End-To-End Performance Analysis and Scalability of Tablets

Total Page:16

File Type:pdf, Size:1020Kb

End-To-End Performance Analysis and Scalability of Tablets End-to-End Performance Analysis and Scalability of Tablets M.Tech Stage 1 Report Submitted for the fulfillment of requirements for the degree of Master of Technology by Deepak Jayanth P M Roll No: 10305913 under the guidance of Dr. Deepak.B Phatak a Department of Computer Science and Engineering Indian Institute of Technology, Bombay Mumbai Contents 1 Introduction 1 1.1 Problem Statement . .1 1.2 Performance Analysis . .1 1.2.1 Why Necessary? . .1 1.3 Common Issues in Performance Analysis . .2 1.3.1 Sources of Bottlenecks[1] . .2 1.3.2 Difficulties & Limitations . .3 1.4 Scalability . .3 1.5 Report Outline . .3 2 Analytical Methods of Performance Analysis 4 2.1 Introduction . .4 2.2 CSMA/CD Basic Operation . .4 2.2.1 DCF mode . .4 2.3 A model for Throughput at MAC level [2] . .5 2.3.1 Model construction . .5 2.3.2 Duration for Transmission time . .5 2.3.3 Observations . .6 2.4 Delay analysis at MAC level . .7 2.4.1 Queuing Models . .7 2.4.2 Single server queue model for MAC operation . .8 2.4.3 Delay Analysis [3] . .8 2.5 A model for Capacity of users [4] . .9 2.5.1 Working . .9 2.5.2 Mapping Application throughput from MAC level . .9 3 Software Approaches of Performance Analysis 11 3.1 Benchmarking . 11 3.2 Android Application Profiling and Characterization [5] . 11 3.2.1 Measurements . 12 3.3 Traffic Characterization . 12 3.3.1 Protocol Overheads . 12 3.3.2 Network Performance . 12 3.3.3 Browsing Performance . 12 i 3.4 Performance Measurement Tools . 13 3.4.1 Lack of Effective tools . 13 3.4.2 Representation for multidimentional Network . 13 3.5 Measurement Issues specific to Tablets . 14 3.5.1 Measurement from Android . 14 3.5.2 Unpredictable memory behaviors . 14 3.5.3 Application Vs Browser based . 14 3.5.4 Mapping Problems . 15 4 Scalability at Data Link layer 16 4.1 Bottlenecks at Data link layer . 16 4.1.1 802.11 DCF operation . 16 4.1.2 Problem of Electromagnetic Interferes . 16 4.2 Improving Scalability . 17 4.2.1 Fair Channel Usage . 17 4.2.2 Channel Planning . 17 5 Scalability in Higher Layers 18 5.1 Using IP Multicast . 18 5.1.1 Implementation Methods [9] . 18 5.2 Regulation of Wireless Traffic . 19 5.3 Scalability at Application Level . 19 6 Protocol Customization 20 6.1 MAC Broadcast using Beacon Stuffing[8] . 20 6.1.1 Mechanism . 20 6.2 Device Customization . 21 6.2.1 OpenWrt . 21 6.2.2 Opensource linux wireless drivers . 21 7 Experiments 22 7.1 Overview . 22 7.2 Experimental Setup . 23 7.3 Throughput . 23 8 Conclusions 25 9 Stage 2 Scope 26 ii List of Figures 1.1 Potential sources of bottlenecks during a communication . .2 2.1 Hidden markov model for contention process . .5 2.2 Time taken for transmission under Basic mode . .6 2.3 Time taken for transmission under RTS/CTS . .6 2.4 Throughput vs Transition probability under Basic mode [2] . .6 2.5 Throughput vs Transition probability under RTS/CTS [2] . .6 2.6 Wasted channel time vs number of stations[2] . .7 2.7 Queuing Systems in general . .8 2.8 Birth death process . .8 2.9 Throughput vs Mean dataframe delay [3] . .9 4.1 802.11b/g A.P frequency planning . 17 4.2 802.11a A.P frequency planning . 17 iii Abstract Performance is the most important characteristic of any network, service, application ,etc. And the study of performance analysis is very important, as these study will help in making critical decision on which hardware to use, technologies to implement, how many users will be served, predict the trend of future inputs to system, etc., or make new better technologies. This work discusses performance analysis of Tablets in general and various ways of measurement and characterization of Tablet usage. It discusses various issues related to sources for bottlenecks of connecting a large number of Tablet users in a wireless network. It also discusses ways of mitigation of bottlenecks and improvements to scalability. Chapter 1 Introduction 1.1 Problem Statement The main goal of this project is analysing and characterizing the behaviors of Tablets in terms of I/O operations, network traffic generation, application, traffic generation,amount of user interactions to touchscreen(swiping,clicking), etc., The other goal is to analyse for scalability issues in connecting huge number of simultaneous tablet users. The typical scenarios considered are scaling issues in a densely populated area like classroom supporting 100 plus tablet users(single hop) or it can be scaling issues in tablets connected through campus infrastructure distributed over a wide area using multiple access points,switches, routers inbetween them(multi hop). The performance analysis made should help in identifying the bottlenecks which exist in connecting and distributing data to huge number of tablets simultaneously. 1.2 Performance Analysis 1.2.1 Why Necessary? Consider any infrastructure to support a design scenario, to answer questions such as how exactly things will run, how many maximum numbers of users can be connected at a time, how exactly the network will scale, how reliable a server will run on increased load,etc., performance analysis is required. For example a news site may get millions of request for a cricket page during world cup where it provides up to date coverage and in other days it will be normal. And same goes for a movie review site during a movie release. A typical web application is generated from a complex network of Application Servers, Database servers coupled with mechanisms such as content load balancing, content caching, resource pooling, etc., These are deployed on large number of servers that are clustered together. For a application to be served and function in a timely manner each of the above mentioned mechanisms should work effectively. So it will be inappropriate to leave any of the above mentioned concepts in the design of a better application. So performance analysis is required for planning of a system, network, infrastructure, application design and analysis to support a smooth running of this design in the future. Failure to predict and plan for a future demand may lead to overwhelming of the server with large number of requests and extreme cases shutting down of server. So the performance analysis is one of the important tasks 1 done, which will possibly give a way to avoid such situations. This is performance analysis at a server level. Another example is a institution wireless infrastructure to support wireless connectivity throughout the campus. In this case before designing such infrastructure an performance analysis interms of capacity planning,requirement of maximum user support must be done to efficient deployment of this infrastructure. Poor pre-performance analysis and planning will lead to poor maintenance and cost of this infrastructure. 1.3 Common Issues in Performance Analysis 1.3.1 Sources of Bottlenecks[1] The performance bottleneck can happen at many places other than the network. The following will bring an idea of places where bottleneck arise. The queueing line represents potential sources of bottlenecks. Figure 1.1: Potential sources of bottlenecks during a communication The Figure 1.1 on page 2 shows pictorially the list of potential locations for bottlenecks which can happen during a communication between a client and a server. When a client requests a http connection, as shown in figure it undergoes the intermediate stages. The requests come in terms of packets to the NIC(Network Interface Card) of server and stored on a buffer as incoming request. The network buffer may already have similar kind of request packets obtained from other clients. This is possibly the first source of bottleneck, once this queue gets full the NIC wont be able to process further requests and it may become a source of bottleneck. If the packet gets through the above queue, packet may next need to do task which requires the access of either of CPU , Database, IO. Each of these three (the CPU, Database , and Disk) have themselves queues of their own, and the same rule of NIC queue apply for the other three device queue. The only difference they are called with different names. At cpu level the bottleneck is caused because of different scheduling methods of process/threads queues. At Network level it because of packets arrived at buffers at Network layer. The packet can be even broken down and correlated with buffer size of incoming Frames on data link layer. The bottleneck queues can also be thought from the point of view of application design level, for eg, a chatty protocol, which sends too many short messages between peers. Here the percentage of bandwidth is wasted as overhead. 2 1.3.2 Difficulties & Limitations The sources of bottlenecks can be anything from a network device, or host computer to a bad application design. This complex network of systems as a whole has a lot a components to study about. A single linux operating system has close to 100 tunable TCP and IP parameters[10]. Web administrator usually play with these parameters and may actually increase some perfor- mance which supports their particular configuration. So the way to measure performance and make sense out of the values obtained considering into account these many varying parameters is a very challenging task. And modelling this requires a careful understanding of each of such components. 1.4 Scalability Scalability is one of the important characteristics of any system, which is the ability of the system to perform gracefully under increased load conditions.
Recommended publications
  • ECE 435 – Network Engineering Lecture 15
    ECE 435 { Network Engineering Lecture 15 Vince Weaver http://web.eece.maine.edu/~vweaver [email protected] 25 March 2021 Announcements • Note, this lecture has no video recorded due to problems with UMaine zoom authentication at class start time • HW#6 graded • Don't forget HW#7 • Project Topics due 1 RFC791 Post-it-Note Internet Protocol Datagram RFC791 Source Destination If other than version 4, Version attach form RFC 2460. Type of Service Precedence high reliability Routine Fragmentation Offset high throughput Priority Transport layer use only low delay Immediate Flash more to follow Protocol Flash Override do not fragment CRITIC/ECP this bit intentionally left blank TCP Internetwork Control UDP Network Control Other _________ Identifier _______________________ Length Header Length Data Print legibly and press hard. You are making up to 255 copies. _________________________________________________ _________________________________________________ _________________________________________________ Time to Live Options _________________________________________________ Do not write _________________________________________________ in this space. _________________________________________________ _________________________________________________ Header Checksum _________________________________________________ _________________________________________________ for more info, check IPv4 specifications at http://www.ietf.org/rfc/rfc0791.txt 2 HW#6 Review • Header: 0x000e: 4500 = version(4), header length(5)=20 bytes ToS=0 0x0010: 0038 = packet length (56 bytes) 0x0012: 572a = identifier 0x0014: 4000 = fragment 0100 0000 0000 0000 = do not fragment, offset 0 0x0016: 40 = TTL = 64 0x0017: 06 = Upper layer protocol (6=TCP) 0x0018: 69cc = checksum 0x001a: c0a80833 = source IP 192.168.8.51 0x001e: 826f2e7f = dest IP 130.111.46.127 • Valid IPs 3 ◦ 123.267.67.44 = N ◦ 8.8.8.8 = Y ◦ 3232237569 = 192.168.8.1 ◦ 0xc0a80801 = 192.168.8.1 • A class-A allocation is roughly 224=232 which is 0.39% • 192.168.13.0/24.
    [Show full text]
  • Směrovací Démon BIRD
    Směrovací démon BIRD CZ.NIC z. s. p. o. Ondřej Filip / [email protected] 8. 6. 2010 – IT10 1 Směrování a forwarding ● Router - zařízení připojené k více sítím ● Umí přeposlat „cizí“ zprávu - forwarding ● Cestu pozná podle směrovací (routovací) tabulky ● Sestavování routovací tabulky – routing – Statické – Dynamické ● Interní - uvnitř AS rychlé, důvěřivé, přesné – RIP, OSPF ● Externí (mezi AS, pomalé, filtering, přibližné – pouze BGP 2 Rozdělení směrovacích protokolů AS 2 RIP BGP AS 1 OSPF BGP BGP AS 3 3 static Směrovací démon ● Na Linuxu (a ostatních UNIXech) – uživatelská aplikace mimo jádro, forwarding v jádře ● Obvykle implementuje více směrovacích protokolů ● Směrovací politika - filtrování ● Quagga (Zebra) – Cisco syntax http://www.quagga.net ● OpenBGPd - http://www.openbgpd.org ● GateD – zastaralý, ne volná licence ● BIRD 4 Historie projektu ● Start projektu v roce 1999 ● Seminární projekt – MFF UK Praha ● Projekt uspán ● Drobné probuzeni v letech 2003 a 2006 (CESNET) ● Plně obnoveno na přelomu 2008/2009 v rámci Laboratoří CZ.NIC - http://labs.nic.cz 5 Cíle projektu ● Opensource směrovací démon – alternativa k tehdejšímu démonu Quagga/Zebra (GateD) ● Rychlý a efektivní ● Portabilní, modulární ● Podpora současných směrovacích protokolů ● IPv6 a IPv4 v jednom zdrojovém kódu (dvojí překlad) ● Snadná konfigurace a rekonfigurace (!) ● Silný filtrovací jazyk 6 Vlastnosti ● Portabilní – Linux, FreeBSD, NetBSD, OpenBSD ● Podpora IPv4 i IPv6 ● Static, RIP, OSPF, BGP - Route reflektor, Směrovací server (Route server) ASN32 (ASPLAIN), MD5
    [Show full text]
  • BIRD's Flight from Lisbon to Prague
    BIRD's flight from Lisbon to Prague CZ.NIC Ondrej Filip / [email protected] With help of Wolfgang Hennerbichler May 6, 2009 – RIPE 60 / Prague 1 Features ● GPL implementation of RIP, BGP, OSPF ● BGP – ASN32, MD5, route server, ... ● IPv4, IPv6 ● Highly flexible – Multiple routing tables - RIBs (internal and also synchronization with OS) ● Protocol PIPE - multiple routers, route reflectors ● Powerful configuration & filtering language ● Automatic reconfiguration ● Currently developed by CZ.NIC Labs 2 Design 3 Filters example define myas = 47200; function bgp_out(int peeras) { if ! (source = RTS_BGP ) then return false; if (0,peeras) ~ bgp_community then return false; if (myas,peeras) ~ bgp_community then return true; if (0, myas) ~ bgp_community then return false; return true; } protocol bgp R25192x1 { local as myas; neighbor 194.50.100.13 as 25192; import where bgp_in(25192); export where bgp_out(25192); rs client; } 4 Filters example function avoid_martians() prefix set martians; { martians = [ 169.254.0.0/16+, 172.16.0.0/12+, 192.168.0.0/16+, 10.0.0.0/8+, 224.0.0.0/4+, 240.0.0.0/4+, 0.0.0.0/32-, 0.0.0.0/0{25,32}, 0.0.0.0/0{0,7} ]; # Avoid RFC1918 networks if net ~ martians then return false; return true; } 5 define myas = 47200; function bgp_out(int peeras) { if ! (source = RTS_BGP ) then return false; if (0,peeras) ~ bgp_community then return false; if (myas,peeras) ~ bgp_community then return true; if (0, myas) ~ bgp_community then return false; return true; } protocol bgp R25192x1 { local as myas; neighbor 194.50.100.13 as 25192;
    [Show full text]
  • Kratka Povijest Unixa Od Unicsa Do Freebsda I Linuxa
    Kratka povijest UNIXa Od UNICSa do FreeBSDa i Linuxa 1 Autor: Hrvoje Horvat Naslov: Kratka povijest UNIXa - Od UNICSa do FreeBSDa i Linuxa Licenca i prava korištenja: Svi imaju pravo koristiti, mijenjati, kopirati i štampati (printati) knjigu, prema pravilima GNU GPL licence. Mjesto i godina izdavanja: Osijek, 2017 ISBN: 978-953-59438-0-8 (PDF-online) URL publikacije (PDF): https://www.opensource-osijek.org/knjige/Kratka povijest UNIXa - Od UNICSa do FreeBSDa i Linuxa.pdf ISBN: 978-953- 59438-1- 5 (HTML-online) DokuWiki URL (HTML): https://www.opensource-osijek.org/dokuwiki/wiki:knjige:kratka-povijest- unixa Verzija publikacije : 1.0 Nakalada : Vlastita naklada Uz pravo svakoga na vlastito štampanje (printanje), prema pravilima GNU GPL licence. Ova knjiga je napisana unutar inicijative Open Source Osijek: https://www.opensource-osijek.org Inicijativa Open Source Osijek je član udruge Osijek Software City: http://softwarecity.hr/ UNIX je registrirano i zaštićeno ime od strane tvrtke X/Open (Open Group). FreeBSD i FreeBSD logo su registrirani i zaštićeni od strane FreeBSD Foundation. Imena i logo : Apple, Mac, Macintosh, iOS i Mac OS su registrirani i zaštićeni od strane tvrtke Apple Computer. Ime i logo IBM i AIX su registrirani i zaštićeni od strane tvrtke International Business Machines Corporation. IEEE, POSIX i 802 registrirani i zaštićeni od strane instituta Institute of Electrical and Electronics Engineers. Ime Linux je registrirano i zaštićeno od strane Linusa Torvaldsa u Sjedinjenim Američkim Državama. Ime i logo : Sun, Sun Microsystems, SunOS, Solaris i Java su registrirani i zaštićeni od strane tvrtke Sun Microsystems, sada u vlasništvu tvrtke Oracle. Ime i logo Oracle su u vlasništvu tvrtke Oracle.
    [Show full text]
  • Free, Functional, and Secure
    Free, Functional, and Secure Dante Catalfamo What is OpenBSD? Not Linux? ● Unix-like ● Similar layout ● Similar tools ● POSIX ● NOT the same History ● Originated at AT&T, who were unable to compete in the industry (1970s) ● Given to Universities for educational purposes ● Universities improved the code under the BSD license The License The license: ● Retain the copyright notice ● No warranty ● Don’t use the author's name to promote the product History Cont’d ● After 15 years, the partnership ended ● Almost the entire OS had been rewritten ● The university released the (now mostly BSD licensed) code for free History Cont’d ● AT&T launching Unix System Labories (USL) ● Sued UC Berkeley ● Berkeley fought back, claiming the code didn’t belong to AT&T ● 2 year lawsuit ● AT&T lost, and was found guilty of violating the BSD license History Cont’d ● BSD4.4-Lite released ● The only operating system ever released incomplete ● This became the base of FreeBSD and NetBSD, and eventually OpenBSD and MacOS History Cont’d ● Theo DeRaadt ○ Originally a NetBSD developer ○ Forked NetBSD into OpenBSD after disagreement the direction of the project *fork* Innovations W^X ● Pioneered by the OpenBSD project in 3.3 in 2002, strictly enforced in 6.0 ● Memory can either be write or execute, but but both (XOR) ● Similar to PaX Linux kernel extension (developed later) AnonCVS ● First project with a public source tree featuring version control (1995) ● Now an extremely popular model of software development anonymous anonymous anonymous anonymous anonymous IPSec ● First free operating system to implement an IPSec VPN stack Privilege Separation ● First implemented in 3.2 ● Split a program into processes performing different sub-functions ● Now used in almost all privileged programs in OpenBSD like httpd, bgpd, dhcpd, syslog, sndio, etc.
    [Show full text]
  • Irscp.Phase2.Pdf
    Wresting Control from BGP: Scalable Fine-grained Route Control ¡ ¡ ¡ Patrick Verkaik , Dan Pei , Tom Scholl , Aman Shaikh , ¡ Alex C. Snoeren , and Jacobus E. van der Merwe ¡ University of California, San Diego AT&T Labs Abstract Internet paths can often provide improved performance characteristics [1, 2, 20], suggesting the potential bene- Today's Internet users and applications are placing in- fit of making routing aware of network conditions [11]. creased demands on Internet service providers to deliver Additionally, today's operators are often required to re- fine-grained, flexible route control. To assist network op- strict the any-to-any connectivity model of the Internet erators in addressing this challenge we present an Intelli- to deal with unwanted traffic in the form of DDoS at- gent Route Service Control Point (IRSCP), a route con- tacks. Responses can take the form of black-holing traf- trol architecture that allows a network operator to flexibly fic, redirecting it to “scrubbing complexes”, or even more control routing between the traffic ingresses and egresses sophisticated differentiation of unwanted traffic based on of an ISP's network without modifying existing routers. network intelligence [24]. Finally, in some cases the de- In essence, IRSCP subsumes the control plane of an ISP's fault BGP decision process is simply at odds with provider network by replacing the distributed BGP decision pro- and/or customer goals. For example, using IGP cost as cess of each router in the network with a more flexi- a tie breaker in the decision process can lead to unbal- ble, logically centralized route computation.
    [Show full text]
  • Beyond the Best: Real-Time Non-Invasive Collection of BGP Messages
    Beyond the Best: Real-Time Non-Invasive Collection of BGP Messages Stefano Vissicchio Luca Cittadini Maurizio Pizzonia Luca Vergantini Valerio Mezzapesa Maria Luisa Papagni Dipartimento di Informatica e Automazione, Universita` degli Studi Roma Tre, Rome, Italy fvissicch,ratm,pizzonia,verganti,mezzapes,[email protected] Abstract Despite such a rich set of potential applications, cur- Interdomain routing in the Internet has a large impact rent BGP monitoring practices are quite limited: very of- on network traffic and related economic issues. For this ten, they employ open source BGP daemon implementa- reason, BGP monitoring attracts both academic and in- tions to establish extra BGP peerings with border routers. dustrial research interest. The most common solution for The daemon acts as a route collector, in the sense that collecting BGP routing data is to establish BGP peerings it collects information received via those extra peerings, between border routers and a route collector. dumps it in some format, and stores it for future analy- The downside of this approach is that it only allows ses. For example, this is the approach adopted by Route- us to trace changes of routes selected as best by routers: Views [20] to collect BGP data for the Internet commu- this drawback hinders a wide range of analyses that need nity. Such a practice has two major drawbacks: (i) it is access to all BGP messages received by border routers. only able to collect those routes that have been selected In this paper, we present an effective technique en- as best by the routers that peer with the collector; and abling fast, non-invasive and scalable collection of all (ii) it is only able to collect BGP messages after ingress BGP messages received by border routers.
    [Show full text]
  • Open Source Software for Routing a Look at the Status of Open Source Software for Routing
    APNIC 34 Open Source Software for Routing A look at the status of Open Source Software for Routing Martin Winter OpenSourceRouting.org 1 Who is OpenSourceRouting Quick Overview of what we do and who we are www.opensourcerouting.org ‣ Started late summer 2011 ‣ Focus on improving Quagga ‣ Funded by Companies who like an Open Source Alternative ‣ Non-Profit Organization • Part of ISC (Internet System Consortium) 2 Important reminder: Quagga/Bird/… are not complete routers. They are only the Route Engine. You still need a forwarding plane 3 Why look at Open Source for routing, Why now? Reasons for Open Source Software in Routing 1 Popular Open Source Software Overview of Bird, Quagga, OpenBGPd, Xorp 2 Current Status of Quagga Details on where to consider Quagga, where to avoid it 3 What Open Source Routing is doing What we (OpenSourceRouting.org) do on Quagga 4 How you can help Open Source needs your help. And it will help you. 5 4 Reasons why the time is NOW A few reasons to at least start thinking about Open Source Could be much cheaper. You don’t need all the Money features and all the specialized hardware everywhere. All the current buzzwords. And most of it started SDN, with Open Source – and is designed for it. Does Cloud, .. your vendor provide you with the features for new requirements in time? Your Missing a feature? Need a special feature to distinguish from the competition? You have access Features to the source code. Not just one company is setting the schedule on Support what the fix and when you get the software fix.
    [Show full text]
  • Protecting Routing with RPKI Mark Kosters, ARIN CTO
    Protecting Routing with RPKI Mark Kosters, ARIN CTO @TeamARIN Agenda •Routing, a short •Using ARIN’s RPKI primer components •Operational routing •RPKI Statistics challenges •IRR Status •Do we have a solution? @TeamARIN 1 Core Internet Functions: Routing & DNS •The Internet relies on two critical resources • DNS: Translates domain names to IP addresses and IP addresses to domain names • Routing: Tells us how to get to an IP address •These critical resources are not secure •DNSSEC and RPKI secure these critical resources @TeamARIN 2 Routing – A Primer @TeamARIN 3 Routing Architecture •The Internet uses a two level routing hierarchy: • Interior Gateway (Routing) Protocol - IGP • Exterior Gateway (Routing) Protocol - EGP @TeamARIN 4 Routing Architecture - IGP • Interior Routing Protocols, used by each network to determine how to reach all destinations that lie within the network • Interior Routing protocols maintain the current topology of the network @TeamARIN 5 Routing Architecture - EGP • Exterior Routing Protocol, used to link each component network together into a single whole • Exterior protocols assume that each network is fully interconnected internally @TeamARIN 6 Exterior Routing: BGP •BGP is a large set of bilateral (1:1) routing sessions • A tells B all the destinations (prefixes) that A is capable of reaching • B tells A all the destinations that B is capable of reaching 10.0.0.0/24 192.2.200.0/24 10.1.0.0/16 10.2.0.0/18 A B @TeamARIN 7 Operational Routing Challenges @TeamARIN 8 Focus on Interconnections • Started out as informal
    [Show full text]
  • Leveraging Sonic Functionalities in Disaggregated Network Switches
    LEVERAGING SONIC FUNCTIONALITIES IN DISAGGREGATED NETWORK SWITCHES Ali AlSabeh, Elie Kfoury, Jorge Crichigno, Elias Bou-Harb Presented by: Ali AlSabeh International Conference on Telecommunications and Signal Processing (TSP 2020) Submission ID: #147 OVERVIEW • Introduction • Motivation • Contribution • Background • Experimentation • Discussion • Conclusion and Future Work INTRODUCTION 3 TRADITIONAL NETWORK SWITCHES • Network switches connect multiple computers in a Local Area Network (LAN) by operating on the data link layer • Traditionally, they are closed source running a proprietary Network Operating System (NOS) • Thus, limiting network operators and hindering the process of developing new network technologies WHITE-BOX SWITCHES • White-box switches are new type of forwarding devices • Their hardware is decoupled from the software • Network engineers can install the NOS of their own based on the infrastructure of their network • Thus, providing the flexibility of customizing the network switch, instead of limiting it to the vendor MOTIVATION 6 MOTIVATION • White-box switches has pushed the need for developing open source NOS to accommodate the ever-increasing network technologies • However, open source products are usually less maintained and documented than closed source products CONTRIBUTION 8 CONTRIBUTION • Iterating over several open source Internet Protocol (IP) routing suites and NOSs that are vendor-agnostic • Highlighting the importance of the novel programmable data planes • Reporting the configuration process and the prerequisites
    [Show full text]
  • Moving Away from Openbgpd to Bird?
    MOVING AWAY FROM OPENBGPD TO BIRD? Apricot 2013, Singapore Jimmy Halim [email protected] OPENBGPD IN A FLASH • 3 processes § Session Engine (SE): manages BGP sessions § Route Decision Engine (RDE): holds the BGP tables, takes routing decisions § Parent: enters routes into the kernel, starts SE and RDE • IPv4 and IPv6 in a single configuration • BGP commands § Using ‘bgpctl’ command for both IPv4 and IPv6 WORKING WITH OPENBGPD The positive notes… • Stable with no related bug since upgrade to 4.8 § 4.3 has been bugged with bugs like BGP malformed attributes and IPv6 MD5 password errors • Provide the needed BGP functionality § Transparent AS support § BGP community support for route manipulation § Support prefix filtering • Flexible BGP commands execution and configuration change § Allow short form and help function from UNIX prompt WORKING WITH OPENBGPD The negative one… • No good in handling prefix filter § Especially if we implement prefix filter per neighbor Ø Means more prefix filters to be created and checked Ø Example if we have 100 peers in IX, then there are at least 100 prefix filters need to be created and checked considering if each peer only have 1 prefix § Resulting in a very long routing convergence Ø More peers in IX Ø More routes • Problem with long routing convergence § The routing convergence can take 2 hours, 6 hours, 12 hours, and even 1 day § The best route selection will not be optimal § Resulting in route blackhole!! WORKING WITH OPENBGPD Routing blackhole!! WORKING WITH OPENBGPD Long routing convergence… WORKING
    [Show full text]
  • BGP Route Attestation: Design and Observation Using IPV6
    Dakota State University Beadle Scholar Masters Theses & Doctoral Dissertations Spring 3-1-2017 BGP Route Attestation: Design and Observation Using IPV6 Michael J. Ham Dakota State University Follow this and additional works at: https://scholar.dsu.edu/theses Recommended Citation Ham, Michael J., "BGP Route Attestation: Design and Observation Using IPV6" (2017). Masters Theses & Doctoral Dissertations. 308. https://scholar.dsu.edu/theses/308 This Dissertation is brought to you for free and open access by Beadle Scholar. It has been accepted for inclusion in Masters Theses & Doctoral Dissertations by an authorized administrator of Beadle Scholar. For more information, please contact [email protected]. BGP ROUTE ATTESTATION: DESIGN AND OBSERVATION USING IPV6 HEADERS by Michael J. Ham A Dissertation Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Science in Cyber Security DAKOTA STATE UNIVERSITY March 2017 ii © 2017 by Michael J. Ham ALL RIGHTS RESERVED iii BGP ROUTE ATTESTATION: DESIGN AND OBSERVATION USING IPV6 HEADERS by Michael J. Ham March 2017 Approved: Dr. Wayne E. Pauli, Chair Dr. Kyle L. Cronin, Committee Dr. Mark L. Hawkes, Committee Accepted and Signed: Wayne E. Pauli, Ph.D. Date Accepted and Signed: Kyle L. Cronin, D.Sc. Date Accepted and Signed: Mark L. Hawkes, Ph. D. Date Mark L. Hawkes Date Dean for Graduate Studies and Research Dakota State University iv Abstract This quasi-experimental before-and-after study examined the impacts of using IPv6 extension headers to carry cryptographic Border Gateway Protocol (BGP) route attestation information. Literature was assessed surrounding: the design of BGP, vulnerabilities in BGP, a survey of proposed route attestation solutions, IPv6 extension header design, overhead in cryptography, and factors influencing the adoption of proposed solutions.
    [Show full text]