From francis.moore at rawflow.com Tue Nov 1 09:29:57 2005 From: francis.moore at rawflow.com (Frank Moore) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Testing scalability on a P2P network In-Reply-To: <4065dd020510311304w5bd3de37p225e499684fbce94@mail.gmail.com> References: <43661853.7000609@rawflow.com> <4065dd020510311304w5bd3de37p225e499684fbce94@mail.gmail.com> Message-ID: <43673595.1050105@rawflow.com> Faried Nawaz wrote: >On 10/31/05, Frank Moore wrote: > > >>Can anyone give me some pointers on scalability testing a P2P network? >>In theory if a P2P network works with N users, it should be possible to >>scale up to larger numbers i.e. N*10, N*100 etc.... >>But is there any way of actually testing this and if so how have other >>people done it? >> >> > >Will a simulation help? There's p2psim -- http://pdos.csail.mit.edu/p2psim/ > > It may help, if this is what other people do in a similar situation. Greg mentioned testing it in the wild, but I'm not sure that's practical for us. I know Bram Cohen did it for BitTorrent, but our dynamics are slightly different. We have a p2p streaming app and it's going to be difficult to find something that enough people are going to want to listen to or watch that will create a network of a million users or more, which is the kind of number that we want to test against. If it was that easy to do, I guess we'd all be in the content delivery business ;-) Cheers, Frank. From sg266 at cornell.edu Tue Nov 1 12:46:15 2005 From: sg266 at cornell.edu (Saikat Guha) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Testing scalability on a P2P network In-Reply-To: <43673595.1050105@rawflow.com> References: <43661853.7000609@rawflow.com> <4065dd020510311304w5bd3de37p225e499684fbce94@mail.gmail.com> <43673595.1050105@rawflow.com> Message-ID: <1130849175.23725.11.camel@himalaya.cs.cornell.edu> On Tue, 2005-11-01 at 09:29 +0000, Frank Moore wrote: > We have a p2p streaming app and it's going to be difficult to find > something that enough > people are going to want to listen to or watch that will create a > network of a million users or more, FWIW, http://www.di.fm/ (and Internet Radio, in general) is always looking for streaming b/w; maybe not a million, but 25K odd is a start, eh? -- Saikat (who is not a Canadian) -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: This is a digitally signed message part Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051101/01b13452/attachment.pgp From ian at locut.us Tue Nov 1 15:07:25 2005 From: ian at locut.us (Ian Clarke) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Testing scalability on a P2P network In-Reply-To: <43673595.1050105@rawflow.com> References: <43661853.7000609@rawflow.com> <4065dd020510311304w5bd3de37p225e499684fbce94@mail.gmail.com> <43673595.1050105@rawflow.com> Message-ID: On 1 Nov 2005, at 09:29, Frank Moore wrote: > It may help, if this is what other people do in a similar situation. > Greg mentioned testing it in the wild, but I'm not sure that's > practical for us. > I know Bram Cohen did it for BitTorrent, but our dynamics are > slightly different. > We have a p2p streaming app and it's going to be difficult to find > something that enough > people are going to want to listen to or watch that will create a > network of a million users or more, > which is the kind of number that we want to test against. > If it was that easy to do, I guess we'd all be in the content > delivery business ;-) Unfortunately testing it in the wild is the only way to be sure as it is virtually impossible to have a 100% accurate simulation of the Internet and user behaviour. While this is true to some extent of most software, it is particularly true of P2P applications. The next best thing to actual beta deployment is probably to use some kind of WAN simulator (try Googling for it) like "The Cloud". I typically use an iterative approach to simulation and testing, starting with a very basic simulation of the network, which may not even take into account things like network latency, and then increasing the realism of the simulation in progressive stages, culminating in a beta deployment of the system. Even if your beta deployment doesn't reach a large number of users, you can at least use it to verify the accuracy of your simulations for a smaller number of users. The number of stages you want to employ depends on the time and resources available to your project. Ian. From eugen at leitl.org Tue Nov 1 16:46:14 2005 From: eugen at leitl.org (Eugen Leitl) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] [hoche@compsci.bristol.ac.uk: [alife] CfP: Symposium on Network Analysis in Natural Sciences and Engineering] Message-ID: <20051101164614.GU2249@leitl.org> ----- Forwarded message from S Hoche ----- From: S Hoche Date: Tue, 01 Nov 2005 11:05:53 +0000 To: alife-announce@lists.idyll.org Subject: [alife] CfP: Symposium on Network Analysis in Natural Sciences and Engineering User-Agent: Mozilla Thunderbird 1.0.6-1.4.1 (X11/20050719) Network Analysis in Natural Sciences and Engineering April 4th-6th 2006 http://irgroup.cs.uni-magdeburg.de/NAiNE/ part of AISB'06: Adaptation in Artificial and Biological Systems University of Bristol, Bristol, England Aims & Scope: ------------- Network analysis and modelling address a wide spectrum of techniques for studying domains consisting of individuals that are linked together into complex networks. Networks refer to artificial and natural systems like communication networks, social networks and biological networks. Both graph theory and techniques recently developed for the analysis of networks provide a substantial background for studying complex network structures and dynamics in artificial and biological systems. They allow us to answer questions in common to these networks like aspects of adaptability, error and attack tolerance, complexity, community structures, and propagation patterns. One of the key features of natural networks is their ability to adapt to changing environments while maintaining an appropriate pattern of behaviour. Such adaptive capacity can be found in a whole range of natural networks, from gene-protein interaction networks within individual cells, through physiological systems, to ecosystems. The aim of this symposium is to provide a forum to bring together scientists from biology, computer science and related disciplines who are concerned with theoretical and applied network analysis and modelling in the context of diverse disciplines, the adaptability in natural networks, and its application to artificial networks. Furthermore, the symposium will serve as a forum for interdisciplinary discussions to promote a comprehensive view of the state of the art in this field and to identify emerging and future research issues. The topics of interest include, but are not limited to: * Adaptability in biological networks * Mining and learning from network data * Prediction of structural network properties * Network dynamics * Network topology * Community structures * Topological motifs * Pattern mining * Social network analysis in human and animal societies * Genetic regulatory and protein interaction networks * Robustness issues * Complexity issues * Model selection and sampling in networks * Massive graph mining * Information networks * Applications of network theory Important Dates: ---------------- December 15th 2005: Submission of tutorial proposals January 15th 2006: Submission of papers February 5th 2006: Notification of decision February 20th 2006: Camera ready papers Submissions: ------------ Submissions in form of an extended abstract of at least 1500 word (2 pages) should be submitted until January 15th 2006. More detailed information can be found at the symposia web site: http://irgroup.cs.uni-magdeburg.de/NAiNE/ Sponsor: -------- EU Project NiSIS (Nature-inspired Smart Information Systems) http://www.nisis.de/ _______________________________________________ alife-announce mailing list alife-announce@lists.idyll.org http://lists.idyll.org/listinfo/alife-announce ----- End forwarded message ----- -- Eugen* Leitl leitl ______________________________________________________________ ICBM: 48.07100, 11.36820 http://www.leitl.org 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051101/fd57b94c/attachment.pgp From bwong at cs.cornell.edu Tue Nov 1 16:53:35 2005 From: bwong at cs.cornell.edu (Bernard Wong) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Closestnode.com announcement Message-ID: <43679D8F.4060206@cs.cornell.edu> We are writing to announce closestnode.com, a free, non-commercial service that we have recently deployed for directing clients to servers and peers that are close to them. Closestnode.com can be used for mapping clients to the closest DHT node, for selecting a nearby mirror a user can download content from, or for finding the closest game server a user can connect to in multiplayer online games. The service is very simple to use: You register a unique application name with us on the web (e.g. mycoolapp) and either link our library into your application or run our standalone program along your server nodes. Once that is done, any node performing a DNS lookup for mycoolapp.closestnode.com will receive the IP address of the the closest (lowest latency) node to itself that is currently running the mycoolapp application. Closestnode.com can be used to implement a generic anycast service. It supports hosts behind firewalls and NAT boxes. One caveat is that a cold lookup with unprimed caches may take up to a few hundred ms, so this system is best suited for distributed systems where sessions last a few seconds or more. More information, code and demos are available at http://www.closestnode.com. The system is an offshoot of recent research at Cornell university, described in the following paper: http://www.cs.cornell.edu/people/egs/papers/meridian-sigcomm05.pdf Don't hesitate to contact us if you have any questions. Best, Bernard, Alex, Gun. From alenlpeacock at gmail.com Tue Nov 1 17:09:11 2005 From: alenlpeacock at gmail.com (Alen Peacock) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Testing scalability on a P2P network In-Reply-To: References: <43661853.7000609@rawflow.com> <4065dd020510311304w5bd3de37p225e499684fbce94@mail.gmail.com> <43673595.1050105@rawflow.com> Message-ID: On 11/1/05, Ian Clarke wrote: > > The next best thing to actual beta deployment is probably to use some > kind of WAN simulator (try Googling for it) like "The Cloud". Just to mention a couple of others: - planetlab at http://www.planet-lab.org/ - emulab at http://www.emulab.net/ The only restrictions seem to be that they have to approve you for use, and approval usually entails being associated with one of the sponsoring institutions. If you or one of your team members are not affiliated, you may be able to find someone at one of the institutions that would be interested in participating in your project. Emulab does accept some open source projects not affiliated with universities. OpenDHT, ePost, DHash, and Tapestry are several prominent projects that are currently listed as using these testbeds. Alen From ap at hamachi.cc Tue Nov 1 19:40:46 2005 From: ap at hamachi.cc (Alex Pankratov) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Closestnode.com announcement In-Reply-To: <43679D8F.4060206@cs.cornell.edu> References: <43679D8F.4060206@cs.cornell.edu> Message-ID: <4367C4BE.1070000@hamachi.cc> Very elegant. Looks a bit like a variation of Akamai services. Alex From mfreed at cs.nyu.edu Tue Nov 1 21:18:49 2005 From: mfreed at cs.nyu.edu (Michael J. Freedman) Date: Sat Dec 9 22:13:03 2006 Subject: [p2p-hackers] Non-transitivity in DHTs In-Reply-To: References: Message-ID: On Mon, 31 Oct 2005, Alen Peacock wrote: > I'm not sure if I fully understand inconsistent roots as it relates > to kademlia. Parallel iterative queries seem to make the probability > of getting an incorrect response from inconsistent roots less severe, > and implementing some sort of simple consensus easy -- since S directs > the routing process, it can compare the results from multiple > responses. Does that seem right, or am I overlooking something more > essential to the problem? Well, the basic problem arises in how you are using Kademlia at the higher-level: write-once vs. semi-mutable, single vs. replicated. The Coral implementation (with its "sloppy" DHT structure) uses the routing structure to attempt to find *the* closest responsible node. If this one node is invisible to you due to non-transitivity, this is exactly where the problem arises. One solution when using iterative lookup is to try one-hop forwarding, i.e., if you can't connect directly, try to get some of the node's immediate neighbors in the ID space to forward your request and the subsequent response. (Invisible nodes along a lookup path also degrade *performance* for iterative lookup; we describe using a negative-result cache in the paper to reduce the performance hit of such nodes. But certainly, the *correctness* problem when these invisible nodes are the roots is much more severe.) Petar's original paper describes a DHT for Kademlia in which put () was executed to the k closest nodes (where, say, k=20 for large systems). Now, if I remember correctly, this largely assumed that keys were unique to values, i.e., hash(value), such that each key had a unique value. Thus, if you find the key at any one of these k nodes, you're done. For Coral and OpenDHT, one could store multiple values under each key (put () was really an append), thus, these k nodes could be storing different values. Even if you are just implementing put() as a set, if you want to support *overwriting* old values (as opposed to a write-once model of hash(value)), this problem still exists. In the WORLDS paper, we describe how these k nodes can continually monitor one another and "fix" up these inconsistencies, so that all k nodes provide relatively good consistency properties (although these puts are certainly not atomic over the k nodes). Your suggestion of a "consensus" algorithm is similar, although it runs on the "client-side"---so that every node doing a get() would need to perform such a "consensus"---as opposed to on the server-side as we suggest. I'm glad you liked the paper, --mike ----- www.michaelfreedman.org www.coralcdn.org From lemonobrien at yahoo.com Tue Nov 1 21:29:58 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] couple of questions... Message-ID: <20051101212958.33611.qmail@web53602.mail.yahoo.com> 1. when i read from a udp socket, sometimes it seems not to read a whole message; especially after recieving a message...it seems to skip...or skid; kind of like its reading too fast. anyone know anything about this? 2. when keeping the firewall hole open between two computers by ping/pong them; does the router keep the hole open for the recieving (pong'd) computer, thus eliminating the need for it to pong the computer which just ping'd it? I would think so...but want to know for sure. thanks You don't get no juice unless you squeeze Lemon Obrien, the Third. --------------------------------- Yahoo! FareChase - Search multiple travel sites in one click. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051101/0fe0be80/attachment.htm From sg266 at cornell.edu Wed Nov 2 00:16:11 2005 From: sg266 at cornell.edu (Saikat Guha) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] couple of questions... In-Reply-To: <20051101212958.33611.qmail@web53602.mail.yahoo.com> References: <20051101212958.33611.qmail@web53602.mail.yahoo.com> Message-ID: <1130890571.23725.51.camel@himalaya.cs.cornell.edu> On Tue, 2005-11-01 at 13:29 -0800, Lemon Obrien wrote: > 2. when keeping the firewall hole open between two computers by > ping/pong them; does the router keep the hole open for the recieving > (pong'd) computer, thus eliminating the need for it to pong the > computer which just ping'd it? I would think so...but want to know for > sure. In general, one cannot rely on incoming UDP traffic to keep the hole open in the absence of outgoing traffic; a number of security-conscious NATs will close the hole. The only reliable way to keep the hole open is to use both "ping/pong", as you do, and not just "pings". cheers, -- Saikat -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: This is a digitally signed message part Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051101/824db661/attachment.pgp From dbarrett at quinthar.com Thu Nov 3 00:32:59 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Live P2P Video State of the Art In-Reply-To: <4365E1F8.3050705@gmail.com> References: <4365E1F8.3050705@gmail.com> Message-ID: <43695ABB.9090803@quinthar.com> Wow, that's a great paper. Is Fabio on this list? If not, can you invite him? Another paper that gives a nice overview: http://www.ebu.ch/en/technical/trev/trev_303-octoshape.pdf Took a look at the Octoshape stuff; any idea on how it works? Erasure coding? -david Gwendal Simon wrote: > The following page may be of interest for you: > http://pulse.netofpeers.net/wiki/index.php/Publications > > In his master thesis document, Fabio makes a rigorous bibliographic work > on P2P live streaming. He also gives some hints of the system he is > currently conceiving. This project, namely Pulse, considers live > "infinite" data streams, very sensitive to delay. > > In the "netofpeers" initiative, such studies usually result in free > python softwares (see Solipsis and Maay). > > Obviously, comments are welcomed ! > > -------------------------------------- > Gwendal Simon > http://solipsis.netofpeers.net > > > > David Barrett wrote: > >> cefn.hoile@bt.com wrote: >> > In contrast to the single-source, multiple recipients model, tvoon in >> > Germany have been exploring a multiple-source, multiple recipients >> > model for live streams. >> >> Ahh, interesting, do you have any links to more technical information on >> how it works? The website stays fairly high level. I like the idea of >> multiple sources / multiple recipients, but I'm curious if the >> complexity pays for itself in the real world. For example: >> >> - Can a node simultaneously receive and broadcast the same stream, or >> need I receive the whole thing before I broadcast? >> >> - Are the streams "live" in the sense that they have no predefined >> length, or is it merely "streaming" pre-recorded (fixed-length) video? >> >> - How does a node splice feeds from multiple sources together in >> realtime to produce a single unified feed for playback? >> >> Basically, is anyone doing anything like this, is it possible, and is it >> worth the effort? >> >> -david >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From wesley at felter.org Thu Nov 3 01:05:59 2005 From: wesley at felter.org (Wes Felter) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Live P2P Video State of the Art In-Reply-To: <43695ABB.9090803@quinthar.com> References: <4365E1F8.3050705@gmail.com> <43695ABB.9090803@quinthar.com> Message-ID: <56ED7A80-8034-45DC-9B84-6A4E25BF324E@felter.org> On Nov 2, 2005, at 6:32 PM, David Barrett wrote: > Another paper that gives a nice overview: > > http://www.ebu.ch/en/technical/trev/trev_303-octoshape.pdf > > Took a look at the Octoshape stuff; any idea on how it works? > Erasure coding? If marketing hype can be considered a good overview. :-) The mention of "any 4 of 12" is an obvious indicator of FEC/erasure coding. I have to wonder if FEC really adds any improvement over Bullet' or Chainsaw. Wes Felter - wesley@felter.org - http://felter.org/wesley/ From dbarrett at quinthar.com Thu Nov 3 01:57:39 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Live P2P Video State of the Art In-Reply-To: <56ED7A80-8034-45DC-9B84-6A4E25BF324E@felter.org> References: <56ED7A80-8034-45DC-9B84-6A4E25BF324E@felter.org> Message-ID: <1130983062.12777C91@ba12.dngr.org> On Wed, 2 Nov 2005 5:07 pm, Wes Felter wrote: > On Nov 2, 2005, at 6:32 PM, David Barrett wrote: > >> Another paper that gives a nice overview: >> http://www.ebu.ch/en/technical/trev/trev_303-octoshape.pdf >> >> Took a look at the Octoshape stuff; any idea on how it works? >> Erasure coding? > > If marketing hype can be considered a good overview. :-) Ha, but it's such *good* hype. :) > The mention of "any 4 of 12" is an obvious indicator of FEC/erasure > coding. I have to wonder if FEC really adds any improvement over > Bullet' or Chainsaw. Agreed. I've heard of very few systems that get the advertised savings out of FEC. Wondering if Octashape is a diamond in the rough? The bullet stuff looks nice; any idea on its current implementation status? Not familiar with Chainsaw, though. Where does it fall in the pantheon of p2p streaming architectures? -david From dbarrett at quinthar.com Sat Nov 5 22:01:47 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! Message-ID: <436D2BCB.5060904@quinthar.com> So you all know I've been working on iGlance for ages. Well, I'm happy to report that after all this time, it's done. (Well, as much as anything in this space is ever done, but it works for some large subset of users, and it has a snazzy website to promote it.) For details, please see: http://www.iglance.com To review, iGlance is a P2P VoIP/videoconferencing application with push to talk, video presence, screen sharing, file transfers, and more. It does NAT traversal, has a custom GUI layer, is open source, and is built atop a simple platform encapsulation layer ("libpig") that does the basics without forcing you to adopt any design religion. If you're a telecommuter, work in a distributed team, or just want to try a new paradigm in communications, give it a shot. Likewise, if you're developer and looking to put your P2P, VoIP, video/file/screen-sharing energy to good, open-source use, check out the code and let me know what you think. Thanks for all your help, and I look forward to your feedback! -david From ian at locut.us Sun Nov 6 15:58:45 2005 From: ian at locut.us (Ian Clarke) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <436D2BCB.5060904@quinthar.com> References: <436D2BCB.5060904@quinthar.com> Message-ID: <58730D22-6938-473F-AAC0-601A0FCFCE32@locut.us> Its about time someone did this :-) It seems like you are pretty heavily reliant on windows stuff though, any plans for Mac or Linux versions? How portable is the code? I personally use a Mac, but I will give this a try on Virtual PC. All the best, Ian. On 5 Nov 2005, at 22:01, David Barrett wrote: > So you all know I've been working on iGlance for ages. Well, I'm > happy > to report that after all this time, it's done. (Well, as much as > anything in this space is ever done, but it works for some large > subset > of users, and it has a snazzy website to promote it.) For details, > please see: > > http://www.iglance.com > > To review, iGlance is a P2P VoIP/videoconferencing application with > push > to talk, video presence, screen sharing, file transfers, and more. It > does NAT traversal, has a custom GUI layer, is open source, and is > built > atop a simple platform encapsulation layer ("libpig") that does the > basics without forcing you to adopt any design religion. > > If you're a telecommuter, work in a distributed team, or just want to > try a new paradigm in communications, give it a shot. Likewise, if > you're developer and looking to put your P2P, VoIP, > video/file/screen-sharing energy to good, open-source use, check > out the > code and let me know what you think. > > Thanks for all your help, and I look forward to your feedback! > > -david > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From dbarrett at quinthar.com Mon Nov 7 04:23:12 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! References: <1131337414.3FAF00A@ba12.dngr.org> Message-ID: <1131337414.29029B5D@dg11.dngr.org> On Sun, 6 Nov 2005 8:45 am, Ian Clarke wrote: > Its about time someone did this :-) I thought so too! :) Push-to-talk is a nice middle-ground, and the video presence is really quite powerful when both sides have cameras. > It seems like you are pretty heavily reliant on windows stuff though, > any plans for Mac or Linux versions? How portable is the code? Actually, there are very few windows dependencies and platform portability was a design goal from the outset. All the file, threads, TLS, sockets, and base stuff currently cross compiles between Windows and Linux (and WinCE for a bit, but I pulled it). Generally libpig is very thin, and almost all of the platform specific code is one in one file (GNonPortable_Win32.cpp/_Linux.cpp). The "thickest" part of libpig is the audio/video capture/playback part as that depends heavily on the platform, but the external API is very minimal. Another somewhat "thick" area is the GUI. But I've sliced this into two layers: - A platform dependent "display RGBA bitmap and return input events" architecture - A platform independent, XML-based, HTML-like, skinnable GUI engine The intent behind libpig is to create thin cross-compile layer, rather than a application design philosophy. Sorta the difference between OpenGL and DirectX -- I want it to fit into my architecture, and not architect around its design. My original intent was to just use APR, ACE, Qt, Boost, etc, but I found myself confused by deep polymorphic trees, esoteric programming practices, compilation problems, licensing problems, and so on. Eventually I decided my needs were so minimal that I'd just go my own way, and I don't regret the decision in the least. > I personally use a Mac, but I will give this a try on Virtual PC. Excellent. Incidentally, I'm extremely eager to do a Mac port (I spend most my life in coffeeshops -- for which iGlance is idealy suited -- and Macs outnumber PCs maybe 2:1). But I don't know jack about the platform, it doesn't work well in VM ware, and I don't want to lug around two laptops. If anyone is interested in bringing iGlance to the Mac, I am *all ears*. > All the best, -david From eugen at leitl.org Mon Nov 7 09:16:54 2005 From: eugen at leitl.org (Eugen Leitl) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] [kragen@pobox.com: making BitTorrent work better with aggregation] Message-ID: <20051107091654.GF2249@leitl.org> ----- Forwarded message from kragen@pobox.com ----- From: kragen@pobox.com Date: Mon, 7 Nov 2005 03:37:02 -0500 (EST) To: kragen-tol@canonical.org Subject: making BitTorrent work better with aggregation Observations of BitTorrent behavior, with an oversimplified model ----------------------------------------------------------------- (This varies a lot from torrent to torrent.) On average, the number of seeders on a BitTorrent torrent is around 10% of the number of leechers, a number that gradually decreases until the torrent dies. This is not true for all torrents, but it's true of a substantial number of them. If you're using such a torrent to publish a file (such as a home video or collection of multi-megapixel photographs) that you wish to remain continuously available, you must operate your own permanent seed. However, you'd like most of the file data in your torrent to travel from one peer to another, rather than from your own seed to the peers. To simplify, I assume that there are no incomplete downloads, and each leecher becomes a seeder for some period of time after they finish --- about 10% of the time they had been leeching. As time goes on, the number of leechers in the torrent approaches the time to download a complete copy of the file, multiplied by the frequency of new requests; P, the number of total peers aside from the permanent seed, is the number of leechers multiplied by a constant around 1.1. Whenever P is 1 or 0, all of the data transmitted in the system must comes from your permanent seed, and BitTorrent degrades to a download protocol similar to FTP or HTTP, but with better protection against corruption of data in transit. Whenever P > 1, non-permanent peers can exchange data with one another (since they're online at the same time), and the load on the permanent seed is lessened. Indeed, if the number of other peers remains above 1 permanently, the permanent seed need never send out data blocks (under the simplifying assumptions above.) Where BitTorrent works well --------------------------- Mostly BitTorrent has been used successfully to date with P in the hundreds, sometimes with a permanent seed and sometimes without. But since P is proportional to the frequency of new requests and the file size, but inversely proportional to the bandwidth to these peers, BitTorrent has not been very successful at distributing small files or those with only a few requestors at any given time. Making BitTorrent work better through aggregation ------------------------------------------------- One answer is multi-file torrents, or ISO torrents, in which a torrent contains hundreds of megabytes of data belonging to many different files. This attacks the problem on two fronts: first, it increases the number of requests for a particular torrent by aggregating demand for many individual files into a single torrent, and second, it increases the amount of time required to complete the download. This may have problems when applied to very large files, however. BitTorrent works much better than previous peer-to-peer file-sharing systems for several reasons, of which the best known is that the software embodies a social norm of reciprocation. The most effective way to get good service from a torrent is to send data to other participants so that they will want to send data to you. Therefore, modifying your own copy of the software to improve your own service at the cost of others is quite difficult. (Most previous systems also suffered from not having "swarming downloads" and from attempting to provide search and confidentiality or deniability facilities.) Suppose, though, you're downloading a 300MB OurMedia video, and you find that it's packaged into a 10GB UDF filesystem, which will take up US$10 of disk space when it finishes downloading, cost you about US$3 of bandwidth at US DSL rates to download, and a similar amount of bandwidth to upload to others, and worst of all, it will take about a day; while downloading the video alone would cost you only about US$0.15 upload and US$0.15 to upload and take less than an hour. You might modify your BitTorrent client's piece-selection algorithm to preferentially request the parts of the UDF filesystem that interests you, and preferentially talk to peers who have it. If everyone does this, the result would be rather as if they're divided among 33 different torrents; each peer stays online for less time, and other peers it will want to talk to come online less often. Making aggregation more effective --------------------------------- Suppose that instead of aggregating 33 OurMedia videos into a single UDF filesystem, the parts of which can be sensibly requested separately, we use an M-of-N secret-sharing scheme to encode the 33 videos into a file such that you must download the whole file, or nearly the whole file, to recover any of the original videos from it. Now we have aligned everyone's incentives properly, without making any changes to the BitTorrent protocol or software --- simply by adding an archiving/unarchiving step outside the purview of BitTorrent itself. Nobody can gain any use from this torrent without downloading the whole thing, or nearly so. The drawbacks of aggregation ---------------------------- The aggregation approach is costly. Even if everyone participating in the earlier-mentioned 10GB torrent is interested in only one video, they have to pay an aggregation tax of 9.7GB --- uploaded, downloaded, and stored --- merely to provide incentives for others to cooperate with them. Economically, this is nearly a deadweight loss. It can be diminished slightly by aggregating related files instead of randomly selected ones. As a consequence, ISPs will wish their customers would download smaller torrents, and pay-for-download services (PayPal me $2 and I'll give you this 300MB file) will have a total cost advantage over peer-to-peer downloading. Other approaches to supporting small and unpopular files with BitTorrent ------------------------------------------------------------------------ Trickling --------- When P = 1, the permanent seed controls the amount of time the client is online by how fast it sends the requested file. Consequently it can lengthen the time to download the file to increase the likelihood that P will increase as another peer comes online. However, if there are only a few ephemeral peers and they are talking to one another quickly, each time the permanent seed sends the last block of the file, the other peers will quickly communicate it among themselves and soon go offline. Still, this is a way to triple or quadruple your effective bandwidth, which is worth something. CacheLogic ---------- CacheLogic is a company that sells peer-to-peer caching devices to ISPs. The idea is that the ISP saves a copy of whatever BitTorrent data passes through it, and serves it to you from their local copy whenever you request it. (I'm not clear on whether it merely participates as a peer in the torrent or actually hijacks your attempted connections to other peers.) Payment ------- MojoNation, and later MNet, had the idea that you would exchange some sort of currency for services such as file downloads. This allows the reciprocity enforcement mechanism to extend beyond pairwise relationships into group relationships, and to provide a measure of otherwise incommensurable goods. This would provide an incentive for people to download files they didn't themselves want, so that they could earn credit from other people who did want them, and then use that credit to download things they did want. I have written about this a bit on the CommerceNet zLab Wiki. ----- End forwarded message ----- -- Eugen* Leitl leitl ______________________________________________________________ ICBM: 48.07100, 11.36820 http://www.leitl.org 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051107/1ba7e520/attachment.pgp From auto43348 at hushmail.com Tue Nov 8 16:41:05 2005 From: auto43348 at hushmail.com (auto43348@hushmail.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! Message-ID: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> Here is my $0.02 on voice p2p comms: 1. Well implemented, OpenSource, strong encryption using standard algorithms which is ON by default. 2. Multiplatform/Os including mobile devices. 3. Firewall traversing. 4. Infrastrctureless p2p. Not requiring a central server. The ability to bootstrap on an internal network seperated from the internet. 5. Scaleable and reliable. 6. Phone, chat, video, PTT, file transfer, SMS, whiteboard, ability to integrate with the PSTN. Integrate with normal telephones. Desktop sharing and PTT integration with radios (like Dingotel) would be nice. Security issues with desktop sharing would need to be firmly addressed. 7. It Just Works. Grandma needs to be able to download, click and use. 8. ATA ability. Ability to put on a standalone device to create an ATA. Drop on something like one of the linux based routers to create an ATA. 9. Good marketing and PR. A critical mass is well, um critical. :) 10. Ability to force relays and increase anonymity if desired would be nice. 11. Effecient use of bandwidth and CPU, with an ability to choose low bandwidth/cpu protocols if desired to help with slower computers, limited bandwidth (like mobile wireless) and sat connections. 12. The pie in the sky would the ability to call (in both directions) an ATA, softphone, 2way radio, SMS, chat or cell and obtain a p2p secure SIP connection using a central infrastructureless design with also having the ability to interface with the PSTN using private gateways or paid services as needed. Something like Skype with it's momentum, critical mass, firewall traversal, multiplatform, default encryption, It Just Works feel, PSTN integration; the 2way ability of Dingotel; OpenSource and multiple protocol interfacing like Gaim; Well implemented, peer reviewed strong secuirty like PGP/GPG/ciphire, with an internal design which doesn't require a central infrastructure and therefore is robust and cannot be shut down (so you don't have problems like after Katrina that because the regional switch was down or overloaded, New Orleans cell phones being called from NY and physically present in Atlanta, don't work.), and works/integrates on an inexpensive black box like a Sipura. I am repeating myself, but that should demonstrate the general idea. :) rearden >Date: Sun, 6 Nov 2005 20:23:12 -0800 >From: David Barrett >Subject: Re: [p2p-hackers] iGlance is here! >To: "Peer-to-peer development." >Message-ID: <1131337414.29029B5D@dg11.dngr.org> >Content-Type: text/plain; charset="us-ascii"; format="flowed" > >On Sun, 6 Nov 2005 8:45 am, Ian Clarke wrote: >> Its about time someone did this :-) > >I thought so too! :) Push-to-talk is a nice middle-ground, and >the >video presence is really quite powerful when both sides have >cameras. > > >> It seems like you are pretty heavily reliant on windows stuff >though, >> any plans for Mac or Linux versions? How portable is the code? > >Actually, there are very few windows dependencies and platform >portability was a design goal from the outset. All the file, >threads, >TLS, sockets, and base stuff currently cross compiles between >Windows >and Linux (and WinCE for a bit, but I pulled it). Generally >libpig is >very thin, and almost all of the platform specific code is one in >one >file (GNonPortable_Win32.cpp/_Linux.cpp). > >The "thickest" part of libpig is the audio/video capture/playback >part >as that depends heavily on the platform, but the external API is >very >minimal. > >Another somewhat "thick" area is the GUI. But I've sliced this >into two >layers: >- A platform dependent "display RGBA bitmap and return input >events" >architecture >- A platform independent, XML-based, HTML-like, skinnable GUI >engine > >The intent behind libpig is to create thin cross-compile layer, >rather >than a application design philosophy. Sorta the difference >between >OpenGL and DirectX -- I want it to fit into my architecture, and >not >architect around its design. > >My original intent was to just use APR, ACE, Qt, Boost, etc, but I >found >myself confused by deep polymorphic trees, esoteric programming >practices, compilation problems, licensing problems, and so on. >Eventually I decided my needs were so minimal that I'd just go my >own >way, and I don't regret the decision in the least. > > >> I personally use a Mac, but I will give this a try on Virtual >PC. > >Excellent. Incidentally, I'm extremely eager to do a Mac port (I >spend >most my life in coffeeshops -- for which iGlance is idealy suited - >- and >Macs outnumber PCs maybe 2:1). But I don't know jack about the >platform, it doesn't work well in VM ware, and I don't want to lug > >around two laptops. > >If anyone is interested in bringing iGlance to the Mac, I am *all >ears*. > >> All the best, > >-david Concerned about your privacy? Instantly send FREE secure email, no account required http://www.hushmail.com/send?l=480 Get the best prices on SSL certificates from Hushmail https://www.hushssl.com?l=485 From mccoy at mad-scientist.com Tue Nov 8 18:42:28 2005 From: mccoy at mad-scientist.com (Jim McCoy) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> References: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> Message-ID: On Nov 8, 2005, at 8:41 AM, wrote: > Here is my $0.02 on voice p2p comms: And a pony. Don't forget that you want a pony too.... From ian at locut.us Tue Nov 8 19:29:08 2005 From: ian at locut.us (Ian Clarke) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> References: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> Message-ID: <070E9F02-EEE0-4159-B96B-B3A03FC72A86@locut.us> On 8 Nov 2005, at 16:41, wrote: > 4. Infrastrctureless p2p. Not requiring a central server. The > ability to bootstrap on an internal network seperated from the > internet. Be careful what you wish for ;-) Skype started out with a decentralised mechanism for user lookup, but later migrated to a centralised solution. Nobody is a bigger fan of decentralisation than I am, but sometimes the easiest way can also be be best. If I was building a VoIP solution, I would centralise user lookup in the interests of getting the product out the door ASAP and minimising the likely number of headaches. You can always decentralise later if you find that you need to. Ian. From dbarrett at quinthar.com Tue Nov 8 21:22:24 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <070E9F02-EEE0-4159-B96B-B3A03FC72A86@locut.us> References: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> <070E9F02-EEE0-4159-B96B-B3A03FC72A86@locut.us> Message-ID: <43711710.3050507@quinthar.com> Ian Clarke wrote: > > On 8 Nov 2005, at 16:41, > wrote: > >> 4. Infrastrctureless p2p. Not requiring a central server. The >> ability to bootstrap on an internal network seperated from the >> internet. > > > Be careful what you wish for ;-) Skype started out with a > decentralised mechanism for user lookup, but later migrated to a > centralised solution. Nobody is a bigger fan of decentralisation than > I am, but sometimes the easiest way can also be be best. > > If I was building a VoIP solution, I would centralise user lookup in > the interests of getting the product out the door ASAP and minimising > the likely number of headaches. You can always decentralise later if > you find that you need to. This is precisely the same logic I've used. iGlance has central servers for authentication, auto-upgrade, and directory lookups, and I think this is appropriate. iGlance also uses central servers for STUN/TURN type functions, but this is designed to be decentralized once the userbase picks up. So it's inappropriately centralized in this respect at the moment, but ready to decentralize when the moment is right. iGlance naturally uses direct connections for all client/client communications (except if one of the clients is over a relay connection, naturally), and I think this is appropriate use of decentralization. -david From dbarrett at quinthar.com Tue Nov 8 21:42:14 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> References: <200511081641.jA8GfGnJ075154@mailserver2.hushmail.com> Message-ID: <43711BB6.9010701@quinthar.com> As you might guess, iGlance isn't quite there. Here's where it is: Today - Open source - NAT / Firewall traversing - Scalable and reliable (maybe? help me find out) - Phone - Chat - Video - PTT - File transfer - Desktop sharing - It just works for Grandma - Ability to force relays Also today, but not mentioned - Skinnable GUI - Extensive privacy options - Extensive self-diagnosis, tunable logfiles, logfile harvesting - Integrated bug reporting - Window sharing Not yet but intended - Strong encryption on by default - Multiplatform including mobile (WinCE, specifically) - Gateway to normal telephones - Good marketing / pr - Critical mass - Good bandwidth usage; adaptive for connections Not yet and not considered, but a good idea - SMS - Whiteboard - PSTN integration (what specifically? Like Asterick?) - Integration with PTT radios - Abilty to choose lower bandwith protocols - Pony Not yet and not sure what it is - ATA ability (what's this?) Not yet and not intended - Infrastructureless P2P - Anonyminity Check out http://www.iglance.com/code.html for details on getting the code via the public Subversion repository. I believe the code is well commented, though there is an absence of overall architecture documentation. I'd be happy to create an overview for whatever area you're most interested in modifying (ie, if you're a security nut, I'll tell you where to look and where to hook in). -david auto43348@hushmail.com wrote: > Here is my $0.02 on voice p2p comms: > > 1. Well implemented, OpenSource, strong encryption using standard > algorithms which is ON by default. > 2. Multiplatform/Os including mobile devices. > 3. Firewall traversing. > 4. Infrastrctureless p2p. Not requiring a central server. The > ability to bootstrap on an internal network seperated from the > internet. > 5. Scaleable and reliable. > 6. Phone, chat, video, PTT, file transfer, SMS, whiteboard, > ability to integrate with the PSTN. Integrate with normal > telephones. Desktop sharing and PTT integration with radios (like > Dingotel) would be nice. Security issues with desktop sharing > would need to be firmly addressed. > 7. It Just Works. Grandma needs to be able to download, click and > use. > 8. ATA ability. Ability to put on a standalone device to create > an ATA. Drop on something like one of the linux based routers to > create an ATA. > 9. Good marketing and PR. A critical mass is well, um critical. :) > 10. Ability to force relays and increase anonymity if desired > would be nice. > 11. Effecient use of bandwidth and CPU, with an ability to choose > low bandwidth/cpu protocols if desired to help with slower > computers, limited bandwidth (like mobile wireless) and sat > connections. > 12. The pie in the sky would the ability to call (in both > directions) an ATA, softphone, 2way radio, SMS, chat or cell and > obtain a p2p secure SIP connection using a central > infrastructureless design with also having the ability to interface > with the PSTN using private gateways or paid services as needed. > > Something like Skype with it's momentum, critical mass, firewall > traversal, multiplatform, default encryption, It Just Works feel, > PSTN integration; the 2way ability of Dingotel; OpenSource and > multiple protocol interfacing like Gaim; Well implemented, peer > reviewed strong secuirty like PGP/GPG/ciphire, with an internal > design which doesn't require a central infrastructure and therefore > is robust and cannot be shut down (so you don't have problems like > after Katrina that because the regional switch was down or > overloaded, New Orleans cell phones being called from NY and > physically present in Atlanta, don't work.), and works/integrates > on an inexpensive black box like a Sipura. > > I am repeating myself, but that should demonstrate the general > idea. :) > > rearden > > >>Date: Sun, 6 Nov 2005 20:23:12 -0800 >>From: David Barrett >>Subject: Re: [p2p-hackers] iGlance is here! >>To: "Peer-to-peer development." >>Message-ID: <1131337414.29029B5D@dg11.dngr.org> >>Content-Type: text/plain; charset="us-ascii"; format="flowed" >> >>On Sun, 6 Nov 2005 8:45 am, Ian Clarke wrote: >> >>>Its about time someone did this :-) >> >>I thought so too! :) Push-to-talk is a nice middle-ground, and >>the >>video presence is really quite powerful when both sides have >>cameras. >> >> >> >>>It seems like you are pretty heavily reliant on windows stuff >> >>though, >> >>>any plans for Mac or Linux versions? How portable is the code? >> >>Actually, there are very few windows dependencies and platform >>portability was a design goal from the outset. All the file, >>threads, >>TLS, sockets, and base stuff currently cross compiles between >>Windows >>and Linux (and WinCE for a bit, but I pulled it). Generally >>libpig is >>very thin, and almost all of the platform specific code is one in >>one >>file (GNonPortable_Win32.cpp/_Linux.cpp). >> >>The "thickest" part of libpig is the audio/video capture/playback >>part >>as that depends heavily on the platform, but the external API is >>very >>minimal. >> >>Another somewhat "thick" area is the GUI. But I've sliced this >>into two >>layers: >>- A platform dependent "display RGBA bitmap and return input >>events" >>architecture >>- A platform independent, XML-based, HTML-like, skinnable GUI >>engine >> >>The intent behind libpig is to create thin cross-compile layer, >>rather >>than a application design philosophy. Sorta the difference >>between >>OpenGL and DirectX -- I want it to fit into my architecture, and >>not >>architect around its design. >> >>My original intent was to just use APR, ACE, Qt, Boost, etc, but I >>found >>myself confused by deep polymorphic trees, esoteric programming >>practices, compilation problems, licensing problems, and so on. >>Eventually I decided my needs were so minimal that I'd just go my >>own >>way, and I don't regret the decision in the least. >> >> >> >>>I personally use a Mac, but I will give this a try on Virtual >> >>PC. >> >>Excellent. Incidentally, I'm extremely eager to do a Mac port (I >>spend >>most my life in coffeeshops -- for which iGlance is idealy suited - >>- and >>Macs outnumber PCs maybe 2:1). But I don't know jack about the >>platform, it doesn't work well in VM ware, and I don't want to lug >> >>around two laptops. >> >>If anyone is interested in bringing iGlance to the Mac, I am *all >>ears*. >> >> >>>All the best, >> >>-david > > > > > > Concerned about your privacy? Instantly send FREE secure email, no account required > http://www.hushmail.com/send?l=480 > > Get the best prices on SSL certificates from Hushmail > https://www.hushssl.com?l=485 > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From lemonobrien at yahoo.com Tue Nov 8 22:03:22 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] iGlance is here! In-Reply-To: <43711BB6.9010701@quinthar.com> Message-ID: <20051108220323.93351.qmail@web53608.mail.yahoo.com> you should be looking for money and try to get other developers... i run a company doing peer to peer stuff; figure out how to create cash streams; i'd love to have you develop stuff on my peer platform; my company is close to launching and we're doing this in the 'file' space; your phone stuff would be a nice bonus... our front is html based but we run on the desk top. is your platform very seperated from the os? our is, and we use WTL on the front; giving us very thin interface attachment on windows; my concern is MFC....i developed in MFC and its a kludge-kinda-pain in the butt object library. as for NAT traversal, how is your simultanious connect? David Barrett wrote: As you might guess, iGlance isn't quite there. Here's where it is: Today - Open source - NAT / Firewall traversing - Scalable and reliable (maybe? help me find out) - Phone - Chat - Video - PTT - File transfer - Desktop sharing - It just works for Grandma - Ability to force relays Also today, but not mentioned - Skinnable GUI - Extensive privacy options - Extensive self-diagnosis, tunable logfiles, logfile harvesting - Integrated bug reporting - Window sharing Not yet but intended - Strong encryption on by default - Multiplatform including mobile (WinCE, specifically) - Gateway to normal telephones - Good marketing / pr - Critical mass - Good bandwidth usage; adaptive for connections Not yet and not considered, but a good idea - SMS - Whiteboard - PSTN integration (what specifically? Like Asterick?) - Integration with PTT radios - Abilty to choose lower bandwith protocols - Pony Not yet and not sure what it is - ATA ability (what's this?) Not yet and not intended - Infrastructureless P2P - Anonyminity Check out http://www.iglance.com/code.html for details on getting the code via the public Subversion repository. I believe the code is well commented, though there is an absence of overall architecture documentation. I'd be happy to create an overview for whatever area you're most interested in modifying (ie, if you're a security nut, I'll tell you where to look and where to hook in). -david auto43348@hushmail.com wrote: > Here is my $0.02 on voice p2p comms: > > 1. Well implemented, OpenSource, strong encryption using standard > algorithms which is ON by default. > 2. Multiplatform/Os including mobile devices. > 3. Firewall traversing. > 4. Infrastrctureless p2p. Not requiring a central server. The > ability to bootstrap on an internal network seperated from the > internet. > 5. Scaleable and reliable. > 6. Phone, chat, video, PTT, file transfer, SMS, whiteboard, > ability to integrate with the PSTN. Integrate with normal > telephones. Desktop sharing and PTT integration with radios (like > Dingotel) would be nice. Security issues with desktop sharing > would need to be firmly addressed. > 7. It Just Works. Grandma needs to be able to download, click and > use. > 8. ATA ability. Ability to put on a standalone device to create > an ATA. Drop on something like one of the linux based routers to > create an ATA. > 9. Good marketing and PR. A critical mass is well, um critical. :) > 10. Ability to force relays and increase anonymity if desired > would be nice. > 11. Effecient use of bandwidth and CPU, with an ability to choose > low bandwidth/cpu protocols if desired to help with slower > computers, limited bandwidth (like mobile wireless) and sat > connections. > 12. The pie in the sky would the ability to call (in both > directions) an ATA, softphone, 2way radio, SMS, chat or cell and > obtain a p2p secure SIP connection using a central > infrastructureless design with also having the ability to interface > with the PSTN using private gateways or paid services as needed. > > Something like Skype with it's momentum, critical mass, firewall > traversal, multiplatform, default encryption, It Just Works feel, > PSTN integration; the 2way ability of Dingotel; OpenSource and > multiple protocol interfacing like Gaim; Well implemented, peer > reviewed strong secuirty like PGP/GPG/ciphire, with an internal > design which doesn't require a central infrastructure and therefore > is robust and cannot be shut down (so you don't have problems like > after Katrina that because the regional switch was down or > overloaded, New Orleans cell phones being called from NY and > physically present in Atlanta, don't work.), and works/integrates > on an inexpensive black box like a Sipura. > > I am repeating myself, but that should demonstrate the general > idea. :) > > rearden > > >>Date: Sun, 6 Nov 2005 20:23:12 -0800 >>From: David Barrett >>Subject: Re: [p2p-hackers] iGlance is here! >>To: "Peer-to-peer development." >>Message-ID: <1131337414.29029B5D@dg11.dngr.org> >>Content-Type: text/plain; charset="us-ascii"; format="flowed" >> >>On Sun, 6 Nov 2005 8:45 am, Ian Clarke wrote: >> >>>Its about time someone did this :-) >> >>I thought so too! :) Push-to-talk is a nice middle-ground, and >>the >>video presence is really quite powerful when both sides have >>cameras. >> >> >> >>>It seems like you are pretty heavily reliant on windows stuff >> >>though, >> >>>any plans for Mac or Linux versions? How portable is the code? >> >>Actually, there are very few windows dependencies and platform >>portability was a design goal from the outset. All the file, >>threads, >>TLS, sockets, and base stuff currently cross compiles between >>Windows >>and Linux (and WinCE for a bit, but I pulled it). Generally >>libpig is >>very thin, and almost all of the platform specific code is one in >>one >>file (GNonPortable_Win32.cpp/_Linux.cpp). >> >>The "thickest" part of libpig is the audio/video capture/playback >>part >>as that depends heavily on the platform, but the external API is >>very >>minimal. >> >>Another somewhat "thick" area is the GUI. But I've sliced this >>into two >>layers: >>- A platform dependent "display RGBA bitmap and return input >>events" >>architecture >>- A platform independent, XML-based, HTML-like, skinnable GUI >>engine >> >>The intent behind libpig is to create thin cross-compile layer, >>rather >>than a application design philosophy. Sorta the difference >>between >>OpenGL and DirectX -- I want it to fit into my architecture, and >>not >>architect around its design. >> >>My original intent was to just use APR, ACE, Qt, Boost, etc, but I >>found >>myself confused by deep polymorphic trees, esoteric programming >>practices, compilation problems, licensing problems, and so on. >>Eventually I decided my needs were so minimal that I'd just go my >>own >>way, and I don't regret the decision in the least. >> >> >> >>>I personally use a Mac, but I will give this a try on Virtual >> >>PC. >> >>Excellent. Incidentally, I'm extremely eager to do a Mac port (I >>spend >>most my life in coffeeshops -- for which iGlance is idealy suited - >>- and >>Macs outnumber PCs maybe 2:1). But I don't know jack about the >>platform, it doesn't work well in VM ware, and I don't want to lug >> >>around two laptops. >> >>If anyone is interested in bringing iGlance to the Mac, I am *all >>ears*. >> >> >>>All the best, >> >>-david > > > > > > Concerned about your privacy? Instantly send FREE secure email, no account required > http://www.hushmail.com/send?l=480 > > Get the best prices on SSL certificates from Hushmail > https://www.hushssl.com?l=485 > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. --------------------------------- Yahoo! FareChase - Search multiple travel sites in one click. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051108/36c3dbec/attachment.html From Arnaud.Legout at sophia.inria.fr Thu Nov 10 17:14:42 2005 From: Arnaud.Legout at sophia.inria.fr (Arnaud Legout) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] New version of the paper "Understanding BitTorrent: An Experimental Perspective" Message-ID: <43738002.1040904@sophia.inria.fr> Hello, we have a new version of the paper "Understanding BitTorrent: An Experimental Perspective", which may be of interest to this community. The latest version is available at http://hal.inria.fr/inria-00000156/en Compared to the previous version, we rewrote large portions of the text, added new results and new plots. This is still an on-going effort. Any comments and criticisms are welcomed. Regards, Arnaud Legout. -- Arnaud Legout, Ph.D. INRIA Sophia Antipolis - Plan?te Phone : 00.33.4.92.38.78.15 2004 route des lucioles - BP 93 Fax : 00.33.4.92.38.79.78 06902 Sophia Antipolis CEDEX E-mail: arnaud.legout@sophia.inria.fr FRANCE Web : http://www-sop.inria.fr/planete/Arnaud.Legout/index.html From lutianbo at software.ict.ac.cn Fri Nov 11 09:26:26 2005 From: lutianbo at software.ict.ac.cn (lutianbo) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Testing scalability on a P2P network References: Message-ID: <001601c5e6a1$fd5c60a0$9702000a@ms2444968e76f7> Hi, when i use openssl(>=0.9.7) in Redhat linux, I have a problem. The file /usr/include/openssl/kssl.h is as follows: ************ #include #include #include ******************** but in fact, there is no such a file named krb5.h in /usr/include/, What should I do? Please help ----- Original Message ----- From: "Greg Bildson" To: "Peer-to-peer development." Sent: Monday, October 31, 2005 11:57 PM Subject: RE: [p2p-hackers] Testing scalability on a P2P network > Run it in the wild with a few million users and see if network performance > degrades. ;-) Seriously, sometimes that is what you have to do. > > Obviously, some beta testing can help but it is not true that certain > features can scale indefinitely. You need to make your app have limits that > it won't go beyond. For example, you can't hold 1 million alternate > locations in memory for a file in a file sharing network. You certainly > can't ping them all via UDP. Being able to remotely turn off some features > or settings (again with boundary limits) can be useful. > > There are some fancy simulators around for basic testing. > > Thanks > -greg > >> -----Original Message----- >> From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On >> Behalf Of Frank Moore >> Sent: Monday, October 31, 2005 8:13 AM >> To: Peer-to-peer development. >> Subject: [p2p-hackers] Testing scalability on a P2P network >> >> >> Hi, >> >> Can anyone give me some pointers on scalability testing a P2P network? >> In theory if a P2P network works with N users, it should be possible to >> scale up to larger numbers i.e. N*10, N*100 etc.... >> But is there any way of actually testing this and if so how have other >> people done it? >> >> Thanks, >> Frank. >> >> >> >> >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From wangyong at software.ict.ac.cn Fri Nov 11 11:00:03 2005 From: wangyong at software.ict.ac.cn (=?gb2312?B?zfXTwg==?=) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Testing scalability on a P2P network Message-ID: <20051111110021.CA77E3FC1E@capsicum.zgp.org> bHV0aWFuYm8NCgl1IG1heSBpbnN0YWxsIHNzbCBzZGsgZmlyc3QuDQoNCgkNCg0KPT09PT09PSAy MDA1LTExLTExIDE3OjI2OjI2IMT61NrAtNDF1tDQtLXAo7o9PT09PT09DQoNCj5IaSwNCj4gICAg d2hlbiBpIHVzZSBvcGVuc3NsKD49MC45LjcpIGluIFJlZGhhdCBsaW51eCwgSSBoYXZlIGEgcHJv YmxlbS4NCj5UaGUgZmlsZSAvdXNyL2luY2x1ZGUvb3BlbnNzbC9rc3NsLmggaXMgYXMgZm9sbG93 czoNCj4NCj4qKioqKioqKioqKioNCj4jaW5jbHVkZSA8c3RkaW8uaD4NCj4jaW5jbHVkZSA8Y3R5 cGUuaD4NCj4jaW5jbHVkZSA8a3JiNS5oPg0KPioqKioqKioqKioqKioqKioqKioqDQo+YnV0IGlu IGZhY3QsIHRoZXJlIGlzIG5vIHN1Y2ggYSBmaWxlIG5hbWVkIGtyYjUuaCBpbiAvdXNyL2luY2x1 ZGUvLCBXaGF0IHNob3VsZCBJIGRvPyBQbGVhc2UgaGVscCANCj4NCj4tLS0tLSBPcmlnaW5hbCBN ZXNzYWdlIC0tLS0tIA0KPkZyb206ICJHcmVnIEJpbGRzb24iIDxnYmlsZHNvbkBsaW1lcGVlci5j b20+DQo+VG86ICJQZWVyLXRvLXBlZXIgZGV2ZWxvcG1lbnQuIiA8cDJwLWhhY2tlcnNAemdwLm9y Zz4NCj5TZW50OiBNb25kYXksIE9jdG9iZXIgMzEsIDIwMDUgMTE6NTcgUE0NCj5TdWJqZWN0OiBS RTogW3AycC1oYWNrZXJzXSBUZXN0aW5nIHNjYWxhYmlsaXR5IG9uIGEgUDJQIG5ldHdvcmsNCj4N Cj4NCj4+IFJ1biBpdCBpbiB0aGUgd2lsZCB3aXRoIGEgZmV3IG1pbGxpb24gdXNlcnMgYW5kIHNl ZSBpZiBuZXR3b3JrIHBlcmZvcm1hbmNlDQo+PiBkZWdyYWRlcy4gIDstKSAgU2VyaW91c2x5LCBz b21ldGltZXMgdGhhdCBpcyB3aGF0IHlvdSBoYXZlIHRvIGRvLg0KPj4gDQo+PiBPYnZpb3VzbHks IHNvbWUgYmV0YSB0ZXN0aW5nIGNhbiBoZWxwIGJ1dCBpdCBpcyBub3QgdHJ1ZSB0aGF0IGNlcnRh aW4NCj4+IGZlYXR1cmVzIGNhbiBzY2FsZSBpbmRlZmluaXRlbHkuICBZb3UgbmVlZCB0byBtYWtl IHlvdXIgYXBwIGhhdmUgbGltaXRzIHRoYXQNCj4+IGl0IHdvbid0IGdvIGJleW9uZC4gIEZvciBl eGFtcGxlLCB5b3UgY2FuJ3QgaG9sZCAxIG1pbGxpb24gYWx0ZXJuYXRlDQo+PiBsb2NhdGlvbnMg aW4gbWVtb3J5IGZvciBhIGZpbGUgaW4gYSBmaWxlIHNoYXJpbmcgbmV0d29yay4gIFlvdSBjZXJ0 YWlubHkNCj4+IGNhbid0IHBpbmcgdGhlbSBhbGwgdmlhIFVEUC4gIEJlaW5nIGFibGUgdG8gcmVt b3RlbHkgdHVybiBvZmYgc29tZSBmZWF0dXJlcw0KPj4gb3Igc2V0dGluZ3MgKGFnYWluIHdpdGgg Ym91bmRhcnkgbGltaXRzKSBjYW4gYmUgdXNlZnVsLg0KPj4gDQo+PiBUaGVyZSBhcmUgc29tZSBm YW5jeSBzaW11bGF0b3JzIGFyb3VuZCBmb3IgYmFzaWMgdGVzdGluZy4NCj4+IA0KPj4gVGhhbmtz DQo+PiAtZ3JlZw0KPj4gDQo+Pj4gLS0tLS1PcmlnaW5hbCBNZXNzYWdlLS0tLS0NCj4+PiBGcm9t OiBwMnAtaGFja2Vycy1ib3VuY2VzQHpncC5vcmcgW21haWx0bzpwMnAtaGFja2Vycy1ib3VuY2Vz QHpncC5vcmddT24NCj4+PiBCZWhhbGYgT2YgRnJhbmsgTW9vcmUNCj4+PiBTZW50OiBNb25kYXks IE9jdG9iZXIgMzEsIDIwMDUgODoxMyBBTQ0KPj4+IFRvOiBQZWVyLXRvLXBlZXIgZGV2ZWxvcG1l bnQuDQo+Pj4gU3ViamVjdDogW3AycC1oYWNrZXJzXSBUZXN0aW5nIHNjYWxhYmlsaXR5IG9uIGEg UDJQIG5ldHdvcmsNCj4+Pg0KPj4+DQo+Pj4gSGksDQo+Pj4NCj4+PiBDYW4gYW55b25lIGdpdmUg bWUgc29tZSBwb2ludGVycyBvbiBzY2FsYWJpbGl0eSB0ZXN0aW5nIGEgUDJQIG5ldHdvcms/DQo+ Pj4gSW4gdGhlb3J5IGlmIGEgUDJQIG5ldHdvcmsgd29ya3Mgd2l0aCBOIHVzZXJzLCBpdCBzaG91 bGQgYmUgcG9zc2libGUgdG8NCj4+PiBzY2FsZSB1cCB0byBsYXJnZXIgbnVtYmVycyBpLmUuIE4q MTAsIE4qMTAwIGV0Yy4uLi4NCj4+PiBCdXQgaXMgdGhlcmUgYW55IHdheSBvZiBhY3R1YWxseSB0 ZXN0aW5nIHRoaXMgYW5kIGlmIHNvIGhvdyBoYXZlIG90aGVyDQo+Pj4gcGVvcGxlIGRvbmUgaXQ/ DQo+Pj4NCj4+PiBUaGFua3MsDQo+Pj4gRnJhbmsuDQo+Pj4NCj4+Pg0KPj4+DQo+Pj4NCj4+PiBf X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXw0KPj4+IHAycC1o YWNrZXJzIG1haWxpbmcgbGlzdA0KPj4+IHAycC1oYWNrZXJzQHpncC5vcmcNCj4+PiBodHRwOi8v emdwLm9yZy9tYWlsbWFuL2xpc3RpbmZvL3AycC1oYWNrZXJzDQo+Pj4gX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18NCj4+PiBIZXJlIGlzIGEgd2ViIHBhZ2Ug bGlzdGluZyBQMlAgQ29uZmVyZW5jZXM6DQo+Pj4gaHR0cDovL3d3dy5uZXVyb2dyaWQubmV0L3R3 aWtpL2Jpbi92aWV3L01haW4vUGVlclRvUGVlckNvbmZlcmVuY2VzDQo+PiANCj4+IA0KPj4gX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18NCj4+IHAycC1oYWNr ZXJzIG1haWxpbmcgbGlzdA0KPj4gcDJwLWhhY2tlcnNAemdwLm9yZw0KPj4gaHR0cDovL3pncC5v cmcvbWFpbG1hbi9saXN0aW5mby9wMnAtaGFja2Vycw0KPj4gX19fX19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX18NCj4+IEhlcmUgaXMgYSB3ZWIgcGFnZSBsaXN0aW5n IFAyUCBDb25mZXJlbmNlczoNCj4+IGh0dHA6Ly93d3cubmV1cm9ncmlkLm5ldC90d2lraS9iaW4v dmlldy9NYWluL1BlZXJUb1BlZXJDb25mZXJlbmNlcw0KPj5fX19fX19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fXw0KPnAycC1oYWNrZXJzIG1haWxpbmcgbGlzdA0KPnAy cC1oYWNrZXJzQHpncC5vcmcNCj5odHRwOi8vemdwLm9yZy9tYWlsbWFuL2xpc3RpbmZvL3AycC1o YWNrZXJzDQo+X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18N Cj5IZXJlIGlzIGEgd2ViIHBhZ2UgbGlzdGluZyBQMlAgQ29uZmVyZW5jZXM6DQo+aHR0cDovL3d3 dy5uZXVyb2dyaWQubmV0L3R3aWtpL2Jpbi92aWV3L01haW4vUGVlclRvUGVlckNvbmZlcmVuY2Vz DQo+DQoNCj0gPSA9ID0gPSA9ID0gPSA9ID0gPSA9ID0gPSA9ID0gPSA9ID0gPQ0KCQkJDQoNCqGh oaGhoaGhoaGhoaGhoaHWwg0KwPGjoQ0KIA0KCQkJCSANCqGhoaGhoaGhoaGhoaGhoaHN9dPCDQqh oaGhoaGhoaGhoaGhoaGhd2FuZ3lvbmdAc29mdHdhcmUuaWN0LmFjLmNuDQqhoaGhoaGhoaGhoaGh oaGhoaGhoTIwMDUtMTEtMTENCg0K From fluckstick at msn.com Mon Nov 14 07:48:27 2005 From: fluckstick at msn.com (MICHAEL HENDRYX) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Thank You Message-ID: Thank you for your consideration, and your time. The Fluckstick was here...Get more from the Web. FREE MSN Explorer download : http://explorer.msn.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051114/64dd18f2/attachment.htm From dsandler at cs.rice.edu Tue Nov 15 08:24:07 2005 From: dsandler at cs.rice.edu (Dan Sandler) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Announcement: FeedTree 0.6.0 (RSS over p2p) Message-ID: <534850D3-0E6D-4732-801B-616C5B42C63B@cs.rice.edu> Version 0.6.0 of FeedTree is now available from http://feedtree.net/ . BLURB. FeedTree uses peer-to-peer group communication to efficiently and rapidly distribute RSS and Atom feed events to subscribers. It reduces the bandwidth burden on feed publishers while bringing a "push"-like service model to end users. FeedTree works with existing RSS and Atom feeds and feed reader software. NEW IN THIS VERSION. Several major features have been introduced, including the most-requested of all: a graphical interface for the FeedTree Proxy. A double-clickable application is available for Windows and MacOS X users, and users of other platforms can run the GUI from a JAR file. A list of other features and bugs fixed is available from the project wiki: http://feedtree.net/project/wiki/Version06 DETAILS. The available FeedTree software includes: * The FeedTree Proxy, an end-user Java application which allows *existing* RSS reading apps to receive updates via the FeedTree network. The proxy also works with current RSS and Atom feeds, polling them as necessary and sharing new content with other FeedTree users. * The FeedTree Publisher, an optional tool allowing feed authors to "push" updates to FeedTree users immediately. It runs alongside existing RSS/Atom feeds, so it works with all existing CMSes and weblog engines. The publisher also allows publishers to add digital signatures to their feeds (helping nodes verify the authenticity of updates). More information, including research papers, documentation, source code, and bug reporting can be found on the FeedTree website: http://feedtree.net/ . We'd love to hear about your experiences using the system, as well as any other feedback you might have. FeedTree is an ongoing project of researchers in the Rice University Department of Computer Science. -- Dan Sandler dsandler@cs.rice.edu http://www.cs.rice.edu/~dsandler/ From der at bth.se Tue Nov 15 20:04:07 2005 From: der at bth.se (David Erman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] New version of the paper "Understanding BitTorrent: An Experimental Perspective" In-Reply-To: <43738002.1040904@sophia.inria.fr> References: <43738002.1040904@sophia.inria.fr> Message-ID: <437A3F37.300@bth.se> Hello, My colleagues and I have additional research on BitTorrent, though from a bit more of a tele-traffic viewpoint. Our publications are available at http://www.its.bth.se/staff/der/ . Regards, David Arnaud Legout wrote: > Hello, > we have a new version of the paper "Understanding BitTorrent: An > Experimental Perspective", which may > be of interest to this community. > The latest version is available at http://hal.inria.fr/inria-00000156/en > > Compared to the previous version, we rewrote large portions of the text, > added new results and new plots. > > This is still an on-going effort. Any comments and criticisms are welcomed. > > Regards, > Arnaud Legout. > -- David Erman, david.erman@bth.se, Tek. Lic., Ph.D. Student Blekinge Institute of Technology, School of Engineering SE-371 79, Karlskrona, Sweden telephone: +46 455 38 56 58, cell: +46 709 28 57 56 From eugen at leitl.org Sat Nov 19 20:08:52 2005 From: eugen at leitl.org (Eugen Leitl) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] [nickm@freehaven.net: Re: Hey guys, here is another (great?) idea] Message-ID: <20051119200852.GW2249@leitl.org> ----- Forwarded message from Nick Mathewson ----- From: Nick Mathewson Date: Sat, 19 Nov 2005 13:22:50 -0500 To: or-talk@freehaven.net Subject: Re: Hey guys, here is another (great?) idea User-Agent: Mutt/1.4.2.1i Reply-To: or-talk@freehaven.net On Sat, Nov 19, 2005 at 09:56:03AM -0800, Brian C wrote: > Matt Thorne wrote: > >it would work better if they were required to contribute. > > It would work better from a technical perspective only. From a technical perspective, it would also fail. Right now, our directory-based server discovery system requires all clients to know about all servers. This works right now for hundreds of servers; for hundreds of thousands, it would fail. We need more architectural work before we can support a P2P model. (Yes, we know about existing p2p models, but the problem isn't trivial. It's easy to do bad things to anonymity by partitioning client knowledge, or worse, isolating clients in adversary-targetable zones.) yrs, -- Nick Mathewson ----- End forwarded message ----- -- Eugen* Leitl leitl ______________________________________________________________ ICBM: 48.07100, 11.36820 http://www.leitl.org 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051119/cc65d64f/attachment.pgp From mac.ibook at gmail.com Sun Nov 20 22:09:44 2005 From: mac.ibook at gmail.com (Yifei Zeng) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] About detecting the transfer speed Message-ID: Hi guys. I am currently writing a small p2p program. I need to show the transfer (for files) speed to the users. The language is Java. However, could anyone give a hit for how to detect the transfer speed? I am using NIO (non-blocking I/O) in java. As every message is sent behind the scene, how can I know the actual transfer speed of each message / file? Thanks oOde From jnkm45 at hotmail.com Mon Nov 21 02:03:08 2005 From: jnkm45 at hotmail.com (Jin Kim) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] PLEASE take me off of your mailing list Message-ID: PLEASE take me off of your mailing list. My email is JnKm45@hotmail.com _________________________________________________________________ Don’t just search. Find. Check out the new MSN Search! http://search.msn.click-url.com/go/onm00200636ave/direct/01/ From coderman at gmail.com Mon Nov 21 09:40:30 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] About detecting the transfer speed In-Reply-To: References: Message-ID: <4ef5fec60511210140r3f67e632x3e1afb1a9a1d92f4@mail.gmail.com> On 11/20/05, Yifei Zeng wrote: > ... could anyone give a hit for how to detect the transfer > speed? I am using NIO (non-blocking I/O) in java. As every message is > sent behind the scene, how can I know the > actual transfer speed of each message / file? a weighted average or rolling weighted average works nicely (tweaking the specifics is a black art / varies widely :) at a socket level tuning send and recv buffer sizes in addition to socket options (like nagle, large windows, etc) can have a significant effect on the accuracy/precision of your estimate and overall throughput. as for java specifically you may need to provide your own derived implementation of java.nio.Buffer which keeps track of transfer stats. * http://java.sun.com/j2se/1.4.2/docs/api/java/nio/Buffer.html best regards, From 01771 at iha.dk Sat Nov 26 01:52:17 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: References: Message-ID: <200511260252.17645.01771@iha.dk> Hey When I subscribed this mailinglist about a year ago, there was a lot of activity. I really enjoyed watching the talk and discussion about different topics. The last months almost noone posted anything, so now im wondering where do people talk about peer-to-peer issues? /Jacob From threelions0916 at yahoo.com.cn Sat Nov 26 02:08:03 2005 From: threelions0916 at yahoo.com.cn (Michael Liu) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? References: <200511260252.17645.01771@iha.dk> Message-ID: <000b01c5f22e$3da5f170$7adefea9@cnc.intra> I was also in doubt too, I have joined this mailing list for 1 week, but this post is the first one I received. ----- Original Message ----- From: "Jacob Madsen" <01771@iha.dk> To: Sent: Saturday, November 26, 2005 9:52 AM Subject: [p2p-hackers] Where do bright minds discuss p2p technology? > Hey > > When I subscribed this mailinglist about a year ago, there was a lot of > activity. I really enjoyed watching the talk and discussion about different > topics. > > The last months almost noone posted anything, so now im wondering where do > people talk about peer-to-peer issues? > > /Jacob > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From coderman at gmail.com Sat Nov 26 02:12:19 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <000b01c5f22e$3da5f170$7adefea9@cnc.intra> References: <200511260252.17645.01771@iha.dk> <000b01c5f22e$3da5f170$7adefea9@cnc.intra> Message-ID: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> i want a refund! On 11/25/05, Michael Liu wrote: > I was also in doubt too, I have joined this mailing list for 1 week, but this post is the first one I received. > > > > > ----- Original Message ----- > From: "Jacob Madsen" <01771@iha.dk> > To: > Sent: Saturday, November 26, 2005 9:52 AM > Subject: [p2p-hackers] Where do bright minds discuss p2p technology? > > > > Hey > > > > When I subscribed this mailinglist about a year ago, there was a lot of > > activity. I really enjoyed watching the talk and discussion about different > > topics. > > > > The last months almost noone posted anything, so now im wondering where do > > people talk about peer-to-peer issues? From dbarrett at quinthar.com Sat Nov 26 02:31:13 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> References: <200511260252.17645.01771@iha.dk> <000b01c5f22e$3da5f170$7adefea9@cnc.intra> <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> Message-ID: <4387C8F1.8010601@quinthar.com> Jacob -- What are you working on? I'm sure we'd all love to hear your ideas. coderman wrote: > i want a refund! > > On 11/25/05, Michael Liu wrote: > >>I was also in doubt too, I have joined this mailing list for 1 week, but this post is the first one I received. >> >> >> >> >>----- Original Message ----- >>From: "Jacob Madsen" <01771@iha.dk> >>To: >>Sent: Saturday, November 26, 2005 9:52 AM >>Subject: [p2p-hackers] Where do bright minds discuss p2p technology? >> >> >> >>>Hey >>> >>>When I subscribed this mailinglist about a year ago, there was a lot of >>>activity. I really enjoyed watching the talk and discussion about different >>>topics. >>> >>>The last months almost noone posted anything, so now im wondering where do >>>people talk about peer-to-peer issues? > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From lemonobrien at yahoo.com Sat Nov 26 02:45:59 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> Message-ID: <20051126024559.90834.qmail@web53609.mail.yahoo.com> well....if you guys lived in san francisco, want to change the world, lived in san francisco, and would work for stock you could talked about it everyday...and code it.... coderman wrote: i want a refund! On 11/25/05, Michael Liu wrote: > I was also in doubt too, I have joined this mailing list for 1 week, but this post is the first one I received. > > > > > ----- Original Message ----- > From: "Jacob Madsen" <01771@iha.dk> > To: > Sent: Saturday, November 26, 2005 9:52 AM > Subject: [p2p-hackers] Where do bright minds discuss p2p technology? > > > > Hey > > > > When I subscribed this mailinglist about a year ago, there was a lot of > > activity. I really enjoyed watching the talk and discussion about different > > topics. > > > > The last months almost noone posted anything, so now im wondering where do > > people talk about peer-to-peer issues? _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051125/0e3f4f1a/attachment.htm From dbarrett at quinthar.com Sat Nov 26 03:12:16 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <20051126024559.90834.qmail@web53609.mail.yahoo.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> Message-ID: <4387D290.4040807@quinthar.com> How many people on this list are in SF? It appears Lemon and I; anyone else? Interested in a p2p-hackers night out? -david Lemon Obrien wrote: > well....if you guys lived in san francisco, want to change the world, > lived in san francisco, and would work for stock you could talked about > it everyday...and code it.... > > */coderman /* wrote: > > i want a refund! > > On 11/25/05, Michael Liu wrote: > > I was also in doubt too, I have joined this mailing list for 1 > week, but this post is the first one I received. > > > > > > > > > > ----- Original Message ----- > > From: "Jacob Madsen" <01771@iha.dk> > > To: > > Sent: Saturday, November 26, 2005 9:52 AM > > Subject: [p2p-hackers] Where do bright minds discuss p2p technology? > > > > > > > Hey > > > > > > When I subscribed this mailinglist about a year ago, there was > a lot of > > > activity. I really enjoyed watching the talk and discussion > about different > > > topics. > > > > > > The last months almost noone posted anything, so now im > wondering where do > > > people talk about peer-to-peer issues? > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > You don't get no juice unless you squeeze > Lemon Obrien, the Third. > > > ------------------------------------------------------------------------ > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From lgonze at panix.com Sat Nov 26 03:41:30 2005 From: lgonze at panix.com (Lucas Gonze) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387D290.4040807@quinthar.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> <4387D290.4040807@quinthar.com> Message-ID: <4387D96A.6090402@panix.com> David Barrett wrote: > How many people on this list are in SF? It appears Lemon and I; > anyone else? Interested in a p2p-hackers night out? Nope. But an Oahu p2p-hackers night out would be very fine -- any chance there are kindred hackers? From sam at neurogrid.com Sat Nov 26 03:46:27 2005 From: sam at neurogrid.com (Sam Joseph) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387D96A.6090402@panix.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> <4387D290.4040807@quinthar.com> <4387D96A.6090402@panix.com> Message-ID: <4387DA93.9010405@neurogrid.com> I'm in oahu - well actually I'm in Japan this week, but am living in oahu. Lucas, I didn't realise you'd moved - are there more of us here? CHEERS> SAM Lucas Gonze wrote: > David Barrett wrote: > >> How many people on this list are in SF? It appears Lemon and I; >> anyone else? Interested in a p2p-hackers night out? > > > > Nope. But an Oahu p2p-hackers night out would be very fine -- any > chance there are kindred hackers? > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From lgonze at panix.com Sat Nov 26 03:54:00 2005 From: lgonze at panix.com (Lucas Gonze) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387DA93.9010405@neurogrid.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> <4387D290.4040807@quinthar.com> <4387D96A.6090402@panix.com> <4387DA93.9010405@neurogrid.com> Message-ID: <4387DC58.2000205@panix.com> Sam Joseph wrote: > I'm in oahu - well actually I'm in Japan this week, but am living in > oahu. Whaa? I thought for sure that was futile. Send me an email when you get back and let's do an Aloha p2p-hackers meetup. > Lucas, I didn't realise you'd moved - are there more of us here? Not that I know of, it is a desert island in that respect. From john.casey at gmail.com Sat Nov 26 05:27:17 2005 From: john.casey at gmail.com (John Casey) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387C8F1.8010601@quinthar.com> References: <200511260252.17645.01771@iha.dk> <000b01c5f22e$3da5f170$7adefea9@cnc.intra> <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> <4387C8F1.8010601@quinthar.com> Message-ID: hehe. perhaps everyone is just keeping their secrets to themselves ;P in the hope that they can later patent their beautiful ideas. On 11/26/05, David Barrett wrote: > Jacob -- > > What are you working on? I'm sure we'd all love to hear your ideas. > > coderman wrote: > > i want a refund! From sam at neurogrid.com Sat Nov 26 05:44:41 2005 From: sam at neurogrid.com (Sam Joseph) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: References: <200511260252.17645.01771@iha.dk> <000b01c5f22e$3da5f170$7adefea9@cnc.intra> <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> <4387C8F1.8010601@quinthar.com> Message-ID: <4387F649.10104@neurogrid.com> Or perhaps they are just embarressed by the ignomity of their previous attempts that they are waiting to actually have something of substance before presenting their new things. At least that's my reason. :-) CHEERS> SAM John Casey wrote: >hehe. perhaps everyone is just keeping their secrets to themselves ;P >in the hope that they can later patent their beautiful ideas. > >On 11/26/05, David Barrett wrote: > > >>Jacob -- >> >>What are you working on? I'm sure we'd all love to hear your ideas. >> >>coderman wrote: >> >> >>>i want a refund! >>> >>> >_______________________________________________ >p2p-hackers mailing list >p2p-hackers@zgp.org >http://zgp.org/mailman/listinfo/p2p-hackers >_______________________________________________ >Here is a web page listing P2P Conferences: >http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > From 01771 at iha.dk Sat Nov 26 19:04:22 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387C8F1.8010601@quinthar.com> References: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> <4387C8F1.8010601@quinthar.com> Message-ID: <200511262004.22744.01771@iha.dk> As it is now, i'm not working on p2p stuff, but next semester (after new year) it will change. I'm about to start on a "final project" and I have chosen to work with structured DHTs. I'm not done defining the project yet, but here is what i have in mind: 1. Implement several known and structured DHTs (like Chord, Kademlia, ...) with a common interface and compare them by running some tests. 2. Solve the "britney problem" either by using caching, a distributed sloppy hash table or some other method I'm not aware of yet. 3. Make "nodeId theft"/spoofing impossible. Right now I'm not sure how I will do it. 4. Implement a simple filesystem where all nodes have a synchronized index of the directory and file structure. Again, I'm not sure how I will do it. If someone got any suggestions or papers about this, then I'll really appreciate to hear about it/them. /Jacob On Saturday 26 November 2005 03:31, David Barrett wrote: > Jacob -- > > What are you working on? I'm sure we'd all love to hear your ideas. > > coderman wrote: > > i want a refund! > > > > On 11/25/05, Michael Liu wrote: > >>I was also in doubt too, I have joined this mailing list for 1 week, but > >> this post is the first one I received. > >> > >> > >> > >> > >>----- Original Message ----- > >>From: "Jacob Madsen" <01771@iha.dk> > >>To: > >>Sent: Saturday, November 26, 2005 9:52 AM > >>Subject: [p2p-hackers] Where do bright minds discuss p2p technology? > >> > >>>Hey > >>> > >>>When I subscribed this mailinglist about a year ago, there was a lot of > >>>activity. I really enjoyed watching the talk and discussion about > >>> different topics. > >>> > >>>The last months almost noone posted anything, so now im wondering where > >>> do people talk about peer-to-peer issues? > > > > _______________________________________________ > > p2p-hackers mailing list > > p2p-hackers@zgp.org > > http://zgp.org/mailman/listinfo/p2p-hackers > > _______________________________________________ > > Here is a web page listing P2P Conferences: > > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From sdaswani at boalthall.berkeley.edu Sat Nov 26 19:37:02 2005 From: sdaswani at boalthall.berkeley.edu (Susheel Daswani) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387D290.4040807@quinthar.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> <4387D290.4040807@quinthar.com> Message-ID: <1cd056b90511261137i65e98b00x7237adcb2f0c978d@mail.gmail.com> I'm in SFC too folks. We should have a p2p poker night or something. Susheel On 11/25/05, David Barrett wrote: > How many people on this list are in SF? It appears Lemon and I; anyone > else? Interested in a p2p-hackers night out? > > -david From egs+p2phackers at cs.cornell.edu Sat Nov 26 21:16:51 2005 From: egs+p2phackers at cs.cornell.edu (Emin Gun Sirer) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <200511262004.22744.01771@iha.dk> from "Jacob Madsen" at Nov 26, 2005 08:04:22 PM Message-ID: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> Hi Jacob, I am not sure what the Britney-problem is exactly (rather, I think the Britney problem is the sheer crappiness of her music, but you seem to be referring to something far more technical and possible fixable), but three things struck me about your note: - Since you are interested in caching, take a look at recent work on how caching can be used to improve the performance of DHTs. Coen and Shenker have a nice paper on how sqrt(N) caching in unstructured p2p systems can improve performance. Our work on Beehive (which is the engine behind CoDoNS, CobWeb, and Corona) showed how O(1) lookup times could be achieved on top of O(log N) DHTs with very modest replication costs. - Since Britney is involved in the problem definition, it's a safe bet that lawyers/RIAA/MPAA will have to be involved as well. You might want to look at recent work on anonymous communication systems, especially source rewriting systems (Tor, onions, crowds, mixes, ap3b, tarzan, etc), dining cryptographer networks (Herbivore, Chaum's DC-nets), and constant broadcast systems (P5). Anonymity is hard to combine with high performance and scalability, but there has been lots of interesting work in the last few years. - I encourage you, as well as everyone else on this list who is interested in designing, building and deploying large scale distributed systems (of any kind, not just peer-to-peer), and is interested in pursuing graduate studies, to apply to Cornell. Do drop me a note if you are thinking of applying or have applied. There is quite a bit of systems building activity here and this is an exciting time to be working on P2P. Existing infrastructure services are so broken in so many ways that there is a huge opportunity for impact. - egs Jacob Madsen writes: > >As it is now, i'm not working on p2p stuff, but next semester (after new year) >it will change. >I'm about to start on a "final project" and I have chosen to work with >structured DHTs. > >I'm not done defining the project yet, but here is what i have in mind: >1. Implement several known and structured DHTs (like Chord, Kademlia, ...) >with a common interface and compare them by running some tests. >2. Solve the "britney problem" either by using caching, a distributed >sloppy hash table or some other method I'm not aware of yet. >3. Make "nodeId theft"/spoofing impossible. Right now I'm not sure how I will >do it. >4. Implement a simple filesystem where all nodes have a synchronized index of >the directory and file structure. Again, I'm not sure how I will do it. > >If someone got any suggestions or papers about this, then I'll really >appreciate to hear about it/them. > >/Jacob From dbarrett at quinthar.com Sat Nov 26 21:55:26 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> References: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> Message-ID: <4388D9CE.3080202@quinthar.com> Emin Gun Sirer wrote: > Hi Jacob, > > I am not sure what the Britney-problem is exactly (rather, I think the > Britney problem is the sheer crappiness of her music, but you seem to be > referring to something far more technical and possible fixable), but > three things struck me about your note: Heh, the problem you cite is probably the more severe one, but my impression is the "Britney problem" is also the "hotspot" problem -- how do I avoid overloading any single node in my DHT when a given keyword becomes incredibly popular. -david From egs+p2phackers at cs.cornell.edu Sat Nov 26 22:41:43 2005 From: egs+p2phackers at cs.cornell.edu (Emin Gun Sirer) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4388D9CE.3080202@quinthar.com> from "David Barrett" at Nov 26, 2005 01:55:26 PM Message-ID: <200511262241.jAQMfhDh029233@cfs35.cs.cornell.edu> David Barrett writes: >> I am not sure what the Britney-problem is exactly (rather, I think the >> Britney problem is the sheer crappiness of her music, but you seem to be >> referring to something far more technical and possibly fixable), but >> three things struck me about your note: > >Heh, the problem you cite is probably the more severe one, but my >impression is the "Britney problem" is also the "hotspot" problem -- how >do I avoid overloading any single node in my DHT when a given keyword >becomes incredibly popular. Ah, that's an interesting problem. The only way I know to deal with hotspots is to dedicate more resources to the query terms causing the hotspot. The difficult question is then "how many nodes should I dedicate to serving an item that is ranked k in popularity? How many copies of popular items should I make and propagate throughout my network ?" This is exactly the question that Beehive tackles. The quick insight is, if you make no copies of an item, the home node bears all the load. If you copy a hot item to all N nodes in the network, load is reduced by a factor of N, and performance improves drastically since the object is available at the first node you consult. Unfortunately, the system would not scale if you tried to copy all the items to all the nodes. So somewhere in the middle is the optimal level of replication, at which the load placed by an item on each node carrying its replicas will be equal to the load placed by all other items on the nodes carrying their replicas, modulo some slop due to discretization, and subject to space and bandwidth constraints on the participating nodes. The Beehive result shows how to compute this optimal level of replication. The derivation is difficult to do in email, but the final formula is pretty succinct, and it doesn't take much more than a few days of coding to layer Beehive onto a DHT like Pastry, Chord, etc. Wish that was the only problem with Britney, - egs From zooko at zooko.com Sat Nov 26 23:25:43 2005 From: zooko at zooko.com (zooko@zooko.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4387DC58.2000205@panix.com> References: <20051126024559.90834.qmail@web53609.mail.yahoo.com> <4387D290.4040807@quinthar.com> <4387D96A.6090402@panix.com> <4387DA93.9010405@neurogrid.com> <4387DC58.2000205@panix.com> Message-ID: <20051126232543.9B2881E3F9@yumyum.zooko.com> > Whaa? I thought for sure that was futile. Send me an email when you > get back and let's do an Aloha p2p-hackers meetup. Hee hee! Next thing I know there will be p2p hackers in Halifax, Nova Scotia... Regards, Zooko From 01771 at iha.dk Sat Nov 26 23:26:12 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> References: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> Message-ID: <200511270026.13819.01771@iha.dk> Hello Emin > I am not sure what the Britney-problem is exactly (rather, I think the > Britney problem is the sheer crappiness of her music, but you seem to be > referring to something far more technical and possible fixable), but > three things struck me about your note: I agree with you about Britney :-) I have only studyed p2p technology (especially DHTs) as a hobby since there are no courses about p2p at the college where I'm a student. So I'm glad you bear with me in my lack of using the right techical term. I was refering to an earlier thread on this list with the subject "How to solve the "Britney problem"?". > - Since you are interested in caching, take a look at recent work on > how caching can be used to improve the performance of DHTs. Coen > and Shenker have a nice paper on how sqrt(N) caching in > unstructured p2p systems can improve performance. Our work on > Beehive (which is the engine behind CoDoNS, CobWeb, and Corona) > showed how O(1) lookup times could be achieved on top of O(log N) > DHTs with very modest replication costs. I never heard of Beehive, so I'll definently check it out. /Jacob From mgp at ucla.edu Sun Nov 27 04:47:28 2005 From: mgp at ucla.edu (Michael Parker) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4388D9CE.3080202@quinthar.com> References: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> <4388D9CE.3080202@quinthar.com> Message-ID: <20051126204728.xaig4gul40c8k8w0@mail.ucla.edu> Have you tried using a Distributed Sloppy Hash Table abstraction (DSHT)? It may not be appropriate in all situations, as it only returns a _subset_ of values stored under a particular key. Nonetheless, it seems quite efficient as it is what the Coral CDN uses to avoid swamping any one node. It works with Chord, Kademlia, and other topologies can be fit to use it (although not all -- Pastry comes to mind). See the paper here: http://www.coralcdn.org/docs/coral-iptps03.ps Regards, Mike Quoting David Barrett : > Emin Gun Sirer wrote: >> Hi Jacob, >> >> I am not sure what the Britney-problem is exactly (rather, I think the >> Britney problem is the sheer crappiness of her music, but you seem to be >> referring to something far more technical and possible fixable), but >> three things struck me about your note: > > Heh, the problem you cite is probably the more severe one, but my > impression is the "Britney problem" is also the "hotspot" problem -- > how do I avoid overloading any single node in my DHT when a given > keyword becomes incredibly popular. > > -david > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From enzomich at gmail.com Sun Nov 27 08:23:51 2005 From: enzomich at gmail.com (Enzo Michelangeli) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? References: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com><4387C8F1.8010601@quinthar.com> <200511262004.22744.01771@iha.dk> Message-ID: <0cf101c5f32b$f5158a20$0200a8c0@em.noip.com> ----- Original Message ----- From: "Jacob Madsen" <01771@iha.dk> To: "Peer-to-peer development." Sent: Sunday, November 27, 2005 3:04 AM Subject: Re: [p2p-hackers] Where do bright minds discuss p2p technology? [...] > 2. Solve the "britney problem" either by using caching, a > distributed sloppy hash table or some other method I'm not aware > of yet. That was discussed on the list a while ago: see the thread at http://zgp.org/pipermail/p2p-hackers/2004-December/002283.html . > 3. Make "nodeId theft"/spoofing impossible. Right now I'm not > sure how I will do it. Also this :-) http://zgp.org/pipermail/p2p-hackers/2005-April/002572.html I think that just storing in the DHT an unguessable nonce (or "random cookie"), never returned in aswers to queries but required in order to replace or delete the tuple, would do the job nicely for simple applications: the nonce is obviously known to the nodes storing the triple, but the chances of those colluding with the "thief" are negligible). The OpenDHT team has devised more sophisticated mechanisms for "community" scenarios when tuples stored by one client can be legitimately removed by another associated client. Enzo From john.casey at gmail.com Sun Nov 27 09:29:30 2005 From: john.casey at gmail.com (John Casey) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <20051126204728.xaig4gul40c8k8w0@mail.ucla.edu> References: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> <4388D9CE.3080202@quinthar.com> <20051126204728.xaig4gul40c8k8w0@mail.ucla.edu> Message-ID: On 11/27/05, Michael Parker wrote: > Have you tried using a Distributed Sloppy Hash Table abstraction > (DSHT)? It may not be appropriate in all situations, as it only returns > a _subset_ of values stored under a particular key. Nonetheless, it > seems quite efficient as it is what the Coral CDN uses to avoid > swamping any one node. It works with Chord, Kademlia, and other > topologies can be fit to use it (although not all -- Pastry comes to > mind). Why can't you use DSHT with Pastry ? don't you just cluster nodes into 3 different levels; local, regional, and global or somesuch by latency? and overflow URL pointers onto the penultimate nodes along the lookup pathes ? or do the local route convergence properties of Pastry somehow kill it ?? From sgentle at gmail.com Sun Nov 27 11:52:39 2005 From: sgentle at gmail.com (Sam Gentle) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started Message-ID: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> Hey all, I'm pretty new to the whole p2p area, but I'd love to get more involved with it and learn some new stuff. So, what would I want to read? What are key things I'd need to know? What sort of projects currently exist and what kind of a state are they in? I realise these are fairly broad questions, but I'd love to get up to scratch on my p2p-fu and maybe even generate some constructive list traffic at the same time. Any suggestions would be most welcome, even if only a plug for some project you've been working on. Cheers, Sam From 01771 at iha.dk Sun Nov 27 12:04:58 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> Message-ID: <200511271304.59304.01771@iha.dk> If I were you, I would probably read the papers on Kademlia, Chord and Pastry. I'm not saying they are the best DHTs around, but those 3 are among the most widely used DHTs and will give you an usefull insight in the DHT structure. On Sunday 27 November 2005 12:52, Sam Gentle wrote: > Hey all, > > I'm pretty new to the whole p2p area, but I'd love to get more > involved with it and learn some new stuff. So, what would I want to > read? What are key things I'd need to know? What sort of projects > currently exist and what kind of a state are they in? > > I realise these are fairly broad questions, but I'd love to get up to > scratch on my p2p-fu and maybe even generate some constructive list > traffic at the same time. Any suggestions would be most welcome, even > if only a plug for some project you've been working on. > > Cheers, > Sam > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From 01771 at iha.dk Sun Nov 27 12:09:33 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> Message-ID: <200511271309.34156.01771@iha.dk> Btw... Kademlia, Chord and Pastry are all structured by design, so you might want to read a paper on unstructured networks too, where topics like random searches are covered. I dont know of any good paper, but maybe someone else does? On Sunday 27 November 2005 12:52, Sam Gentle wrote: > Hey all, > > I'm pretty new to the whole p2p area, but I'd love to get more > involved with it and learn some new stuff. So, what would I want to > read? What are key things I'd need to know? What sort of projects > currently exist and what kind of a state are they in? > > I realise these are fairly broad questions, but I'd love to get up to > scratch on my p2p-fu and maybe even generate some constructive list > traffic at the same time. Any suggestions would be most welcome, even > if only a plug for some project you've been working on. > > Cheers, > Sam > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From sam at neurogrid.com Sun Nov 27 12:53:15 2005 From: sam at neurogrid.com (Sam Joseph) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <200511271309.34156.01771@iha.dk> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> <200511271309.34156.01771@iha.dk> Message-ID: <4389AC3B.3080006@neurogrid.com> How about this: http://www.neurogrid.net/JosephP2PMetaDataSearchLayers.pdf from http://www.neurogrid.net/php/publications.php A couple of years old now, but it tries to cover various approaches to meta-data based search in p2p networks of all different types. http://citeseer.ist.psu.edu/milojicic02peertopeer.html is another good general review paper on p2p CHEERS> SAM Jacob Madsen wrote: >Btw... Kademlia, Chord and Pastry are all structured by design, so you might >want to read a paper on unstructured networks too, where topics like random >searches are covered. I dont know of any good paper, but maybe someone else >does? > >On Sunday 27 November 2005 12:52, Sam Gentle wrote: > > >>Hey all, >> >>I'm pretty new to the whole p2p area, but I'd love to get more >>involved with it and learn some new stuff. So, what would I want to >>read? What are key things I'd need to know? What sort of projects >>currently exist and what kind of a state are they in? >> >>I realise these are fairly broad questions, but I'd love to get up to >>scratch on my p2p-fu and maybe even generate some constructive list >>traffic at the same time. Any suggestions would be most welcome, even >>if only a plug for some project you've been working on. >> >>Cheers, >>Sam >>_______________________________________________ >>p2p-hackers mailing list >>p2p-hackers@zgp.org >>http://zgp.org/mailman/listinfo/p2p-hackers >>_______________________________________________ >>Here is a web page listing P2P Conferences: >>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> >> >_______________________________________________ >p2p-hackers mailing list >p2p-hackers@zgp.org >http://zgp.org/mailman/listinfo/p2p-hackers >_______________________________________________ >Here is a web page listing P2P Conferences: >http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > From hoovernj at gmail.com Sun Nov 27 13:45:30 2005 From: hoovernj at gmail.com (hoovernj@gmail.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p, technology? Message-ID: <4389B87A.5020106@gmail.com> Bleh. More like "my colguges and I have devised a way to create a distributed hard drive colleges across..." In other words white papers :( > Or perhaps they are just embarressed by the ignomity of their previous > attempts that they are waiting to actually have something of substance > before presenting their new things. > > At least that's my reason. :-) > > CHEERS> SAM From m.rogers at cs.ucl.ac.uk Sun Nov 27 14:00:42 2005 From: m.rogers at cs.ucl.ac.uk (Michael Rogers) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <200511262004.22744.01771@iha.dk> References: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> <4387C8F1.8010601@quinthar.com> <200511262004.22744.01771@iha.dk> Message-ID: <4389BC0A.1000800@cs.ucl.ac.uk> Hi Jacob, > 1. Implement several known and structured DHTs (like Chord, Kademlia, ...) > with a common interface and compare them by running some tests. These papers might be worth a look: http://www.cs.washington.edu/homes/gummadi/papers/p1101-gummadi.pdf http://pdos.lcs.mit.edu/chord/papers/iptps-evol.pdf http://project-iris.net/irisbib/papers/dhtcomparison:iptps04/paper.pdf > 3. Make "nodeId theft"/spoofing impossible. Right now I'm not sure how I will > do it. Castro et al looked at this problem: http://www.research.microsoft.com/~antr/PAST/security.pdf > 4. Implement a simple filesystem where all nodes have a synchronized index of > the directory and file structure. Again, I'm not sure how I will do it. Might be worth looking at CFS, PAST and FARSITE. Cheers, Michael From sgentle at gmail.com Sun Nov 27 14:58:40 2005 From: sgentle at gmail.com (Sam Gentle) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <4389AC3B.3080006@neurogrid.com> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> <200511271309.34156.01771@iha.dk> <4389AC3B.3080006@neurogrid.com> Message-ID: <489e77c10511270658y2ccf9226y406e467be76c95c2@mail.gmail.com> On 11/27/05, Sam Joseph wrote: > http://citeseer.ist.psu.edu/milojicic02peertopeer.html > > is another good general review paper on p2p I'm about halfway through that now - it's quite good, thanks. On 11/27/05, joejoe99@softhome.net wrote: > check out http://www.dp2p.net/ Also very nice. I'm only really familiar with MUTE, Freenet and I2P out of those, so there should be good to have a look through. On 11/27/05, Jacob Madsen <01771@iha.dk> wrote: > If I were you, I would probably read the papers on Kademlia, Chord and Pastry. > I'm not saying they are the best DHTs around, but those 3 are among the most > widely used DHTs and will give you an usefull insight in the DHT structure. I'll definitely have a look at those. I see a lot of references to DHTs, especially on this list, so it'd be nice to get more familiar with them. Also, the Tapestry paper explained the mystery of Plaxton meshes (which really needs a Wikpedia entry), so that's something. It seems as though in most (all?) of those systems there's some form of "similarness" mapping between nodes, like with those Plexton meshes you have common number suffixes. Is that always the case, or just for certain types of networks? Sam From osokin at osokin.com Sun Nov 27 21:15:39 2005 From: osokin at osokin.com (Serguei Osokine) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <1cd056b90511261137i65e98b00x7237adcb2f0c978d@mail.gmail.com> Message-ID: > I'm in SFC too folks. We should have a p2p poker night or something. Hmm... if you're in SFC, then I guess I might say that I'm in SFC too. Count me in, but without poker. Best wishes - S.Osokine. 27 Nov 2005. -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On Behalf Of Susheel Daswani Sent: Saturday, November 26, 2005 11:37 AM To: Peer-to-peer development. Subject: Re: [p2p-hackers] Where do bright minds discuss p2p technology? I'm in SFC too folks. We should have a p2p poker night or something. Susheel On 11/25/05, David Barrett wrote: > How many people on this list are in SF? It appears Lemon and I; anyone > else? Interested in a p2p-hackers night out? > > -david _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From sdaswani at cs.stanford.edu Mon Nov 28 00:39:06 2005 From: sdaswani at cs.stanford.edu (Susheel Daswani) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: References: <1cd056b90511261137i65e98b00x7237adcb2f0c978d@mail.gmail.com> Message-ID: <1cd056b90511271639w6aa39784r55ad3c8876b8fc12@mail.gmail.com> Serguei, I actually moved to SFC, so I wasn't stretching the truth. Poker is purely optional too :). Susheel On 11/27/05, Serguei Osokine wrote: > > I'm in SFC too folks. We should have a p2p poker night or something. > > Hmm... if you're in SFC, then I guess I might say that I'm in > SFC too. Count me in, but without poker. > > Best wishes - > S.Osokine. > 27 Nov 2005. From dbarrett at quinthar.com Mon Nov 28 21:40:26 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC Message-ID: <438B794A.1080100@quinthar.com> So looks like there's a decent showing of P2P guys in San Francisco -- six by my count. How about sushi and beer this week at, say Ryoko? http://tinyurl.com/bkk5d Maybe, Wednesday, 9pm? Any objections or affirmations? -david From travis at redswoosh.net Mon Nov 28 21:56:25 2005 From: travis at redswoosh.net (Travis Kalanick) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <438B794A.1080100@quinthar.com> References: <438B794A.1080100@quinthar.com> Message-ID: <39025.67.188.193.83.1133214985.squirrel@webmail.redswoosh.net> Sounds good by me. I'll be there. Looking forward to meeting you all. Travis David Barrett said: > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? > > http://tinyurl.com/bkk5d > > Maybe, Wednesday, 9pm? Any objections or affirmations? > > -david > > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > Travis Kalanick Red Swoosh, Inc. Founder, Chairman travis@redswoosh.net (v) 310.666.1429 (f) 253.322.9478 AIM: ScourTrav123 From bmukherj at shoshin.uwaterloo.ca Mon Nov 28 22:48:06 2005 From: bmukherj at shoshin.uwaterloo.ca (Roop Mukherjee) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: <4389BC0A.1000800@cs.ucl.ac.uk> References: <4ef5fec60511251812q354b55c0v23a0579f7056b4e2@mail.gmail.com> <4387C8F1.8010601@quinthar.com> <200511262004.22744.01771@iha.dk> <4389BC0A.1000800@cs.ucl.ac.uk> Message-ID: Looks like the SFC folks will meet soon. For the rest of us with real winters;)- any p2p folks in the neighborhood of Ottawa, ON Canada, interested in having a similar meeting? - roop ______________________________________ From Serguei.Osokine at efi.com Mon Nov 28 23:02:39 2005 From: Serguei.Osokine at efi.com (Serguei Osokine) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC Message-ID: <4A60C83D027E224BAA4550FB1A2B120EC42736@fcexmb04.efi.internal> > Maybe, Wednesday, 9pm? Sorry - I'm busy on Wednesday... -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On Behalf Of David Barrett Sent: Monday, November 28, 2005 1:40 PM To: Peer-to-peer development. Subject: [p2p-hackers] P2P in SFC So looks like there's a decent showing of P2P guys in San Francisco -- six by my count. How about sushi and beer this week at, say Ryoko? http://tinyurl.com/bkk5d Maybe, Wednesday, 9pm? Any objections or affirmations? -david _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From dbarrett at quinthar.com Mon Nov 28 23:09:20 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <4A60C83D027E224BAA4550FB1A2B120EC42736@fcexmb04.efi.internal> References: <4A60C83D027E224BAA4550FB1A2B120EC42736@fcexmb04.efi.internal> Message-ID: <438B8E20.3030903@quinthar.com> What day/time would you propose? Serguei Osokine wrote: >>Maybe, Wednesday, 9pm? > > > Sorry - I'm busy on Wednesday... > > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of David Barrett > Sent: Monday, November 28, 2005 1:40 PM > To: Peer-to-peer development. > Subject: [p2p-hackers] P2P in SFC > > > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? > > http://tinyurl.com/bkk5d > > Maybe, Wednesday, 9pm? Any objections or affirmations? > > -david > > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From Serguei.Osokine at efi.com Mon Nov 28 23:18:00 2005 From: Serguei.Osokine at efi.com (Serguei Osokine) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC Message-ID: <4A60C83D027E224BAA4550FB1A2B120EC42737@fcexmb04.efi.internal> > What day/time would you propose? Monday, Tuesday, Wednesday, or Thursday next week? Any time after 8pm is fine with me. -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On Behalf Of David Barrett Sent: Monday, November 28, 2005 3:09 PM To: Peer-to-peer development. Subject: Re: [p2p-hackers] P2P in SFC What day/time would you propose? Serguei Osokine wrote: >>Maybe, Wednesday, 9pm? > > > Sorry - I'm busy on Wednesday... > > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of David Barrett > Sent: Monday, November 28, 2005 1:40 PM > To: Peer-to-peer development. > Subject: [p2p-hackers] P2P in SFC > > > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? > > http://tinyurl.com/bkk5d > > Maybe, Wednesday, 9pm? Any objections or affirmations? > > -david > > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From dbarrett at quinthar.com Mon Nov 28 23:19:37 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <4A60C83D027E224BAA4550FB1A2B120EC42737@fcexmb04.efi.internal> References: <4A60C83D027E224BAA4550FB1A2B120EC42737@fcexmb04.efi.internal> Message-ID: <438B9089.6030401@quinthar.com> So this week is out? No problem. Anyone else? Serguei Osokine wrote: >>What day/time would you propose? > > > Monday, Tuesday, Wednesday, or Thursday next week? > Any time after 8pm is fine with me. > > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of David Barrett > Sent: Monday, November 28, 2005 3:09 PM > To: Peer-to-peer development. > Subject: Re: [p2p-hackers] P2P in SFC > > > What day/time would you propose? > > Serguei Osokine wrote: > >>>Maybe, Wednesday, 9pm? >> >> >> Sorry - I'm busy on Wednesday... >> >>-----Original Message----- >>From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On >>Behalf Of David Barrett >>Sent: Monday, November 28, 2005 1:40 PM >>To: Peer-to-peer development. >>Subject: [p2p-hackers] P2P in SFC >> >> >>So looks like there's a decent showing of P2P guys in San Francisco -- >>six by my count. How about sushi and beer this week at, say Ryoko? >> >> http://tinyurl.com/bkk5d >> >>Maybe, Wednesday, 9pm? Any objections or affirmations? >> >>-david >> >> >> >>_______________________________________________ >>p2p-hackers mailing list >>p2p-hackers@zgp.org >>http://zgp.org/mailman/listinfo/p2p-hackers >>_______________________________________________ >>Here is a web page listing P2P Conferences: >>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >>_______________________________________________ >>p2p-hackers mailing list >>p2p-hackers@zgp.org >>http://zgp.org/mailman/listinfo/p2p-hackers >>_______________________________________________ >>Here is a web page listing P2P Conferences: >>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> >> > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > From sdaswani at berkeley.edu Mon Nov 28 23:24:41 2005 From: sdaswani at berkeley.edu (Susheel Daswani) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <438B9089.6030401@quinthar.com> References: <4A60C83D027E224BAA4550FB1A2B120EC42737@fcexmb04.efi.internal> <438B9089.6030401@quinthar.com> Message-ID: <1cd056b90511281524h2ccf78dam4ffea84084f0946f@mail.gmail.com> I may be able to make it this Wednesday for a bit. Next week might work too. Susheel On 11/28/05, David Barrett wrote: > So this week is out? No problem. Anyone else? > > Serguei Osokine wrote: > >>What day/time would you propose? > > > > > > Monday, Tuesday, Wednesday, or Thursday next week? > > Any time after 8pm is fine with me. > > > > -----Original Message----- > > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > > Behalf Of David Barrett > > Sent: Monday, November 28, 2005 3:09 PM > > To: Peer-to-peer development. > > Subject: Re: [p2p-hackers] P2P in SFC > > > > > > What day/time would you propose? > > > > Serguei Osokine wrote: > > > >>>Maybe, Wednesday, 9pm? > >> > >> > >> Sorry - I'm busy on Wednesday... > >> > >>-----Original Message----- > >>From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > >>Behalf Of David Barrett > >>Sent: Monday, November 28, 2005 1:40 PM > >>To: Peer-to-peer development. > >>Subject: [p2p-hackers] P2P in SFC > >> > >> > >>So looks like there's a decent showing of P2P guys in San Francisco -- > >>six by my count. How about sushi and beer this week at, say Ryoko? > >> > >> http://tinyurl.com/bkk5d > >> > >>Maybe, Wednesday, 9pm? Any objections or affirmations? > >> > >>-david > >> > >> > >> > >>_______________________________________________ > >>p2p-hackers mailing list > >>p2p-hackers@zgp.org > >>http://zgp.org/mailman/listinfo/p2p-hackers > >>_______________________________________________ > >>Here is a web page listing P2P Conferences: > >>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > >>_______________________________________________ > >>p2p-hackers mailing list > >>p2p-hackers@zgp.org > >>http://zgp.org/mailman/listinfo/p2p-hackers > >>_______________________________________________ > >>Here is a web page listing P2P Conferences: > >>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > >> > >> > > > > _______________________________________________ > > p2p-hackers mailing list > > p2p-hackers@zgp.org > > http://zgp.org/mailman/listinfo/p2p-hackers > > _______________________________________________ > > Here is a web page listing P2P Conferences: > > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > _______________________________________________ > > p2p-hackers mailing list > > p2p-hackers@zgp.org > > http://zgp.org/mailman/listinfo/p2p-hackers > > _______________________________________________ > > Here is a web page listing P2P Conferences: > > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From lemonobrien at yahoo.com Tue Nov 29 01:15:46 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <438B8E20.3030903@quinthar.com> Message-ID: <20051129011547.34494.qmail@web53605.mail.yahoo.com> I can come anytime...I think this would be neat; i don't know about you guys; but i own my own company; coming out with a product soon. I know david has iGlance...which is not in my space, but believe meeting other like minded people who know "peer" is the next big thing...sorry my friends; but the web is played out. el David Barrett wrote: What day/time would you propose? Serguei Osokine wrote: >>Maybe, Wednesday, 9pm? > > > Sorry - I'm busy on Wednesday... > > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of David Barrett > Sent: Monday, November 28, 2005 1:40 PM > To: Peer-to-peer development. > Subject: [p2p-hackers] P2P in SFC > > > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? > > http://tinyurl.com/bkk5d > > Maybe, Wednesday, 9pm? Any objections or affirmations? > > -david > > > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051128/5d210ed4/attachment.html From travis at redswoosh.net Tue Nov 29 01:44:52 2005 From: travis at redswoosh.net (Travis Kalanick) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <20051129011547.34494.qmail@web53605.mail.yahoo.com> References: <438B8E20.3030903@quinthar.com> <20051129011547.34494.qmail@web53605.mail.yahoo.com> Message-ID: <40513.67.188.193.83.1133228692.squirrel@webmail.redswoosh.net> Lemon, I agree with you. Since most people seem to be able to make the Wednesday time, maybe we should finalize on that. David, do we have a consensus? T Lemon Obrien said: > I can come anytime...I think this would be neat; i don't know about you > guys; but i own my own company; coming out with a product soon. I know > david has iGlance...which is not in my space, but believe meeting other > like minded people who know "peer" is the next big thing...sorry my > friends; but the web is played out. > > el > > David Barrett wrote: > What day/time would you propose? > > Serguei Osokine wrote: >>>Maybe, Wednesday, 9pm? >> >> >> Sorry - I'm busy on Wednesday... >> >> -----Original Message----- >> From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On >> Behalf Of David Barrett >> Sent: Monday, November 28, 2005 1:40 PM >> To: Peer-to-peer development. >> Subject: [p2p-hackers] P2P in SFC >> >> >> So looks like there's a decent showing of P2P guys in San Francisco -- >> six by my count. How about sushi and beer this week at, say Ryoko? >> >> http://tinyurl.com/bkk5d >> >> Maybe, Wednesday, 9pm? Any objections or affirmations? >> >> -david >> >> >> >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> >> > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > You don't get no juice unless you squeeze > Lemon Obrien, the Third._______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > Travis Kalanick Red Swoosh, Inc. Founder, Chairman travis@redswoosh.net (v) 310.666.1429 (f) 253.322.9478 AIM: ScourTrav123 From unixsmaxer at hotmail.com Tue Nov 29 01:59:31 2005 From: unixsmaxer at hotmail.com (Salem Mark) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework Message-ID: Hello All, I have been looking for a suitable P2P framework to build my application upon. I came across Gnutella, which in its pure architecture suffers from scalability problems due to flooding. I also came ascross JXTA. However, I found it to be complex and huge. DHT approaches such as FreePastry and Chord cannot support multi-criteria search and as far as I understood they can be used to answer exact-match queries only. I was just wondering if there are any P2P frameworks/APIs that I am missing. I am basically trying to extend the service discovery protocol within Jabber/XMPP, such that distributed jabber servers operate like registries and collaborate together in order to answer/process service-request queries. In order to do so, I believe I need a proper underlying network topology, that is scalable and robust. I though of using Gnutella and implement one of the "scalability-enhancing" techniques, such as random walks, iterative deepening, or routing indices. Any p2p frameworks I am missing? any suggestions or comments would be appreciated. Thanks. Regards, Salem _________________________________________________________________ No masks required! Use MSN Messenger to chat with friends and family. http://go.msnserver.com/HK/25382.asp From lemonobrien at yahoo.com Tue Nov 29 02:13:02 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <40513.67.188.193.83.1133228692.squirrel@webmail.redswoosh.net> Message-ID: <20051129021302.45977.qmail@web53606.mail.yahoo.com> i can also wait...i'm debuging :) Travis Kalanick wrote: Lemon, I agree with you. Since most people seem to be able to make the Wednesday time, maybe we should finalize on that. David, do we have a consensus? T Lemon Obrien said: > I can come anytime...I think this would be neat; i don't know about you > guys; but i own my own company; coming out with a product soon. I know > david has iGlance...which is not in my space, but believe meeting other > like minded people who know "peer" is the next big thing...sorry my > friends; but the web is played out. > > el > > David Barrett wrote: > What day/time would you propose? > > Serguei Osokine wrote: >>>Maybe, Wednesday, 9pm? >> >> >> Sorry - I'm busy on Wednesday... >> >> -----Original Message----- >> From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On >> Behalf Of David Barrett >> Sent: Monday, November 28, 2005 1:40 PM >> To: Peer-to-peer development. >> Subject: [p2p-hackers] P2P in SFC >> >> >> So looks like there's a decent showing of P2P guys in San Francisco -- >> six by my count. How about sushi and beer this week at, say Ryoko? >> >> http://tinyurl.com/bkk5d >> >> Maybe, Wednesday, 9pm? Any objections or affirmations? >> >> -david >> >> >> >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences >> >> > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > You don't get no juice unless you squeeze > Lemon Obrien, the Third._______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > Travis Kalanick Red Swoosh, Inc. Founder, Chairman travis@redswoosh.net (v) 310.666.1429 (f) 253.322.9478 AIM: ScourTrav123 _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051128/2d74a0cf/attachment.htm From lgonze at panix.com Tue Nov 29 02:30:02 2005 From: lgonze at panix.com (Lucas Gonze) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <20051129011547.34494.qmail@web53605.mail.yahoo.com> References: <20051129011547.34494.qmail@web53605.mail.yahoo.com> Message-ID: <438BBD2A.4060300@panix.com> Lemon Obrien wrote: > I can come anytime...I think this would be neat; i don't know about > you guys; but i own my own company; coming out with a product soon. I > know david has iGlance...which is not in my space, but believe meeting > other like minded people who know "peer" is the next big thing...sorry > my friends; but the web is played out. I wish I could be there, because I disagree with Lemon on the web thing. P2P is gradually being absorbed into the web. The next major step is a move from message passing to document passing. From lemonobrien at yahoo.com Tue Nov 29 03:11:45 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <438BBD2A.4060300@panix.com> Message-ID: <20051129031145.59685.qmail@web53603.mail.yahoo.com> >>is a move from message passing to document passing ? you'll always need a message to tell something to move...in physics its called energy. and yeah, i'm write; the web is dead. step 1. to becoming a p2p developer...get rid of meaningless bullshit and pull up pants. Lucas Gonze wrote: Lemon Obrien wrote: > I can come anytime...I think this would be neat; i don't know about > you guys; but i own my own company; coming out with a product soon. I > know david has iGlance...which is not in my space, but believe meeting > other like minded people who know "peer" is the next big thing...sorry > my friends; but the web is played out. I wish I could be there, because I disagree with Lemon on the web thing. P2P is gradually being absorbed into the web. The next major step is a move from message passing to document passing. _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051128/0617fb93/attachment.html From dbarrett at quinthar.com Tue Nov 29 04:06:12 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC In-Reply-To: <20051129021302.45977.qmail@web53606.mail.yahoo.com> References: <20051129021302.45977.qmail@web53606.mail.yahoo.com> Message-ID: <438BD3B4.4030200@quinthar.com> There's no hurry. Let's target next Wednesday to get the biggest "take". Here's the scoop: Ryoko's Sushi - Wednesday, 12/7 at 9pm - URL: http://tinyurl.com/bkk5d - Phone: (415) 775-1028 - Address: 619 Taylor St, San Francisco, CA 94102 Call me (801.860.0540) if you have trouble finding it. I've got Lemon, Travis, Susheel, and Serguei on the list. Laurent, Ryan -- you game? As for the rest, a ticket to San Francisco ain't so expensive... -david Lemon Obrien wrote: > i can also wait...i'm debuging :) > > */Travis Kalanick /* wrote: > > Lemon, I agree with you. Since most people seem to be able to make the > Wednesday time, maybe we should finalize on that. > > David, do we have a consensus? > > > T > > Lemon Obrien said: > > I can come anytime...I think this would be neat; i don't know > about you > > guys; but i own my own company; coming out with a product soon. I > know > > david has iGlance...which is not in my space, but believe meeting > other > > like minded people who know "peer" is the next big thing...sorry my > > friends; but the web is played out. > > > > el > > > > David Barrett wrote: > > What day/time would you propose? > > > > Serguei Osokine wrote: > >>>Maybe, Wednesday, 9pm? > >> > >> > >> Sorry - I'm busy on Wednesday... > >> > >> -----Original Message----- > >> From: p2p-hackers-bounces@zgp.org > [mailto:p2p-hackers-bounces@zgp.org]On > >> Behalf Of David Barrett > >> Sent: Monday, November 28, 2005 1:40 PM > >> To: Peer-to-peer development. > >> Subject: [p2p-hackers] P2P in SFC > >> > >> > >> So looks like there's a decent showing of P2P guys in San > Francisco -- > >> six by my count. How about sushi and beer this week at, say Ryoko? > >> > >> http://tinyurl.com/bkk5d > >> > >> Maybe, Wednesday, 9pm? Any objections or affirmations? > >> > >> -david > >> > >> > >> > >> _______________________________________________ > >> p2p-hackers mailing list > >> p2p-hackers@zgp.org > >> http://zgp.org/mailman/listinfo/p2p-hackers > >> _______________________________________________ > >> Here is a web page listing P2P Conferences: > >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > >> _______________________________________________ > >> p2p-hackers mailing list > >> p2p-hackers@zgp.org > >> http://zgp.org/mailman/listinfo/p2p-hackers > >> _______________________________________________ > >> Here is a web page listing P2P Conferences: > >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > >> > >> > > _______________________________________________ > > p2p-hackers mailing list > > p2p-hackers@zgp.org > > http://zgp.org/mailman/listinfo/p2p-hackers > > _______________________________________________ > > Here is a web page listing P2P Conferences: > > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > > > > > > You don't get no juice unless you squeeze > > Lemon Obrien, the > Third._______________________________________________ > > p2p-hackers mailing list > > p2p-hackers@zgp.org > > http://zgp.org/mailman/listinfo/p2p-hackers > > _______________________________________________ > > Here is a web page listing P2P Conferences: > > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > Travis Kalanick > Red Swoosh, Inc. > Founder, Chairman > travis@redswoosh.net > (v) 310.666.1429 > (f) 253.322.9478 > AIM: ScourTrav123 > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > > > You don't get no juice unless you squeeze > Lemon Obrien, the Third. > > > ------------------------------------------------------------------------ > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From mgp at ucla.edu Tue Nov 29 05:26:26 2005 From: mgp at ucla.edu (Michael Parker) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? In-Reply-To: References: <200511262116.jAQLGptL024550@cfs35.cs.cornell.edu> <4388D9CE.3080202@quinthar.com> <20051126204728.xaig4gul40c8k8w0@mail.ucla.edu> Message-ID: <20051128212626.d522a9ahsko0ccc0@mail.ucla.edu> On second thought, you should be able to implement a DSHT on Pastry. I don't know why, but I assumed that Pastry's two different metrics when routing -- first by prefix length, and then by numerical distance to the key -- wouldn't allow it, although perhaps it may complicate things a little. My bad. - Mike Parker Quoting John Casey : > On 11/27/05, Michael Parker wrote: >> Have you tried using a Distributed Sloppy Hash Table abstraction >> (DSHT)? It may not be appropriate in all situations, as it only returns >> a _subset_ of values stored under a particular key. Nonetheless, it >> seems quite efficient as it is what the Coral CDN uses to avoid >> swamping any one node. It works with Chord, Kademlia, and other >> topologies can be fit to use it (although not all -- Pastry comes to >> mind). > > Why can't you use DSHT with Pastry ? don't you just cluster nodes into > 3 different levels; local, regional, and global or somesuch by > latency? and overflow URL pointers onto the penultimate nodes along > the lookup pathes ? or do the local route convergence properties of > Pastry somehow kill it ?? > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From seth.johnson at RealMeasures.dyndns.org Tue Nov 29 11:04:12 2005 From: seth.johnson at RealMeasures.dyndns.org (Seth Johnson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Short-term MTV Gig for Jabber Developer in NYC Message-ID: <438C35AC.FDA6F6B7@RealMeasures.dyndns.org> -------- Original Message -------- Subject: [jadmin] short-term freelance gig at MTV in NYC /high-message-volume jabber1.4 deployment / flash zero-bytepatch for ejabberd? Date: Mon, 28 Nov 2005 23:43:50 -0500 From: "Kirschner, Larry" Reply-To: Jabber server administration list To: I'm using jabber as the socket-communication layer in a multiplayer game platform. I need it to perform much better than what I'm seeing. I'm looking to bring someone in as a freelancer to help me set up a jabber environment that meets the requirements below. You should be an expert admin on one of the open source jabbers (mainly looking at jabber1, and ejabberd so far). If you're interested email me with your rate, resume, etc. at larry.kirschner@mtvn.com. There's a crunch to get this done so it'd be great if you're available immediately. I'm guessing this will be a few days to a week or so of work. On the other hand if you're not looking for work but just want to chime in, any help/advice is greatly appreciated. REQUIREMENTS: * 10000 concurrent users* Users grouped into muc rooms in groups of 5 to 20* 10000 (muc) messages/second (these will mostly come from the GAME_SERVER user who will broadcast game events over a small pool of connections)* Small number of rooms with many users (500+). These are the game lobbies. Message rate to lobby rooms will be much lower than message rate to game rooms, mostly just LOBBY_ENTER and LOBBY_EXIT messages* Ability to support flash 0-byte XmlSocket connections Because of the flash requirement, I've been using jabber1.4, but it's not performing anywhere near the way I need it to. Instead it seems to be limiting messages to about 1 every 2 seconds and dropping (rather than delaying) messages sent in the interum. The current DEV deployment is: jabber 1.4.3muc 0.6.0jadc2s 0.9.0 (connected as a service on the same box as jabberd) DEV box is linux 2.6.9 with a single Intel Xeon 3.06GHz and 1GB ram. The production env box is beefier with 4 procs. I haven't been able to figure out what's causing the poor performance. I have all karma turned off and debug turned on. I'm very open to trying other open-source jabbers if they have a patch to work with flash XmlSockets. Ejabberd in particular looks like it would be a great fit for this platform. I've been looking around for an ejabberd/flash-socket patch, but all I find is lots of mail-list requests like this one asking for the patch. Thanks, Larry KirschnerSoftware ArchitectMTV Networks -------------- next part -------------- _______________________________________________ jadmin mailing list jadmin@jabber.org http://mail.jabber.org/mailman/listinfo/jadmin FAQ: http://www.jabber.org/about/jadminfaq.shtml _______________________________________________ From bneijt at gmail.com Tue Nov 29 10:35:00 2005 From: bneijt at gmail.com (Bram Neijt) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: References: Message-ID: <46c2f4ab0511290235s5cfefc68sac3aa67cd589b7ae@mail.gmail.com> I'm currently trying to document some P2P information, and found allot of networks and frameworks being similar (except maybe for ports). The most advanced, I think, is currently GNUnet ( www.gnunet.org ), but this is also slow in development because of it's large amount of features and complexity. Most frameworks also seem big on security an annonymity (like I2P, Tor union router). So you might be missing Tor, I2P and GNUnet. Good luck, Bram On 11/29/05, Salem Mark wrote: > I have been looking for a suitable P2P framework to build my application > upon. I came across Gnutella, which in its pure architecture suffers from > scalability problems due to flooding. I also came ascross JXTA. However, I > found it to be complex and huge. From Michael.Iles at cognos.com Tue Nov 29 11:44:01 2005 From: Michael.Iles at cognos.com (Iles, Michael) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Where do bright minds discuss p2p technology? Message-ID: <2D175FBDE19E3B4A84C23742848AF5A3029BCCC2@sottemail2.ent.ad.cognos.com> +1 for an Ottawa meeting, and +1 for sushi and beer :) Mike. (Ottawa, the land of real winters and overpriced sushi.) -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org] On Behalf Of Roop Mukherjee Sent: November 28, 2005 5:48 PM To: Peer-to-peer development. Subject: Re: [p2p-hackers] Where do bright minds discuss p2p technology? Looks like the SFC folks will meet soon. For the rest of us with real winters;)- any p2p folks in the neighborhood of Ottawa, ON Canada, interested in having a similar meeting? - roop ______________________________________ _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences This message may contain privileged and/or confidential information. If you have received this e-mail in error or are not the intended recipient, you may not use, copy, disseminate or distribute it; do not open any attachments, delete it immediately from your system and notify the sender promptly by e-mail that you have done so. Thank you. From 01771 at iha.dk Tue Nov 29 13:14:35 2005 From: 01771 at iha.dk (Jacob Madsen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? Message-ID: <200511291414.35852.01771@iha.dk> Hey, I recently read a slideshow made by Ian Clarke and Oskar Sandberg for DEFCON 13 and its titled "Routing in The Dark: Scalable Searches in Dark P2P Networks". After going through the slideshow I found this interview with Ian Clarke: http://p2pnet.net/story/5790 c/p from the article: "Clarke: The new thing here, which isn't all that clear from the NYT article, is that we have developed a way to create a globally scalable ?invite only? network. Think of Freenet meets Orkut. The idea is that not only will people not be able to know what you are doing with Freenet, but they won't even have any way to find out that you are running Freenet at all. This is important if running Freenet itself becomes illegal."" From what I understand the new approach is the invite only thing, where each node is only connected to "friends". I get that this contribute to hiding a nodes activity, since it wont make connection attempts to unknown nodes and wont allow unknown nodes to connect to itself, but I cant see how Freenet and any other "Darknet" will prevent the node from being discovered by sniffing the traffic. I know this sounds like a question about Freenet, but its more about hiding traffic in general when building a p2p darknet. Is it possible to "cloak" the traffic in known protocols like http? Or hide the traffic using another method? /Jacob From emmert at ftw.at Tue Nov 29 13:29:46 2005 From: emmert at ftw.at (Barbara Emmert) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <200511291414.35852.01771@iha.dk> Message-ID: <438C65DA.6911.14DC0243@localhost> > Is it possible to "cloak" the traffic in known protocols like http? Or hide > the traffic using another method? One method of "hiding traffic" can be found in www.cs.umd.edu/projects/p5/p5.pdf The authors propose that every peer generates an amount of traffic as random noise. An external observer will thus have difficulties in discerning signal packets from noise packets. From wolfgang.mueller at wiai.uni-bamberg.de Tue Nov 29 14:04:28 2005 From: wolfgang.mueller at wiai.uni-bamberg.de (Wolfgang Mueller) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <200511271309.34156.01771@iha.dk> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> <200511271309.34156.01771@iha.dk> Message-ID: <20051129140428.GA17176@portos.uni-bamberg.de> Dear all, I am a P2P similarity search person, and have some other literature suggestions (as suggestions always are, the're incomplete): > Btw... Kademlia, Chord and Pastry are all structured by design, so you might > want to read a paper on unstructured networks too, where topics like random > searches are covered. I dont know of any good paper, but maybe someone else > does? In terms of unstructured networks, I am a great fan of this stuff http://arxiv.org/abs/cond-mat/0406152 . It is data type agnostic, yet efficient, surprisingly efficient, if you consider that the preconditions to make it work are very weak. In addition to Neurogrid, there are plenty of other approaches out there that try to improve link structure based on semantics. The Firework Query model springs to mind: http://citeseer.ist.psu.edu/ng02peer.html and its refinements done in Bibster http://bibster.semanticweb.org/publications/publications.htm , http://citeseer.ist.psu.edu/context/2394099/715233 however, I guess some of Bibster's authors are on this list, right? In terms of DHT literature: http://www.srhea.net/papers/bamboo-usenix.pdf I like very much, as it provides great level of implementation detail. For P2P-IR the great classics IMHO are the papers about psearch and successors http://citeseer.ist.psu.edu/tang02psearch.html . A general view on similarity search using one approach given there is given in: http://pdos.csail.mit.edu/~rtm/papers/search_feasibility.ps . One approach to solving this problem is PIER: http://pier.cs.berkeley.edu/papers.html . A quite different approach to P2P-IR is PlanetP http://www.panic-lab.rutgers.edu/Research/planetp/ with scalable extensions Minerva http://www.mpi-sb.mpg.de/departments/d5/software/minerva/ and Rumorama (our pet here in Bamberg) http://portal.acm.org/citation.cfm?id=1099706&coll=ACM&dl=ACM&CFID=6 And I won't forget mentioning the Freenet-based FASD by Amr Kronfol. What is the current state of this, by the way? http://citeseer.ist.psu.edu/571354.html Disclaimer: I know this is pretty incomplete and rather cited at random, I am aware of plenty more papers e.g. at Stanford Peers and other "usual suspects ". Please view this rather as a starting point. Cheers, Wolfgang -- Dr. Wolfgang Mueller LS Medieninformatik Universitaet Bamberg From m.rogers at cs.ucl.ac.uk Tue Nov 29 14:10:39 2005 From: m.rogers at cs.ucl.ac.uk (Michael Rogers) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <200511291414.35852.01771@iha.dk> References: <200511291414.35852.01771@iha.dk> Message-ID: <438C615F.5070207@cs.ucl.ac.uk> Hi Jacob, As far as I know the Freenet developers are planning to use a plugin architecture, so it will be possible to develop different transport plugins, some of which could use steganography. However if the eavesdropper can see that your node is communicating 24/7 with a suspected Freenet node, the fact that the traffic looks like IRC in Swahili might not make much difference... I guess the best disguise would be another P2P protocol, so constant high-bandwidth traffic wouldn't look suspicious. GTK-Gnutella supports TLS-encrypted connections. Cheers, Michael From zooko at zooko.com Tue Nov 29 14:03:13 2005 From: zooko at zooko.com (zooko@zooko.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] darknet ~= (blacknet, f2f net) In-Reply-To: <200511291414.35852.01771@iha.dk> References: <200511291414.35852.01771@iha.dk> Message-ID: <20051129140314.046DD698@yumyum.zooko.com> It's a shame that the distinct concepts of "friend-to-friend net" [1] and "blacknet" [2, 3, 4, 5] are being munged together in the media under the rubric "darknet". The word "darknet" was coined, as far as I know, by Biddle, England, Peinado, Willman [6]. Last time I read their paper, it appeared to me to describe a system like Tim May's Blacknet -- an anonymous, secure, decentralized network which is used to transfer information illegally. It didn't mention anything about using friend-to-friend techniques to build such a network. However, the media seems to have started using the word "Darknet" to mean a friend-to-friend net and/or a blacknet [7, 8], thus simultaneously making it harder for people to think about blacknets which are based on other than friend-to-friend architectures and making it harder for people to think about friend-to-friend networks which are used for other than illegal information sharing. I place some of the blame for this development on the Freenet folks, who may be the first to promulgate this munging, and if they aren't the first they're certainly the most effective. Of course, courting controversy in the mass media is part of the Freenet strategy, and I'm not saying it's a bad strategy. But oh well. It is too late to change media usage, and it isn't a good idea to maintain technical jargon which is related to but subtly different from media terminology, so how about us technical folks, when we wish to denote a network-used-for-illegal-information-trading, use the original term "blacknet", and when we wish to denote a network-built-on-friend-to-friend, use "friend-to-friend net" or "f2f", and when we wish to refer to both of them together or to confuse visiting reporters, we use "darknet". Regards, Zooko [1] http://en.wikipedia.org/wiki/Friend-to-friend [2] http://www.privacyexchange.org/iss/confpro/cfpuntraceable.html [3] http://www.ussrback.com/crypto/misc/blacknet.html [4] http://www-personal.umich.edu/~ludlow/worries.txt [5] http://cypherpunks.venona.com/date/1993/08/msg00538.html [6] http://www.bearcave.com/misl/misl_tech/msdrm/darknet.htm [7] http://www.darknet.com/ [8] http://en.wikipedia.org/wiki/Darknet From zooko at zooko.com Tue Nov 29 14:17:13 2005 From: zooko at zooko.com (zooko@zooko.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <200511291414.35852.01771@iha.dk> References: <200511291414.35852.01771@iha.dk> Message-ID: <20051129141713.6A9CB698@yumyum.zooko.com> But in answer to your original question: > Is it possible to "cloak" the traffic in known protocols like http? Or hide > the traffic using another method? This is more or less the subject of steganography, which is subject is deep and tricky and academic and ill-applied. In particular, it is mostly applied to static texts rather than to interactive protocols. Here is a survey of it which is probably good, though I've not read it thoroughly myself: http://www.petitcolas.net/fabien/publications/journal.html Regards, Zooko From m.rogers at cs.ucl.ac.uk Tue Nov 29 14:36:18 2005 From: m.rogers at cs.ucl.ac.uk (Michael Rogers) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] darknet ~= (blacknet, f2f net) In-Reply-To: <20051129140314.046DD698@yumyum.zooko.com> References: <200511291414.35852.01771@iha.dk> <20051129140314.046DD698@yumyum.zooko.com> Message-ID: <438C6762.4030806@cs.ucl.ac.uk> zooko@zooko.com wrote: > The word "darknet" was coined, as far as I know, by Biddle, England, Peinado, > Willman [6]. Last time I read their paper, it appeared to me to describe a > system like Tim May's Blacknet -- an anonymous, secure, decentralized network > which is used to transfer information illegally. It didn't mention anything > about using friend-to-friend techniques to build such a network. You can't see it in the HTML version, but the caption to figure 3 appears (to me) to describe something like a friend-to-friend network: http://www.geocities.com/mirrormedia2/p2p/darknet5.pdf I agree with your suggested blacknet/darknet/f2f terminology though. Cheers, Michael From zooko at zooko.com Tue Nov 29 14:21:51 2005 From: zooko at zooko.com (zooko@zooko.com) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <20051129141713.6A9CB698@yumyum.zooko.com> References: <200511291414.35852.01771@iha.dk> <20051129141713.6A9CB698@yumyum.zooko.com> Message-ID: <20051129142151.8E1A035E4@yumyum.zooko.com> following up to myself to correct a mistake: > > Here is a survey of it > which is probably good, though I've not read it thoroughly myself: > > http://www.petitcolas.net/fabien/publications/journal.html I meant the "limits of steganography" article on that page. Here is the citeseer version: http://citeseer.ist.psu.edu/63482.html All praise citeseer. And would someone please hurry and decentralize it before it is too late? Regards, Zooko From danderson at gnuterra.com Tue Nov 29 15:36:35 2005 From: danderson at gnuterra.com (Drew Anderson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC - Add two more In-Reply-To: <438B794A.1080100@quinthar.com> Message-ID: Since Sushi and P2P are on the menu, we'd like to join in as well: Drew Anderson and Don Hoffman (Gnuterra Corporation, makers of Morpheus). Wednesday evening works for us or any other day really. Thanks, Drew -----Original Message----- From: David Barrett [mailto:dbarrett@quinthar.com] Sent: Monday, November 28, 2005 1:40 PM To: Peer-to-peer development. Subject: [p2p-hackers] P2P in SFC So looks like there's a decent showing of P2P guys in San Francisco -- six by my count. How about sushi and beer this week at, say Ryoko? http://tinyurl.com/bkk5d Maybe, Wednesday, 9pm? Any objections or affirmations? -david From jbj at forbidden.co.uk Tue Nov 29 15:55:57 2005 From: jbj at forbidden.co.uk (Jeremy James) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] P2P in SFC - Add two more In-Reply-To: References: Message-ID: <438C7A0D.6090504@forbidden.co.uk> > -----Original Message----- > From: David Barrett [mailto:dbarrett@quinthar.com] > Sent: Monday, November 28, 2005 1:40 PM > To: Peer-to-peer development. > Subject: [p2p-hackers] P2P in SFC > > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? Blimey - this looks to be quite an event. For the advantage of us folks on this side on the pond (and elsewhere in US/Canada/World, of course), I trust you'll make a note of any decent quotes, interesting ideas, good Sushi choices etc? Jeremy From gbildson at limepeer.com Tue Nov 29 16:33:55 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: Message-ID: > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of Salem Mark > Sent: Monday, November 28, 2005 9:00 PM > To: p2p-hackers@zgp.org > Subject: [p2p-hackers] p2p framework > > > Hello All, > > I came across Gnutella, which in its pure architecture suffers from > scalability problems due to flooding. Gnutella "flooding"? That is so 2002. Your phrase "iterative deepening" sounds more like the dynamic querying that we use now. Having said that, I don't think existing Gnutella protocols are clean enough for use as an extensible framework. But, I do always like to clarify the above point. Thanks -greg From agthorr at cs.uoregon.edu Tue Nov 29 16:45:30 2005 From: agthorr at cs.uoregon.edu (Daniel Stutzbach) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: References: Message-ID: <20051129164529.GD1120@cs.uoregon.edu> On Tue, Nov 29, 2005 at 11:33:55AM -0500, Greg Bildson wrote: > > I came across Gnutella, which in its pure architecture suffers from > > scalability problems due to flooding. > > Gnutella "flooding"? That is so 2002. Your phrase "iterative deepening" > sounds more like the dynamic querying that we use now. I find it amusing when people claim a functioning 2-million peer system doesn't scale. :-) -- Daniel Stutzbach Computer Science Ph.D Student http://www.barsoom.org/~agthorr University of Oregon From dcarboni at gmail.com Tue Nov 29 16:47:10 2005 From: dcarboni at gmail.com (Davide Carboni) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: References: Message-ID: <71b79fa90511290847jf1165b1l32ab63afcacede54@mail.gmail.com> > > Having said that, I don't think existing Gnutella protocols are clean enough > for use as an extensible framework. But, I do always like to clarify the > above point. This is a very interesting point of discussion. I'm interested in knowing your "extended" opinion about that. -- Le saghe non fanno diventare ciechi. (Lillo e Greg) -- http://people.crs4.it/dcarboni From adanar at ics.forth.gr Tue Nov 29 17:13:09 2005 From: adanar at ics.forth.gr (Haris Papadakis) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: <20051129164529.GD1120@cs.uoregon.edu> References: <20051129164529.GD1120@cs.uoregon.edu> Message-ID: On Tue, 29 Nov 2005, Daniel Stutzbach wrote: > On Tue, Nov 29, 2005 at 11:33:55AM -0500, Greg Bildson wrote: > > > I came across Gnutella, which in its pure architecture suffers from > > > scalability problems due to flooding. > > > > Gnutella "flooding"? That is so 2002. Your phrase "iterative deepening" > > sounds more like the dynamic querying that we use now. > > I find it amusing when people claim a functioning 2-million peer > system doesn't scale. :-) > Well, actually, either does not scale or does not give good coveragae. Cos as I have said in another list, the basic reason Gnutella scales is TTL, no? Is it not tha case in Gnutella: Scalability, coverage, pick one? I must have an email somewhere from a developer in Limewire saying that it is NOT the purpose of Gnutella to reach all the network.. Harris Papadakis ICS-FORTH From Serguei.Osokine at efi.com Tue Nov 29 17:52:54 2005 From: Serguei.Osokine at efi.com (Serguei Osokine) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework Message-ID: <4A60C83D027E224BAA4550FB1A2B120EC42738@fcexmb04.efi.internal> On Tuesday, November 29, 2005 Haris Papadakis wrote: > ...it is NOT the purpose of Gnutella to reach all the network. No, it is not - but it might do that anyway as a bonus, even at its current size. This study: http://www.grouter.net/gnutella/search.htm shows that with some simple proactive caching Gnutella can effectively search several million network nodes. Current implementations are not doing that - probably because the feeling is that no one needs that much coverage in a file-sharing application, so today dynamic querying mentioned by Greg, and such things as QRP (sort of a Bloom filter) are used instead. But if the wider network coverage is needed, the possibility is certainly there - especially since proactive caching is orthogonal to dynamic querying and other optimizations and can be used together with them. I'd say that reaching 10M nodes or so is not out of question, and this limit keeps growing, because it is directly proportional to the average node bandwidth and session time. Best wishes - S.Osokine. 29 Nov 2005. -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On Behalf Of Haris Papadakis Sent: Tuesday, November 29, 2005 9:13 AM To: Peer-to-peer development. Subject: Re: [p2p-hackers] p2p framework On Tue, 29 Nov 2005, Daniel Stutzbach wrote: > On Tue, Nov 29, 2005 at 11:33:55AM -0500, Greg Bildson wrote: > > > I came across Gnutella, which in its pure architecture suffers from > > > scalability problems due to flooding. > > > > Gnutella "flooding"? That is so 2002. Your phrase "iterative deepening" > > sounds more like the dynamic querying that we use now. > > I find it amusing when people claim a functioning 2-million peer > system doesn't scale. :-) > Well, actually, either does not scale or does not give good coveragae. Cos as I have said in another list, the basic reason Gnutella scales is TTL, no? Is it not tha case in Gnutella: Scalability, coverage, pick one? I must have an email somewhere from a developer in Limewire saying that it is NOT the purpose of Gnutella to reach all the network.. Harris Papadakis ICS-FORTH _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From matthew at matthew.at Tue Nov 29 17:55:40 2005 From: matthew at matthew.at (Matthew Kaufman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Amicima updates Message-ID: <200511291753.jATHrjU72911@where.matthew.at> Yesterday: November 28, 2005: New open-source releases of MFP, MFPNet, and MObj are available, incorporating feature enhancements and bug fixes from real-world experience. All users are encouraged to read the associated CHANGES.txt files and upgrade to the latest versions. See the downloads page. http://www.amicima.com/developers/downloads.html And Today: November 29, 2005: Interested in seeing how MFP and MFPNet can be used to build an application? Download and try out amiciPhone, our technology demonstration for Windows XP. http://www.amicima.com/applications Matthew Kaufman matthew@matthew.at matthew@amicima.com http://www.amicima.com From caihailong at gmail.com Tue Nov 29 17:54:52 2005 From: caihailong at gmail.com (Hailong Cai) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: Message-ID: <004301c5f50e$01f72ad0$cfa45d81@csewang03> There are a bunch of works that are built upon Gnutella-like topology while using other techniques to attack the scalability problem. You may have a look at these related works, although some of them are still a design rather than implementation. - GIA, sigcomm 2003 - Shortcuts, Infocom 2003 - hybrid search, Infocom 2005 - Foreseer, Middleware 2004 -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org] On Behalf Of Salem Mark Sent: Monday, November 28, 2005 8:00 PM To: p2p-hackers@zgp.org Subject: [p2p-hackers] p2p framework Hello All, I have been looking for a suitable P2P framework to build my application upon. I came across Gnutella, which in its pure architecture suffers from scalability problems due to flooding. I also came ascross JXTA. However, I found it to be complex and huge. DHT approaches such as FreePastry and Chord cannot support multi-criteria search and as far as I understood they can be used to answer exact-match queries only. I was just wondering if there are any P2P frameworks/APIs that I am missing. I am basically trying to extend the service discovery protocol within Jabber/XMPP, such that distributed jabber servers operate like registries and collaborate together in order to answer/process service-request queries. In order to do so, I believe I need a proper underlying network topology, that is scalable and robust. I though of using Gnutella and implement one of the "scalability-enhancing" techniques, such as random walks, iterative deepening, or routing indices. Any p2p frameworks I am missing? any suggestions or comments would be appreciated. Thanks. Regards, Salem _________________________________________________________________ No masks required! Use MSN Messenger to chat with friends and family. http://go.msnserver.com/HK/25382.asp _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From gbildson at limepeer.com Tue Nov 29 18:16:00 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: Message-ID: It scales and gives good coverage. Its goal is to reach as little of the network as required to produce reasonable results (150 to 250 + altlocs). If a search can't retrieve this many results with a full TTL (TTL=3, outdegree=30) broadcast then yes, the query will not exceed some maximum broadcast. Reaching the entire network != Scalability. Scalability == network survival with increasing # of users. As Serguei mentions, Gnutella has dynamic querying, TTL and flow control to limit traffic (in about that order). Thanks -greg > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of Haris Papadakis > Sent: Tuesday, November 29, 2005 12:13 PM > To: Peer-to-peer development. > Subject: Re: [p2p-hackers] p2p framework > > > On Tue, 29 Nov 2005, Daniel Stutzbach wrote: > > > On Tue, Nov 29, 2005 at 11:33:55AM -0500, Greg Bildson wrote: > > > > I came across Gnutella, which in its pure architecture suffers from > > > > scalability problems due to flooding. > > > > > > Gnutella "flooding"? That is so 2002. Your phrase > "iterative deepening" > > > sounds more like the dynamic querying that we use now. > > > > I find it amusing when people claim a functioning 2-million peer > > system doesn't scale. :-) > > > Well, actually, either does not scale or does not give good coveragae. Cos > as I have said in another list, the basic reason Gnutella scales is TTL, > no? Is it not tha case in Gnutella: Scalability, coverage, pick one? > I must have an email somewhere from a developer in Limewire saying that it > is NOT the purpose of Gnutella to reach all the network.. > > Harris Papadakis > ICS-FORTH > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From gbildson at limepeer.com Tue Nov 29 18:17:38 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: <71b79fa90511290847jf1165b1l32ab63afcacede54@mail.gmail.com> Message-ID: Do you mean Gnutella's use as a framework or otherwise? Thanks -greg > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of Davide Carboni > Sent: Tuesday, November 29, 2005 11:47 AM > To: Peer-to-peer development. > Subject: Re: [p2p-hackers] p2p framework > > > > > > Having said that, I don't think existing Gnutella protocols are > clean enough > > for use as an extensible framework. But, I do always like to > clarify the > > above point. > > This is a very interesting point of discussion. I'm interested in > knowing your "extended" opinion about that. > > -- > Le saghe non fanno diventare ciechi. > (Lillo e Greg) > -- > http://people.crs4.it/dcarboni > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From p2p-hackers at ryanb.org Tue Nov 29 18:29:09 2005 From: p2p-hackers at ryanb.org (Ryan Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <438C65DA.6911.14DC0243@localhost> References: <438C65DA.6911.14DC0243@localhost> Message-ID: On Tue, 29 Nov 2005, Barbara Emmert wrote: > The authors propose that every peer generates an amount of traffic as random > noise. An external observer will thus have difficulties in discerning signal > packets from noise packets. if you're truly serious (read: paranoid) about obscuring traffic, you'll want to go further than this. the mixmaster class of anonymous remailers have done solid work in this area for a long time. they might be worth a look. specifically, type ii mixmaster remailers go far beyond simply adding noise to the signal. they also prevent well-known vulnerabilities due to message sizes, timing, and sender/receiver patterns. type iii (mixminion) remailers do even more. http://www.iusmentis.com/technology/remailers/index-mix.html http://mixmaster.sourceforge.net/faq.shtml http://mixminion.net/ -Ryan -- http://ryan.barrett.name/ From strib at amsterdam.lcs.mit.edu Tue Nov 29 18:35:52 2005 From: strib at amsterdam.lcs.mit.edu (Jeremy Stribling) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <20051129142151.8E1A035E4@yumyum.zooko.com> References: <200511291414.35852.01771@iha.dk> <20051129141713.6A9CB698@yumyum.zooko.com> <20051129142151.8E1A035E4@yumyum.zooko.com> Message-ID: <438C9F88.2050803@pdos.lcs.mit.edu> zooko@zooko.com wrote: >All praise citeseer. And would someone please hurry and decentralize it before >it is too late? > Working on it. Should have something public within a few months: http://pdos.csail.mit.edu/papers/overcite:iptps05/index.html Jeremy From coderman at gmail.com Tue Nov 29 19:59:02 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] darknet ~= (blacknet, f2f net, vpn, small world) Message-ID: <4ef5fec60511291159i590c8b97r6ce81f4385c558fb@mail.gmail.com> On 11/29/05, zooko@zooko.com wrote: > > It's a shame that the distinct concepts of "friend-to-friend net" [1] and > "blacknet" [2, 3, 4, 5] are being munged together in the media under the rubric > "darknet". it would be nice to have an index of attributes and consequences of these networks. for example: who do you trust? - friends - associates - third parties - no one [reputation is hard] how do you identify? - password / phrase - hardware token - biometric [perhaps all of the above *grin*] how do you key? - public key / WoT - certificate authortity (PKI) - manual key distribution out of band - revocation and auditing how do you secure? - network traffic - applications and processes - hosts and operating systems - key storage - physical security even SSL/SSH/IKE get r00ted now and then and strong security at all these levels is incredibly difficult. these are the main differences i find interesting in all of the approaches. the rest is just throwing bits around. :P From elias at soe.ucsc.edu Tue Nov 29 20:14:28 2005 From: elias at soe.ucsc.edu (Elias Sinderson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: <20051129164529.GD1120@cs.uoregon.edu> References: <20051129164529.GD1120@cs.uoregon.edu> Message-ID: <438CB6A4.8020105@cse.ucsc.edu> Daniel Stutzbach wrote: > I find it amusing when people claim a functioning 2-million peer > system doesn't scale. :-) 'Scalability' is relative, and the definition is often contingent upon the requirements of the system at hand. For example, an online banking application that could handle 2M active users would clearly be considered scalable enough for the application domain. However, when most people use the term these days, and especially with respect to P2P systems, they are using the term in reference to internet-scale scalability. To whit, while a 2M peer system may seem impressive at first blanche, a 20M peer system is better; a 200M peer system is _much_ better; a 2B peer system begins to approximate what we really want (at slightly less than half the size of the IPv4 address space). The above represents a shift in scale of 3 orders of magnitude, something gnutella is clearly not capable of. In this sense, it is a tautology to say that gnutella doesn't scale. Sure, it may work well enough in a limited sense, but it is a fallacy to confuse that with true scalability. I mentioned the IPv4 address space, which is something like 4.29B or so. This was thought to be more than enough addresses, yet now we find ourselves in the middle of shifting to IPv6, which has on the order of 3.4*10^38 addresses... Excessive, perhaps, but at least there's room to grow. :-) So, yes, Gnutella may scale well enough, but it clearly doesn't define (much loess aproach) scalability in any meaningful sense. Regards, Elias From Serguei.Osokine at efi.com Tue Nov 29 20:21:47 2005 From: Serguei.Osokine at efi.com (Serguei Osokine) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) Message-ID: <4A60C83D027E224BAA4550FB1A2B120EC42739@fcexmb04.efi.internal> On Tuesday, November 29, 2005 Elias Sinderson wrote: > The above represents a shift in scale of 3 orders of magnitude, > something gnutella is clearly not capable of. Oh, I dunno - last time Gnutella had scalability problems, it was around 5K-10K nodes. After those problems were fixed, it started growing without any meltdowns from thousands to millions of nodes. These are the same three orders of magnuitude growth, and they were fairly painless. Why not another three orders of magnitude? What is it that is clear to you about Gnutella that makes it uncapable of growing a thousand more times? Best wishes - S.Osokine. 29 Nov 2005. -----Original Message----- From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On Behalf Of Elias Sinderson Sent: Tuesday, November 29, 2005 12:14 PM To: Peer-to-peer development. Subject: Re: [p2p-hackers] scalability (was: p2p framework) Daniel Stutzbach wrote: > I find it amusing when people claim a functioning 2-million peer > system doesn't scale. :-) 'Scalability' is relative, and the definition is often contingent upon the requirements of the system at hand. For example, an online banking application that could handle 2M active users would clearly be considered scalable enough for the application domain. However, when most people use the term these days, and especially with respect to P2P systems, they are using the term in reference to internet-scale scalability. To whit, while a 2M peer system may seem impressive at first blanche, a 20M peer system is better; a 200M peer system is _much_ better; a 2B peer system begins to approximate what we really want (at slightly less than half the size of the IPv4 address space). The above represents a shift in scale of 3 orders of magnitude, something gnutella is clearly not capable of. In this sense, it is a tautology to say that gnutella doesn't scale. Sure, it may work well enough in a limited sense, but it is a fallacy to confuse that with true scalability. I mentioned the IPv4 address space, which is something like 4.29B or so. This was thought to be more than enough addresses, yet now we find ourselves in the middle of shifting to IPv6, which has on the order of 3.4*10^38 addresses... Excessive, perhaps, but at least there's room to grow. :-) So, yes, Gnutella may scale well enough, but it clearly doesn't define (much loess aproach) scalability in any meaningful sense. Regards, Elias _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From agthorr at cs.uoregon.edu Tue Nov 29 20:24:00 2005 From: agthorr at cs.uoregon.edu (Daniel Stutzbach) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: <438CB6A4.8020105@cse.ucsc.edu> References: <20051129164529.GD1120@cs.uoregon.edu> <438CB6A4.8020105@cse.ucsc.edu> Message-ID: <20051129202359.GI1120@cs.uoregon.edu> On Tue, Nov 29, 2005 at 12:14:28PM -0800, Elias Sinderson wrote: > The above represents a shift in scale of 3 orders of magnitude, > something gnutella is clearly not capable of. It's not clear to me. Why do you believe Gnutella cannot scale 3 more orders of magnitude? -- Daniel Stutzbach Computer Science Ph.D Student http://www.barsoom.org/~agthorr University of Oregon From gbildson at limepeer.com Tue Nov 29 20:51:43 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: <438CB6A4.8020105@cse.ucsc.edu> Message-ID: The only thing that may not scale is the network bootstrap (initial entry point) mechanisms. Then the scalability is mostly constrained by how many new users join the network in a day - and those systems can be decentralized more as well so that issue could go away. I see no reason why the steady state network can't scale. I believe you are making suppositions that are just not true. Guess that would make this statement more of a nautology. ;-) Thanks -greg > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of Elias Sinderson > Sent: Tuesday, November 29, 2005 3:14 PM > To: Peer-to-peer development. > Subject: Re: [p2p-hackers] scalability (was: p2p framework) > > > Daniel Stutzbach wrote: > > > I find it amusing when people claim a functioning 2-million peer > > system doesn't scale. :-) > > 'Scalability' is relative, and the definition is often contingent upon > the requirements of the system at hand. For example, an online banking > application that could handle 2M active users would clearly be > considered scalable enough for the application domain. However, when > most people use the term these days, and especially with respect to P2P > systems, they are using the term in reference to internet-scale > scalability. To whit, while a 2M peer system may seem impressive at > first blanche, a 20M peer system is better; a 200M peer system is _much_ > better; a 2B peer system begins to approximate what we really want (at > slightly less than half the size of the IPv4 address space). > > The above represents a shift in scale of 3 orders of magnitude, > something gnutella is clearly not capable of. In this sense, it is a > tautology to say that gnutella doesn't scale. Sure, it may work well > enough in a limited sense, but it is a fallacy to confuse that with true > scalability. I mentioned the IPv4 address space, which is something like > 4.29B or so. This was thought to be more than enough addresses, yet now > we find ourselves in the middle of shifting to IPv6, which has on the > order of 3.4*10^38 addresses... Excessive, perhaps, but at least there's > room to grow. :-) > > So, yes, Gnutella may scale well enough, but it clearly doesn't define > (much loess aproach) scalability in any meaningful sense. > > > Regards, > Elias > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From gojomo at bitzi.com Tue Nov 29 21:33:57 2005 From: gojomo at bitzi.com (Gordon Mohr) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: References: Message-ID: <438CC945.8020305@bitzi.com> Greg Bildson wrote: > The only thing that may not scale is the network bootstrap (initial entry > point) mechanisms. Then the scalability is mostly constrained by how many > new users join the network in a day - and those systems can be decentralized > more as well so that issue could go away. Yes. And if the network did have 2 billion nodes, you could probably bootstrap by trying public addresses randomly, finding plenty of acceptable entry peers soon enough. - Gordon From wesley at felter.org Tue Nov 29 22:21:11 2005 From: wesley at felter.org (Wes Felter) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic from a darknet? In-Reply-To: <438C65DA.6911.14DC0243@localhost> References: <438C65DA.6911.14DC0243@localhost> Message-ID: <438CD457.5060703@felter.org> Barbara Emmert wrote: >>Is it possible to "cloak" the traffic in known protocols like http? Or hide >>the traffic using another method? > > > One method of "hiding traffic" can be found in > www.cs.umd.edu/projects/p5/p5.pdf > The authors propose that every peer generates an amount of traffic as > random noise. An external observer will thus have difficulties in > discerning signal packets from noise packets. Only terrorists generate a constant rate of random traffic. :-) (Maybe the actual solution is to make your computer appear to be a worm-infected spam zombie... TCP over spam-stego over SMTP anyone?) Wes Felter - wesley@felter.org From sam at neurogrid.com Wed Nov 30 00:21:28 2005 From: sam at neurogrid.com (Sam Joseph) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Agents and Peer-to-Peer Computing (AP2PC 2006) Call for Papers Message-ID: <438CF088.1010907@neurogrid.com> PRELIMINARY CALL FOR PAPERS/PARTICIPATION Fifth International Workshop on Agents and Peer-to-Peer Computing (AP2PC 2006) http://p2p.ingce.unibo.it/ held at AAMAS 2006 International Conference on Autonomous Agents and MultiAgent Systems Future University, Hakodate, Japan. from 8 May - 12 May 2006. Peer-to-peer (P2P) computing has attracted enormous media attention, initially spurred by the popularity of file sharing systems such as Napster, Gnutella, and Morpheus. More recently systems like BitTorrent and eDonkey have continued to sustain that attention. New techniques such as distributed hash-tables (DHTs), semantic routing, and Plaxton Meshes are being combined with traditional concepts such as Hypercubes, Trust Metrics and caching techniques to pool together the untapped computing resources at the "edges" of the internet. These new techniques and possibilities have generated a lot of interest in many industrial organizations, and has resulted in the creation of a P2P working group on standardization in this area. (http://www.irtf.org/charter?gtype=rg&group=p2prg). In P2P computing peers and services forego central coordination and dynamically organise themselves to support knowledge sharing and collaboration, in both cooperative and non-cooperative environments. The success of P2P systems strongly depends on a number of factors. Firstly, the ability to ensure equitable distribution of content and services. Economic and business models which rely on incentive mechanisms to supply contributions to the system are being developed, along with methods for controlling the "free riding" issue. Second, the ability to enforce provision of trusted services. Reputation based P2P trust management models are becoming a focus of the research community as a viable solution. The trust models must balance both constraints imposed by the environment (e.g. scalability) and the unique properties of trust as a social and psychological phenomenon. Recently, we are also witnessing a move of the P2P paradigm to embrace mobile computing in an attempt to achieve even higher ubiquitousness. The possibility of services related to physical location and the relation with agents in physical proximity could introduce new opportunities and also new technical challenges. Although researchers working on distributed computing, MultiAgent Systems, databases and networks have been using similar concepts for a long time, it is only fairly recently that papers motivated by the current P2P paradigm have started appearing in high quality conferences and workshops. Research in agent systems in particular appears to be most relevant because, since their inception, MultiAgent Systems have always been thought of as collections of peers. The MultiAgent paradigm can thus be superimposed on the P2P architecture, where agents embody the description of the task environments, the decision-support capabilities, the collective behavior, and the interaction protocols of each peer. The emphasis in this context on decentralization, user autonomy, dynamic growth and other advantages of P2P, also leads to significant potential problems. Most prominent among these problems are coordination: the ability of an agent to make decisions on its own actions in the context of activities of other agents, and scalability: the value of the P2P systems lies in how well they scale along several dimensions, including complexity, heterogeneity of peers, robustness, traffic redistribution, and so forth. It is important to scale up coordination strategies along multiple dimensions to enhance their tractability and viability, and thereby to widen potential application domains. These two problems are common to many large-scale applications. Without coordination, agents may be wasting their efforts, squander resources and fail to achieve their objectives in situations requiring collective effort. This workshop will bring together researchers working on agent systems and P2P computing with the intention of strengthening this connection. The increasing interest in this research area is evident in that the four previous editions of AP2PC has been among the most popular AAMAS workshops in terms of participation. Research in Agents and Peer to Peer is by its nature interdisciplinary and offers a challenges for several communities, such as distributed systems, networks and database systems. We believe that all of these communities have much to contribute in terms of moving this area forward. We seek high-quality and original contributions on the general theme of "Agents and P2P Computing" according to the following non-exhaustive list of topics of special interest: - Intelligent agent techniques for P2P computing - P2P computing techniques for MultiAgent Systems - The Semantic Web, Semantic Coordination Mechanisms and P2P systems - Scalability, coordination, robustness and adaptability in P2P systems - Self-organization and emergent behavior in P2P networks - E-commerce and P2P computing - Participation and Contract Incentive Mechanisms in P2P Systems - Computational Models of Trust and Reputation - Community of interest building and regulation, and behavioral norms - Intellectual property rights in P2P systems - P2P architectures - Scalable Data Structures for P2P systems - Services in P2P systems (service definition languages, service discovery, filtering and composition etc.) - Knowledge Discovery and P2P Data Mining Agents - P2P oriented information systems - Information ecosystems and P2P systems - Security issues in P2P networks - Mobile P2P - Pervasive computing based on P2P architectures (ad-hoc networks,wireless communication devices and mobile systems) - Grid computing solutions based on agents and P2P paradigms - Legal issues in P2P networks IMPORTANT DATES Abstract submission: 15th January 2006 Paper submission: 19th January 2006 Acceptance notification: 19th February 2006 Workshop: 9th May 2006 Camera ready for post-proceedings: 20th July 2006 REGISTRATION Accomodation and workshop registration will be handled by the AAMAS 2006 organization along with the main conference registration. PUBLICATION AND SUBMISSION INSTRUCTIONS Previously unpublished papers should be formatted according to the LNCS/LNAI author instructions for proceedings and they should not be longer than 12 pages (about 5000 words including figures, tables, references, etc.). Papers should be submitted as a pdf file through the Microsoft conference management system at the following url: https://msrcmt.research.microsoft.com/AP2PC2006/ As in preceding editions, where accepted papers have been published by Springer in the Lecture Notes on Computer Science series (2002 Vol. 2533, 2003 Vol. 2871, 2004 Vol. 3601, 2005 publication in progress), we are planning to publish revised versions of accepted papers in the same Springer series. We invite authors to compare their contributions with preceding papers presented at previous AP2PC workshops (http://www.informatik.uni-trier.de/~ley/db/conf/ap2pc/index.html). In addition, please consider here the evaluation criterion that our reviewers will be using; http://www.neurogrid.net/ap2pc2005/review-form.html ORGANIZING COMMITTEE Program Co-chairs Sonia Bergamaschi, Dept. of Science Engineering, University of Modena and Reggio-Emilia, via Vignolese, 905 - 41100 Modena Italy Tel. +39 059 2056132 - Fax +39 059 2056126 E-mail: bergamaschi.sonia@unimo.it Zoran Despotovic (Main Contact) Future Networking Lab, DoCoMo Communications Laboratories Europe, Landsberger Str. 312 80687 Munich, Germany E-mail: despotovic@docomolab-euro.com Sam Joseph Dept. of Information and Computer Science, University of Hawaii at Manoa, USA 1680 East-West Road, POST 309, Honolulu, HI 96822 E-mail: srjoseph@hawaii.edu Gianluca Moro Dept. of Electronics, Computer Science and Systems (DEIS) University of Bologna Via Venezia, 52 I-47023 Cesena (FC), Italy Tel. +39 0547 339237, Fax +39 0547 339208 Email: gmoro@deis.unibo.it PROGRAM COMMITTEE Karl Aberer, EPFL, Lausanne, Switzerland Alessandro Agostini, ITC-IRST, Trento, Italy Djamal Benslimane, Universite Claude Bernard, France Sonia Bergamaschi, University of Modena and Reggio-Emilia, Italy M. Brian Blake, Georgetown University, USA Rajkumar Buyya, University of Melbourne, Australia Paolo Ciancarini, University of Bologna, Italy Costas Courcoubetis, Athens University of Economics and Business, Greece Yogesh Deshpande, University of Western Sydney, Australia Asuman Dogac, Middle East Technical University, Turkey Boi V. Faltings, EPFL, Lausanne, Switzerland Maria Gini, University of Minnesota, USA Dina Q. Goldin, University of Connecticut, USA Chihab Hanachi, University of Toulouse, France Mark Klein, Massachusetts Institute of Technology, USA Matthias Klusch, DFKI, Saarbrucken, Germany Tan Kian Lee, National University of Singapore, Singapore Zakaria Maamar, Zayed University, UAE Wolfgang Mayer, University of South Australia, Australia Dejan Milojicic, Hewlett Packard Labs, USA Alberto Montresor, University of Bologna, Italy Luc Moreau, University of Southampton, UK Jean-Henry Morin, University of Geneve, Switzerland Andrea Omicini, University of Bologna, Italy Maria Orlowska, University of Queensland, Australia Aris. M. Ouksel, University of Illinois at Chicago, USA Mike Papazoglou, Tilburg University, Netherlands Mari'a S. Pe'rez-Herna'ndez, Universidad Polite'cnica de Madrid, Spain Paolo Petta, Austrian Research Institute for AI, Austria, Jean Marc Pierson, INSA de Lyon, France Jeremy Pitt, Imperial College, UK Dimitris Plexousakis, Institute of Computer Science, FORTH, Greece Martin Purvis, University of Otago, New Zealand Omer F. Rana, Cardiff University, UK Douglas S. Reeves, North Carolina State University, USA Thomas Risse, Fraunhofer IPSI, Darmstadt, Germany Pierangela Samarati, University of Milan, Italy Christophe Silbertin-Blanc, University of Toulouse, France Maarten van Steen, Vrije Universiteit, Netherlands Katia Sycara, Robotics Institute, Carnegie Mellon University, USA Peter Triantafillou, Technical University of Crete, Greece Anand Tripathi, University of Minnesota, USA Vijay K. Vaishnavi, Georgia State University, USA Francisco Valverde-Albacete, Universidad Carlos III de Madrid, Spain Maurizio Vincini, University of Modena and Reggio-Emilia, Italy Fang Wang, BTexact Technologies, UK Gerhard Weiss, Technische Universitaet, Germany Bin Yu, North Carolina State University, USA Franco Zambonelli, University of Modena and Reggio-Emilia, Italy From enzomich at gmail.com Wed Nov 30 00:32:10 2005 From: enzomich at gmail.com (Enzo Michelangeli) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] How is it possible to hide the traffic froma darknet? References: <438C65DA.6911.14DC0243@localhost> <438CD457.5060703@felter.org> Message-ID: <12cf01c5f545$9e55d160$0200a8c0@em.noip.com> ----- Original Message ----- From: "Wes Felter" Sent: Wednesday, November 30, 2005 6:21 AM > (Maybe the actual solution is to make your computer appear to be a > worm-infected spam zombie... TCP over spam-stego over SMTP anyone?) That was done by Peter Wayner during the last millennium ("Disappearing Cryptography", 1996, http://www.amazon.com/gp/product/1558607692/ ) and implemented here: http://www.spammimic.com/ Enzo From sbest at best.com Wed Nov 30 01:18:05 2005 From: sbest at best.com (Scott C. Best) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Re: P2P in SFC In-Reply-To: <20051129052645.620F93FE08@capsicum.zgp.org> References: <20051129052645.620F93FE08@capsicum.zgp.org> Message-ID: <20051130005752.Q69048@kaboodle.org> I don't think I can make it next week; Wednesday's are date night with my wife, and while the sushi would be a hit...I'm worried she'd find the conversation less than thrilling. :*) If something falls thru with the babysitters, though, I may try to make it: my company is looking to hire a p2p developer in 2006 for either short-term and long-term work. Similar to Amicima, we're building software plugins for a user-to-user connection system called "echoWare". We recently announced a remote-support system based on it and VNC, and it's getting some pretty good traction: http://software.newsforge.com/software/05/11/14/2129224.shtml?tid=133 Right now, echoWare is an open-source Windows DLL, but our porting efforts to Linux should be done next month. Once that's done, I'd like to extend the protocol so that the echoServer (the packet relay server that interconnects echoWare clients) first attempts to interconnect clients via TCP/UDP punch-thru, before "falling back" to packet-buffering. The redone echoServer will also be open-sourced in Linux so it can utilize raw sockets as part of the mediation. Hopefully someone in the SF Bay area crowd is interested in hearing more details along with their Unagi. :) cheers, Scott sbest@echogent.com > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of David Barrett > Sent: Monday, November 28, 2005 1:40 PM > To: Peer-to-peer development. > Subject: [p2p-hackers] P2P in SFC > > > So looks like there's a decent showing of P2P guys in San Francisco -- > six by my count. How about sushi and beer this week at, say Ryoko? > > http://tinyurl.com/bkk5d > > Maybe, Wednesday, 9pm? Any objections or affirmations? > > -david From matthew at matthew.at Wed Nov 30 02:12:15 2005 From: matthew at matthew.at (Matthew Kaufman) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Re: P2P in SFC In-Reply-To: <20051130005752.Q69048@kaboodle.org> Message-ID: <200511300210.jAU2AIU73725@where.matthew.at> The two of us here at amicima can probably spin up there, though it is 90+ min away, so we'd personally like it to be a little earlier in the evening :) Matthew From joejoe99 at softhome.net Wed Nov 30 00:51:15 2005 From: joejoe99 at softhome.net (joejoe99@softhome.net) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: References: Message-ID: On Tue, 29 Nov 2005 01:59:31 +0000 "Salem Mark" wrote: > I have been looking for a suitable P2P framework to build > my application upon. > I was just wondering if there are any P2P frameworks/APIs > that I am missing. http://kenosis.sourceforge.net/ From lemonobrien at yahoo.com Wed Nov 30 03:15:04 2005 From: lemonobrien at yahoo.com (Lemon Obrien) Date: Sat Dec 9 22:13:04 2006 Subject: ah oh...RE: [p2p-hackers] Re: P2P in SFC In-Reply-To: <200511300210.jAU2AIU73725@where.matthew.at> Message-ID: <20051130031504.40457.qmail@web53605.mail.yahoo.com> i think the restaraunt, 'ryoko' is small; if my memory fails me; i use to live downtown. am i right? lemon Matthew Kaufman wrote: The two of us here at amicima can probably spin up there, though it is 90+ min away, so we'd personally like it to be a little earlier in the evening :) Matthew _______________________________________________ p2p-hackers mailing list p2p-hackers@zgp.org http://zgp.org/mailman/listinfo/p2p-hackers _______________________________________________ Here is a web page listing P2P Conferences: http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences You don't get no juice unless you squeeze Lemon Obrien, the Third. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zgp.org/pipermail/p2p-hackers/attachments/20051129/a33f1784/attachment.htm From dbarrett at quinthar.com Wed Nov 30 06:48:20 2005 From: dbarrett at quinthar.com (David Barrett) Date: Sat Dec 9 22:13:04 2006 Subject: ah oh...RE: [p2p-hackers] Re: P2P in SFC In-Reply-To: <20051130031504.40457.qmail@web53605.mail.yahoo.com> References: <20051130031504.40457.qmail@web53605.mail.yahoo.com> Message-ID: <1133333303.7A28C7@dl11.dngr.org> I prefer to think of it as "cozy". But not to fear, it has a decent sized back room. Regardless, let's wait for the final guest list before deciding if we switch locales. On Tue, 29 Nov 2005 10:37 pm, Lemon Obrien wrote: > i think the restaraunt, 'ryoko' is small; if my memory fails me; i use > to live downtown. > > am i right? > > lemon > > Matthew Kaufman wrote: > >> The two of us here at amicima can probably spin up there, though it is >> 90+ >> min away, so we'd personally like it to be a little earlier in the >> evening >> :) >> >> Matthew >> >> _______________________________________________ >> p2p-hackers mailing list >> p2p-hackers@zgp.org >> http://zgp.org/mailman/listinfo/p2p-hackers >> _______________________________________________ >> Here is a web page listing P2P Conferences: >> http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > You don't get no juice unless you squeeze > Lemon Obrien, the Third. From gwendal.simon at francetelecom.com Wed Nov 30 07:50:51 2005 From: gwendal.simon at francetelecom.com (SIMON Gwendal RD-MAPS-ISS) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) Message-ID: If we assume that the link structure relies on some semantic properties, the partial flooding of the network is a a real chance for the personalization of the search. Results will be more relevant if you restrict your request to semantically close neighbors. Thus, for me, "internet" means "graph" or "distributed system" but I can understand that these responses don't satisfy a vast majority of humans. The first hit in Google is... "Internet Explorer" ! I guess that if I ask to this list what is "internet", I will have few IE responses. Note that this strategy admits flaws as it is possible that I could never know that internet is also used to make money because my semantic surroundings is not related to business. But, anyhow, "not so open-minded egocentric results" or "majority-based results", that is the question... We develop this idea in open-source p2p system, namely Maay. A very early pre-alpha release is available at : http://maay.netofpeers.net -------------- Gwendal Simon France Telecom R&D http://solipsis.netofpeers.net > -----Message d'origine----- > De : p2p-hackers-bounces@zgp.org > [mailto:p2p-hackers-bounces@zgp.org] De la part de Gordon Mohr > Envoy? : mardi 29 novembre 2005 22:34 > ? : Peer-to-peer development. > Objet : Re: [p2p-hackers] scalability (was: p2p framework) > > Greg Bildson wrote: > > The only thing that may not scale is the network bootstrap > (initial entry > > point) mechanisms. Then the scalability is mostly > constrained by how many > > new users join the network in a day - and those systems can > be decentralized > > more as well so that issue could go away. > > Yes. And if the network did have 2 billion nodes, you > could probably bootstrap by trying public addresses > randomly, finding plenty of acceptable entry peers > soon enough. > > - Gordon > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From fis at wiwi.hu-berlin.de Wed Nov 30 09:46:15 2005 From: fis at wiwi.hu-berlin.de (Matthias Fischmann) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: <46c2f4ab0511290235s5cfefc68sac3aa67cd589b7ae@mail.gmail.com> References: <46c2f4ab0511290235s5cfefc68sac3aa67cd589b7ae@mail.gmail.com> Message-ID: <20051130094614.GA27847@localhost.localdomain> a few remarks: - GNUnet: i had a look at it a while ago and my estimate then was that it would die away. too many design decisions are interwoven in too much an ad-hoc fashion. some of those decisions (crypto issues, the overlay topology, etc.) have become obsolete, but cannot be replaced without breaking the whole thing. i myself can't see any reason for ever touching it again. - tor (the onion router) is not a p2p *framework*, but a very specific application for anonymizing tcp streams in a p2p way. good design, though, and it might contain some code that can be reused for other projects. anonymity is always a good thing to start from. but you might have other problems to address first. - i know very little about i2p, but i think it is another chaum mix for anonymizing tcp streams. in contrast to tor, it doesn't connect to the non-i2p world as nicely, which may have made the design simpler and more elegant. same as above, though: don't you need something else? cheers, matthias On Tue, Nov 29, 2005 at 11:35:00AM +0100, Bram Neijt wrote: > To: "Peer-to-peer development." > From: Bram Neijt > Date: Tue, 29 Nov 2005 11:35:00 +0100 > Subject: Re: [p2p-hackers] p2p framework > > I'm currently trying to document some P2P information, and found allot > of networks and frameworks being similar (except maybe for ports). > > The most advanced, I think, is currently GNUnet ( www.gnunet.org ), > but this is also slow in development because of it's large amount of > features and complexity. > Most frameworks also seem big on security an annonymity (like I2P, Tor > union router). > > So you might be missing Tor, I2P and GNUnet. > > Good luck, > Bram > > On 11/29/05, Salem Mark wrote: > > I have been looking for a suitable P2P framework to build my application > > upon. I came across Gnutella, which in its pure architecture suffers from > > scalability problems due to flooding. I also came ascross JXTA. However, I > > found it to be complex and huge. > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051130/e1312519/attachment.pgp From fis at wiwi.hu-berlin.de Wed Nov 30 09:49:37 2005 From: fis at wiwi.hu-berlin.de (Matthias Fischmann) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: <438CB6A4.8020105@cse.ucsc.edu> References: <20051129164529.GD1120@cs.uoregon.edu> <438CB6A4.8020105@cse.ucsc.edu> Message-ID: <20051130094937.GB27847@localhost.localdomain> On Tue, Nov 29, 2005 at 12:14:28PM -0800, Elias Sinderson wrote: > 'Scalability' is relative, and the definition is often contingent upon > [...] > better; a 2B peer system begins to approximate what we really want (at > slightly less than half the size of the IPv4 address space). you are aware that this planet currently inhabits only 1B people that are connected to the internet at all, are you? (-: of course you can always be optimistic and think ahead, but still... m. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051130/f5aeae42/attachment.pgp From fis at wiwi.hu-berlin.de Wed Nov 30 09:53:43 2005 From: fis at wiwi.hu-berlin.de (Matthias Fischmann) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] scalability (was: p2p framework) In-Reply-To: <20051130094937.GB27847@localhost.localdomain> References: <20051129164529.GD1120@cs.uoregon.edu> <438CB6A4.8020105@cse.ucsc.edu> <20051130094937.GB27847@localhost.localdomain> Message-ID: <20051130095343.GC27847@localhost.localdomain> > you are aware that this planet currently inhabits only 1B people that ^^^^^^^^ tried to be smart, and failed. (-: 'is inhabited by'. cheers, m. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Digital signature Url : http://zgp.org/pipermail/p2p-hackers/attachments/20051130/def4a906/attachment.pgp From m.rogers at cs.ucl.ac.uk Wed Nov 30 10:41:52 2005 From: m.rogers at cs.ucl.ac.uk (Michael Rogers) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: <20051130094614.GA27847@localhost.localdomain> References: <46c2f4ab0511290235s5cfefc68sac3aa67cd589b7ae@mail.gmail.com> <20051130094614.GA27847@localhost.localdomain> Message-ID: <438D81F0.9060908@cs.ucl.ac.uk> Matthias Fischmann wrote: > - tor (the onion router) is not a p2p *framework*, but a very > specific application for anonymizing tcp streams in a p2p way. I wouldn't even call it P2P - there's a central and fairly static list of Tor routers. Cheers, Michael From bneijt at gmail.com Wed Nov 30 12:07:22 2005 From: bneijt at gmail.com (Bram Neijt) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] State of GNUnet 0.7.0 (Re: p2p framework) Message-ID: <46c2f4ab0511300407x4558fca6sd265b6449154efb0@mail.gmail.com> Hi. everybody. I'm just beginning at looking into P2P and started a side-line project. However, I have future dreams to develop a P2P client for distributed 3D data sharing, distributed IRC and a community/mail system. So, I'm also looking for a framework. Now I'm not out for speed, but am looking for: secure and annonymous but identifiable clients. Although I'm not really content with the gnunetd server, I though GNUnet would be a good candidate. Because I'll probably work out my own library (C++ fan) it's more the core protocol I'm worried about. Any suggestions on where to focus my attention? Greetings, Bram PS This is a reply on this part of an earlier message: On 11/30/05, Matthias Fischmann wrote: > a few remarks: > - GNUnet: i had a look at it a while ago and my estimate then was > that it would die away. too many design decisions are interwoven > in too much an ad-hoc fashion. some of those decisions (crypto > issues, the overlay topology, etc.) have become obsolete, but > cannot be replaced without breaking the whole thing. i myself > can't see any reason for ever touching it again. From dcarboni at gmail.com Wed Nov 30 18:16:35 2005 From: dcarboni at gmail.com (Davide Carboni) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] p2p framework In-Reply-To: References: <71b79fa90511290847jf1165b1l32ab63afcacede54@mail.gmail.com> Message-ID: <71b79fa90511301016q54c57883se119ee54ea01212c@mail.gmail.com> On 11/29/05, Greg Bildson wrote: > Do you mean Gnutella's use as a framework or otherwise? > Yes I do. My question is: are there some implementation of gnutella that can be used to build upon new applications and to develop new services (beyond simple file sharing) ? D. From ian.clarke at gmail.com Wed Nov 30 18:48:12 2005 From: ian.clarke at gmail.com (Ian Clarke) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Getting started In-Reply-To: <20051129140428.GA17176@portos.uni-bamberg.de> References: <489e77c10511270352u5472d55ej2193959890266820@mail.gmail.com> <200511271309.34156.01771@iha.dk> <20051129140428.GA17176@portos.uni-bamberg.de> Message-ID: <823242bd0511301048x44978d20w@mail.gmail.com> On 29/11/05, Wolfgang Mueller wrote: > And I won't forget mentioning the Freenet-based FASD by Amr Kronfol. > What is the current state of this, by the way? > http://citeseer.ist.psu.edu/571354.html To my knowledge, Amr did not take this any further after his paper, which is a shame. Ian. From rrrw at neofonie.de Wed Nov 30 20:07:23 2005 From: rrrw at neofonie.de (Ronald Wertlen) Date: Sat Dec 9 22:13:04 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: <20051130095529.6CAE83FEB8@capsicum.zgp.org> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> Message-ID: <438E067B.2040408@neofonie.de> Hi, Gnutella-bashing certainly may be fun, the truth is, it is tremendously well-adapted for its purpose (I think Serguei's said the relevant stuff). However, I also believe it is pretty clear that from a search point of view, a random super-peer based network does not scale - it is never going to get the kind of precision and recall that we would call intelligent. It would be too slow or too inaccurate. (This belief may be substantiated by looking at one of the best search and retrieval super-peer networks we know - our brains (menufactured by millenia of evolution or a master craftsman ;-)) - and that's certainly not randomly structured, although parts of it probably are.) To sum up some: Gnutella is great in a non-critical scenario, but sucks for obsessive science types. ;-) best wishes, Ron From agthorr at cs.uoregon.edu Wed Nov 30 21:05:11 2005 From: agthorr at cs.uoregon.edu (Daniel Stutzbach) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: <438E067B.2040408@neofonie.de> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> Message-ID: <20051130210510.GH2800@cs.uoregon.edu> On Wed, Nov 30, 2005 at 09:07:23PM +0100, Ronald Wertlen wrote: > However, I also believe it is pretty clear that from a search point of > view, a random super-peer based network does not scale - it is never > going to get the kind of precision and recall that we would call > intelligent. It would be too slow or too inaccurate. Instead of saying "Gnutella does not scale", I think it would be more accurate to say "Gnutella does not perform the operation I am interested in". -- Daniel Stutzbach Computer Science Ph.D Student http://www.barsoom.org/~agthorr University of Oregon From coderman at gmail.com Wed Nov 30 21:38:46 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: <20051130210510.GH2800@cs.uoregon.edu> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> <20051130210510.GH2800@cs.uoregon.edu> Message-ID: <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> On 11/30/05, Daniel Stutzbach wrote: > Instead of saying "Gnutella does not scale", I think it would be more > accurate to say "Gnutella does not perform the operation I am > interested in". perhaps the following are more accurate observations: - it is difficult to protect gnutella protocol against malicious / aggressive peers - it is difficult to conserve bandwidth consumption for large gnutella peer groups i implemented a weighted iterative discovery protocol a while back called 'alpine' that ordered destination peer lists used for resource discovery by the relative quality associated with a given peer derived from past interactions (past responses, usefulness of resources provided, etc). the transport level was a logical UDP connection based protocol that persisted between application instances and supported reconnecting when endpoints changed (NAT, etc). this made scaling characteristics simple as bandwidth and memory were the limiting factors. (i tested a 4.5million logical connection pool between two gigabit servers at OSDL) the reason i prefer an iterative unicast without forwarding is that it greatly improves the ability to optimize queries and avoid resource consumption attacks. a peer performing a search is in direct control of the rate of discovery, can terminate early, and may order the search according to local criteria. lack of forwarding makes it difficult for a peer to abuse the resources of another (in gnutella a well connected silent client can inject a large number of queries which propagate according to TTL / other metrics. a single query packet consumes many times more peer resources than the originating sender expended. one major point of note with this approach is that it requires much larger peer groups since they must all be directly addressed. i considered 1k to 10k peers a common size but expected individual nodes with bandwidth to be capable of 100k or more. transitive introduction was also weighted by peer quality with the expectation that high quality peers would know additional high quality peers that share similar interests / relevant resources. the list archives and archive.org have additional details if you are curious / bored. best regards, From afisk at speedymail.org Wed Nov 30 21:42:39 2005 From: afisk at speedymail.org (Adam Fisk) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability In-Reply-To: <438E067B.2040408@neofonie.de> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> Message-ID: <438E1CCF.4010907@speedymail.org> I don't understand your post. When you say "critical", I assume you're talking about life and death situations? Are you talking about anything specifically? DHTs have failure rates. Ad hoc and mesh networks can become useful in emergency situations where conventional infrastructures break down, but the centralized/p2p/structured/unstructured questions here are far from obvious. On the "obsessive science types" issue, this completely misses the point. It's a very non "obsessive science type" statement. There are strong reasons for using the massive indexing/random walk approach above DHTs -- reasons that have nothing to do with scalability. In particulary, DHTs are, well, hash tables. Hash tables don't work well for metadata queries. They do fine for keywords (hotspots are a problem, but they can be solved), but they aren't as nice a fit for metadata. RDF and DHTs are tough to squeeze together, for example. The massive indexing (mutual index caching to use Serguei's term)/random walk approach can get around these issues more easily. They are also not nearly as brittle as DHTs. Sure, DHTs repair themselves after node joins and leaves, but node transience generally has a much greater effect on DHTs than it does on massive indexing networks. I also think you're underestimating the efficiency of massive indexing and random walks. Sure, these networks don't scale logarithmically, but they do pretty darn well. I encourage everyone to stay specific with their posts. All the Best, Adam Ronald Wertlen wrote: > Hi, > > Gnutella-bashing certainly may be fun, the truth is, it is > tremendously well-adapted for its purpose (I think Serguei's said the > relevant stuff). > > However, I also believe it is pretty clear that from a search point of > view, a random super-peer based network does not scale - it is never > going to get the kind of precision and recall that we would call > intelligent. It would be too slow or too inaccurate. > > (This belief may be substantiated by looking at one of the best search > and retrieval super-peer networks we know - our brains (menufactured > by millenia of evolution or a master craftsman ;-)) - and that's > certainly not randomly structured, although parts of it probably are.) > > To sum up some: Gnutella is great in a non-critical scenario, but > sucks for obsessive science types. ;-) > > best wishes, Ron > > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > From gbildson at limepeer.com Wed Nov 30 21:58:21 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> Message-ID: Your UDP based protocol sounds similar to our experimental GUESS protocol. As such, I have always felt that a connectionless UDP protocol is more at risk from abuse. While the cost of delivering queries to many hosts is higher, there is also less opportunity to monitor the activity of the query source. Given a network where there is a true cost and delay to finding available TCP connections, this ways against a greedy client churning connections as well. Our experience of massive query traffic from greedy clients in 2003 led to my being very suspicious of short term connections for querying. The other benefit that you can get from longer lived TCP connections is index forwarding. In the modern Gnutella network, QRP (keyword bloom filtering) indexes are rolled up and propagated two hops from leaf to ultrapeer to neighboring ultrapeers. This allows for query routing on the last hop(s) that a query may travel. With a high outdegree and a low TTL, large routing efficiencies are gained. Queries are not delivered to ultrapeers where keyword matches would not occur. Out-of-band UDP results still allow direct delivery of responses and delivery as needed as well. Thanks -greg > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of coderman > Sent: Wednesday, November 30, 2005 4:39 PM > To: Peer-to-peer development. > Subject: Re: [p2p-hackers] Re: scalability (was: p2p framework) > > > On 11/30/05, Daniel Stutzbach wrote: > > Instead of saying "Gnutella does not scale", I think it would be more > > accurate to say "Gnutella does not perform the operation I am > > interested in". > > perhaps the following are more accurate observations: > - it is difficult to protect gnutella protocol against malicious / > aggressive peers > - it is difficult to conserve bandwidth consumption for large gnutella > peer groups > > i implemented a weighted iterative discovery protocol a while back > called 'alpine' that ordered destination peer lists used for resource > discovery by the relative quality associated with a given peer derived > from past interactions (past responses, usefulness of resources > provided, etc). > > the transport level was a logical UDP connection based protocol that > persisted between application instances and supported reconnecting > when endpoints changed (NAT, etc). this made scaling characteristics > simple as bandwidth and memory were the limiting factors. (i tested a > 4.5million logical connection pool between two gigabit servers at > OSDL) > > the reason i prefer an iterative unicast without forwarding is that it > greatly improves the ability to optimize queries and avoid resource > consumption attacks. a peer performing a search is in direct control > of the rate of discovery, can terminate early, and may order the > search according to local criteria. lack of forwarding makes it > difficult for a peer to abuse the resources of another (in gnutella a > well connected silent client can inject a large number of queries > which propagate according to TTL / other metrics. a single query > packet consumes many times more peer resources than the originating > sender expended. > > one major point of note with this approach is that it requires much > larger peer groups since they must all be directly addressed. i > considered 1k to 10k peers a common size but expected individual nodes > with bandwidth to be capable of 100k or more. > > transitive introduction was also weighted by peer quality with the > expectation that high quality peers would know additional high quality > peers that share similar interests / relevant resources. > > the list archives and archive.org have additional details if you are > curious / bored. > > best regards, > _______________________________________________ > p2p-hackers mailing list > p2p-hackers@zgp.org > http://zgp.org/mailman/listinfo/p2p-hackers > _______________________________________________ > Here is a web page listing P2P Conferences: > http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences From gbildson at limepeer.com Wed Nov 30 22:04:55 2005 From: gbildson at limepeer.com (Greg Bildson) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: Message-ID: > -----Original Message----- > From: p2p-hackers-bounces@zgp.org [mailto:p2p-hackers-bounces@zgp.org]On > Behalf Of Greg Bildson > Sent: Wednesday, November 30, 2005 4:58 PM > To: Peer-to-peer development. > Subject: RE: [p2p-hackers] Re: scalability (was: p2p framework) > available TCP connections, this ways against a greedy client churning ... weighs ... From coderman at gmail.com Wed Nov 30 22:17:23 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability (was: p2p framework) In-Reply-To: References: <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> Message-ID: <4ef5fec60511301417h27b605a0h8fd6d529c40c5eab@mail.gmail.com> On 11/30/05, Greg Bildson wrote: > Your UDP based protocol sounds similar to our experimental GUESS protocol. there are similarities; GUESS was one of the few other UDP search / resource discovery protocols in the works at the time (2001 to 2003). > As such, I have always felt that a connectionless UDP protocol is more at > risk from abuse. yes, which is why i mentioned logical connection based. initiating a session requires a handshake similar to TCP. the logical connections are expect to last for the duration of a peer identity - longevity plays a part in weighted ordering of peer lists. > While the cost of delivering queries to many hosts is > higher, there is also less opportunity to monitor the activity of the query > source. Given a network where there is a true cost and delay to finding > available TCP connections, this ways against a greedy client churning > connections as well. Our experience of massive query traffic from greedy > clients in 2003 led to my being very suspicious of short term connections > for querying. sounds very reasonable. hard to derive any kind of meaningful reputation for such volatile connections. again, the alpine UDP connections were not short lived - they survived between application instances (saved to berkeleydb) and reconnected upon startup or endpoint change (NAT, dynip). > The other benefit that you can get from longer lived TCP connections is > index forwarding. In the modern Gnutella network, QRP (keyword bloom > filtering) indexes are rolled up and propagated two hops from leaf to > ultrapeer to neighboring ultrapeers. This allows for query routing on the > last hop(s) that a query may travel. With a high outdegree and a low TTL, > large routing efficiencies are gained. Queries are not delivered to > ultrapeers where keyword matches would not occur. Out-of-band UDP results > still allow direct delivery of responses and delivery as needed as well. agreed. and this touches upon a great optimization for any decentralized resource discovery protocol: aggressive caching between trusted peers is the best way to improve the depth and breadth of queries while simultaneously reducing execution times. From afisk at speedymail.org Wed Nov 30 22:38:42 2005 From: afisk at speedymail.org (Adam Fisk) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability In-Reply-To: <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> <20051130210510.GH2800@cs.uoregon.edu> <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> Message-ID: <438E29F2.4020105@speedymail.org> I always thought alpine was an interesting protocol, and it was one of a mix of protocols and papers that went into the thinking behind GUESS and Gnutella's current indexing/walking approach. I agree particularly on the protection against malicious attacks -- you have to devote significant resources to get other nodes to give up resources. DHTs and index/walking are far more susceptible to DDOS attacks. I was always amazed you were able to make so many connections, although I know the eDonkey guys maintain incredibly high numbers of connections as well. That's actually a fascinating finding in light of the paper someone mentioned earlier on discovering the optimal number of connections to maintain in DHTs -- you might maintain more if you have the right connection scheme. I like the approach of just keeping as many connections as you can. 4.5 million? Wow. Connections on anywhere near that scale (I'd take 100,000 any day) combined with indexing sounds like a great approach to me. Indexing 2 hops away would go even further, and just don't use TTLs at all (you'd just be indexing it all and searching your local database). Then again, I guess indexing 10,000,000,000 nodes on each machine might be, well, optimistic. Somewhere in there would make the system scale better while also solving your DDOS problem, though. What ever became of Alpine? -Adam coderman wrote: >On 11/30/05, Daniel Stutzbach wrote: > > >>Instead of saying "Gnutella does not scale", I think it would be more >>accurate to say "Gnutella does not perform the operation I am >>interested in". >> >> > >perhaps the following are more accurate observations: >- it is difficult to protect gnutella protocol against malicious / >aggressive peers >- it is difficult to conserve bandwidth consumption for large gnutella >peer groups > >i implemented a weighted iterative discovery protocol a while back >called 'alpine' that ordered destination peer lists used for resource >discovery by the relative quality associated with a given peer derived >from past interactions (past responses, usefulness of resources >provided, etc). > >the transport level was a logical UDP connection based protocol that >persisted between application instances and supported reconnecting >when endpoints changed (NAT, etc). this made scaling characteristics >simple as bandwidth and memory were the limiting factors. (i tested a >4.5million logical connection pool between two gigabit servers at >OSDL) > >the reason i prefer an iterative unicast without forwarding is that it >greatly improves the ability to optimize queries and avoid resource >consumption attacks. a peer performing a search is in direct control >of the rate of discovery, can terminate early, and may order the >search according to local criteria. lack of forwarding makes it >difficult for a peer to abuse the resources of another (in gnutella a >well connected silent client can inject a large number of queries >which propagate according to TTL / other metrics. a single query >packet consumes many times more peer resources than the originating >sender expended. > >one major point of note with this approach is that it requires much >larger peer groups since they must all be directly addressed. i >considered 1k to 10k peers a common size but expected individual nodes >with bandwidth to be capable of 100k or more. > >transitive introduction was also weighted by peer quality with the >expectation that high quality peers would know additional high quality >peers that share similar interests / relevant resources. > >the list archives and archive.org have additional details if you are >curious / bored. > >best regards, >_______________________________________________ >p2p-hackers mailing list >p2p-hackers@zgp.org >http://zgp.org/mailman/listinfo/p2p-hackers >_______________________________________________ >Here is a web page listing P2P Conferences: >http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences > > > From coderman at gmail.com Wed Nov 30 23:17:43 2005 From: coderman at gmail.com (coderman) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability In-Reply-To: <438E29F2.4020105@speedymail.org> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> <20051130210510.GH2800@cs.uoregon.edu> <4ef5fec60511301338r52b4c7cem10eedcce1dfb891f@mail.gmail.com> <438E29F2.4020105@speedymail.org> Message-ID: <4ef5fec60511301517n69ab3966v32d6161858f4551f@mail.gmail.com> On 11/30/05, Adam Fisk wrote: > ... > I was always amazed you were able to make so many connections, although > I know the eDonkey guys maintain incredibly high numbers of connections > as well. That's actually a fascinating finding in light of the paper > someone mentioned earlier on discovering the optimal number of > connections to maintain in DHTs -- you might maintain more if you have > the right connection scheme. I like the approach of just keeping as > many connections as you can. this scalability is only possible because the UDP protocol is designed for control / messaging communication only. this means buffer requirements are minimal and connection overhead very light. if you need a bearer transport the congestion avoidance and xmit/recv buffers become a huge overhead at this scale. > What ever became of Alpine? it is hibernating awaiting a rewrite. i started working on feedbackfs to improve the nature of implicit feedback on resources obtained via alpine before starting the rewrite. feedbackfs got me distracted on security (given the nature of the details tracked by feedbackfs it really has to be secure to protect peer privacy) which has been my current focus. im recursing back out of this rabbit hole and will resume work on it at some point. i'm glad to know that it was useful to others in some manner; i certainly think the approach has merit regardless of where it is implemented (GUESS++). From lgonze at panix.com Wed Nov 30 23:37:54 2005 From: lgonze at panix.com (Lucas Gonze) Date: Sat Dec 9 22:13:05 2006 Subject: [p2p-hackers] Re: scalability In-Reply-To: <438E1CCF.4010907@speedymail.org> References: <20051130095529.6CAE83FEB8@capsicum.zgp.org> <438E067B.2040408@neofonie.de> <438E1CCF.4010907@speedymail.org> Message-ID: <438E37D2.4030609@panix.com> > Ronald Wertlen wrote: > >> To sum up some: Gnutella is great in a non-critical scenario, but >> sucks for obsessive science types. ;-) > A couple p2p-hackers jokes: Punchline: one to screw in the lightbulb, then figure out why it worked, 999 to figure out how to screw in the lightbulb. DHTs are like the guy looking for his keys under the lamp rather than in the place where he lost them. A whole subculture of papers, publications and conferences (not to mention mailing lists) has been spawned around blind faith in the badness of Justin Frankel's topology and goodness of his promiscuous message-passing strategy. Both of these are points of culture rather than science.