobility n ‒ 1 association, n paths i m Deployment: ‒ Still works if up to n-1 paths break o H - i t ‒ Supported by all major operating systems ‒ Path monitoring by heartbeats l u ‒ Usable via tunnelling over IPv4, some providers already provide it directly! ‒ Fine-granular configuration M ss re og ‒ Per-association congestion control Pr n i Flow Routing rk g o Multi-Streaming n W i m Key Assumption of Classical Internet Routing: ‒ Up to 65,536 streams via single association a e r t ‒ Router memory is scarce and expensive => Stateless Packet Routing ‒ Useful e.g.
    [Show full text]
  • Revisiting the IETF Multipath Extensions on Transport Layer
    Revisiting the IETF Multipath Extensions on Transport Layer DISSERTATION to obtain the academic grade doctor rerum naturalium (dr. rer. nat.) in Computer Science Submitted to the Faculty of Economics Institute for Computer Science and Business Information Systems University of Duisburg-Essen by Martin Becke born on 08.08.1977 in Ankum, Germany President of the University of Duisburg-Essen: Prof. Dr. Ulrich Radtke Dean of the Faculty of Economics: Prof. Dr. Volker Clausen Reviewers: 1. Prof. Dr.-Ing. Erwin P. Rathgeb 2. Prof. Dr. Klaus Echtle Submitted on: September 11, 2014 Date of Disputation: November 12, 2014 ii Selbst¨andigkeitserkl¨arung Hiermit erkl¨are ich, die vorliegende Arbeit selbst¨andig ohne fremde Hilfe verfaßt und nur die angegebene Literatur und Hilfsmittel verwendet zu haben. Weiter erkl¨are ich, dass diesem Promotionsverfahren keine Promotionsversuche in diesem Fach oder in einem anderen Fach vorausgegangen sind und dass die eingereichte Arbeit oder wesentliche Teile derselben in keinem anderen Verfahren zur Erlangung eines akademischen Grades vorgelegt worden sind. Martin Becke September 11, 2014 iii iv Abstract Load sharing on the transport layer of the OSI reference model is an important topic in the IETF standardization. This approach is also supported by the industry to optimize the use of the resources in a network like the Internet. After many trials, two basic sets of mechanisms and functionalities on the transport layer have been proposed by the IETF to achieve load sharing. These basic sets extend the protocol mechanisms that were originally designed for the use in singlepath dominated networks and represent only a first step to introduce a real end-to-end multipath transfer on the Internet.
    [Show full text]
  • On Robustness and Countermeasures of Reliable Server Pooling Systems Against Denial of Service Attacks
    On Robustness and Countermeasures of Reliable Server Pooling Systems Against Denial of Service Attacks Thomas Dreibholz1,ErwinP.Rathgeb1, and Xing Zhou2 1 University of Duisburg-Essen Institute for Experimental Mathematics Ellernstrae 29, D-45326 Essen, Germany Tel.: +49 201 183-7637, Fax: +49 201 183-7673 [email protected] 2 Hainan University College of Information Science and Technology Renmin Road 58, 570228 Haikou, Hainan, China Tel.: +86 898 6625-0584, Fax: +86 898 6618-7056 [email protected] Abstract. The Reliable Server Pooling (RSerPool) architecture is the IETF’s novel approach to standardize a light-weight protocol framework for server redundancy and session failover. It combines ideas from dif- ferent research areas into a single, resource-efficient and unified archi- tecture. While there have already been a number of contributions on the performance of RSerPool for its main tasks – pool management, load distribution and failover handling – the robustness of the protocol framework has not yet been evaluated against intentional attacks. The first goal of this paper is to provide a robustness analysis. In particular, we would like to outline the attack bandwidth necessary for a significant impact on the service. Furthermore, we present and evalu- ate our countermeasure approach to significantly reduce the impact of attacks. Keywords: Reliable Server Pooling, Attacks, Denial of Service, Robust- ness, Countermeasures. 1 Introduction and Scope The Reliable Server Pooling (RSerPool) architecture [1] is a generic, application- independent framework for server pool [2] and session management, based on the Stream Control Transmission Protocol (SCTP) [3]. While there have already been a number of publications on the performance of RSerPool for load bal- ancing [4] and server failure handling [5], there has not yet been any research Parts of this work have been funded by the German Research Foundation (Deutsche Forschungsgemeinschaft).
    [Show full text]
  • Introducing TCP &
    Introducing TCP & UDP Internet Transport Layers (C) Herbert Haas 2005/03/11 1 TCP/IP Protocol Suite BootP Application SMTP HTTP FTP Telnet DNS DHCP SNMP etc. Presentation ( M I M E ) Session Routing Protocols OSPF BGP TCP UDP Transport (User Datagram RIP EGP (Transmission Control Protocol) Protocol) IP (Internet Protocol) Network ICMP ARP RARP Link IP Transmission over ATM IEEE 802.2 X.25 FR PPP Physical RFC 1483 RFC 1042 RFC 1356 RFC 1490 RFC 1661 2005/03/11 2 2 TCP/UDP and OSI Transport Layer 4 Layer 4 Protocol = TCP (Connection-Oriented) Layer 4 Protocol = UDP (Connectionless) IP Host A IP Host B TCP/UDP Connection (Transport-Pipe) 4 4 M M Router 1 Router 2 2005/03/11 3 3 TCP Facts (1) Connection-oriented layer 4 protocol Carried within IP payload Provides a reliable end-to-end transport of data between computer processes of different end systems Error detection and recovery Sequencing and duplication detection Flow control RFC 793 (C) Herbert Haas 2005/03/11 4 In this Chapter we talk about TCP. TCP is a connection-oriented layer 4 protocol and only works between the hosts. It synchronizes (connects) the hosts with each other via the “3-Way-Handshake” before the real transmission begins. After this a reliable end-to-end transmission is established. TCP was standardized in September 1981 in RFC 793. (Remember: IP was standardized in September 1981 too, RFC 791). TCP is always used with IP and it also protects the IP packet as its checksum spans over (almost) the whole IP packet.
    [Show full text]
  • Dcc Rest.Indd
    The Stream Control Transmission Protocol (SCTP) and its Potential for Amateur Radio Eduardo Gonzalez Dr. Stan McClellan Dr. Wuxu Peng FlexRadio Systems Texas State Univeristy Texas State University 4616 W. Howard Lane Suite 1-150 601 University Drive 601 University Drive Austin, TX USA 78728 San Marcos, TX USA 78666 San Marcos, TX USA 78666 Email: ed.gonzalez@flex-radio.com Email: [email protected] Email: [email protected] Abstract The Stream Control Transmission Protocol (SCTP) provides several unique features not found in TCP (Transmission Control Protocol) and in UDP (User Datagram Protocol) while maintaining the useful aspects of both. This paper provides an introduction to SCTP and several features that should be very attractive to the Amateur Radio Community. These features are particularly useful with the rise of Software Defined Radio which use network interfaces to provide both control and data streams. The main features explored are multi-homing, multi-streaming and the ability to select reliable vs unreliable and ordered vs non ordered delivery of application messages. I. Introduction SCTP is a relatively young transport protocol which grew out of several projects/research that were trying to replace traditional telephone signaling methods with packet based protocols. TCP was found to have some reliability and timing weaknesses that were unacceptable to the industry, hence a new protocol was drafted. It became an IETF Proposed Standard in 2000 and was published as RFC 2960 [1] which was later replaced by RFC 4960 [2] in 2007. It is now mandatory to use SCTP for SS7-based PSTN signaling over IP as well as in the IETF Reliable Server Pooling framework [3].
    [Show full text]
  • Reliable Server Pooling
    University of Duisburg-Essen, Institute for Experimental Mathematics SCTP and RSerPool: Architectures and Protocols for the Future Internet Dr. Thomas Dreibholz University of Duisburg-Essen, Germany [email protected] http://www.iem.uni-due.de/~dreibh Prof. Xing Zhou Hainan University, China [email protected] University of Duisburg-Essen, Institute for Experimental Mathematics SCTP and RSerPool: 下一代互联网架构标准及其协议 Dr. Thomas Dreibholz University of Duisburg-Essen, Germany [email protected] http://www.iem.uni-due.de/~dreibh Prof. Xing Zhou Hainan University, China [email protected] Table of Contents IETF and Standardization Background Next Generation Internet Architecture Stream Control Transmission Protocol (SCTP) Reliable Server Pooling (RSerPool) − Overview − The RSPLIB Implementation − Demo Presentation − How to Apply RSerPool for Applications Adapting existing applications and developing new applications Examples: client and server Summary Thomas Dreibholz's Reliable Server Pooling Page http://tdrwww.iem.uni-due.de/dreibholz/rserpool/ SCTP and RSerPool – Architectures and Protocols for the Future Internet Thomas Dreibholz P. 3 IETF and Standardization Background (1) Internet Engineering Task Force (IETF): − International organization for the standardization of Internet protocols − All standards are released by IETF as RFC (“Request for Comments”) − Examples: TCP, UDP, IP, ... − Organized into different Working Groups (WG), e.g. Transport Services (TSVWG) (responsible for SCTP) Signalling Transport (SigTran) Reliable Server Pooling (RSerPool) ... New protocols from the IETF: − Stream Control Transmission Protocol (SCTP, RFC 4960): Advanced transport protocol (i.e. next generation of TCP) Important contributors: − Randall Stewart (Cisco Systems, U.S.A.) − Michael Tüxen (Münster University of Applied Sciences, Germany) − Andreas Jungmaier, Thomas Dreibholz (Uni.
    [Show full text]