/[gzz]/gzz/Documentation/misc/hemppah-progradu/research_problems
ViewVC logotype

Diff of /gzz/Documentation/misc/hemppah-progradu/research_problems

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.41 by hemppah, Wed Feb 5 11:50:09 2003 UTC revision 1.42 by hemppah, Wed Feb 5 12:32:50 2003 UTC
# Line 40  information about O(log n) nodes Line 40  information about O(log n) nodes
40  -Of couse, there is the possibility to route in constant times, but it requires that *each** node  -Of couse, there is the possibility to route in constant times, but it requires that *each** node
41  maintains information about all the nodes in the network. Therefore , practically, this method  maintains information about all the nodes in the network. Therefore , practically, this method
42  impossible  impossible
43  -Example systems: Chord, CAN, Kademlia, Pastry, Tapestry, Viceroy, Symphony, SkipNet, Skip Graph  -Example systems: Chord \cite{stoica01chord}, CAN \cite{ratnasamy01can}, Kademlia \cite{maymounkov02kademlia}, Pastry \cite{rowston01pastry}, Tapestry \cite{zhao01tapestry}, Viceroy \cite{malkhi02viceroy}, Symphony \cite{gurmeet03symphony}, SkipNet \cite{harvey03skipnet2}, Skip Graph \cite{AspnesS2003}
44  -Example applications: CFS, PAST, Oceanstore                  Plaxton \cite{plaxton97accessingnearby}, Kelips \cite{gupta03kelips}, Overlapping Distance Halving DHT \cite{naor03simpledht}
45    -Example applications: CFS \cite{dabek01widearea}, PAST \cite{rowstron01storage}, Oceanstore \cite{kubiatowicz00oceanstore}
46    
47  *Update*  *Update*
48  -Viceroy system achieves O(log n) hops with only O(1) neighbors  -Viceroy system achieves O(log n) hops with only O(1) neighbors
49  -Isn't yet clear whether these improvements will interfere with the robustness  -Isn't yet clear whether these improvements will interfere with the robustness
50  -More on this later...  -More on this later...
51    
52  1.2. Small World Networks (SWN)  1.2. Small World Networks (SWN) \cite{kleinberg99small, nips02-Kleinberg}, \cite{bonsma02swan}
53  +fast routing (aka searching)  +fast routing (aka searching)
54  +quite scalable, however not as scalable as DHTs  +quite scalable, however not as scalable as DHTs
55  +robust  +robust
# Line 80  present it here with these characters). Line 81  present it here with these characters).
81  And, if these requirements are met, SWN network can locate any data in O(log^2  And, if these requirements are met, SWN network can locate any data in O(log^2
82  n) hops (Kleinberg and e.g. simulations in SWAN)  n) hops (Kleinberg and e.g. simulations in SWAN)
83    
84  1.3. Flooding Broadcast Networks (FBN)  1.3. Flooding Broadcast Networks (FBN) and Hybrid systems
85  +own resources are not mapped into the network  +own resources are not mapped into the network
86  +keyword/fuzzy search possible  +keyword/fuzzy search possible
 -not scalable  
 -huge network traffic  
 -not fast routing  
 -no guarantee that all data will be located  
   
 -Example systems: Gnutella, Fastrack family (Kazaa, Morpheus), JXTA Search, Gnutella2  
   
 1.4. Hybrid systems (HS)  
87  -based on FBNt technique,  -based on FBNt technique,
88  +solves some of the Gnutella's scalability issues by introducing ``Super nodes'' (a superNode acts like a local hub, building an index  +solves some of the Gnutella's scalability issues by introducing ``Super nodes'' (a superNode acts like a local hub, building an index
89  of the resources being shared by each node connected to it and proxying lookup queries on behalf of other nodes)  of the resources being shared by each node connected to it and proxying lookup queries on behalf of other nodes)
90  +this kind of structure reduces network traffic in comparison to a original broadcast query algorithm employed on the Gnutella system  +this kind of structure reduces network traffic in comparison to a original broadcast query algorithm employed on the Gnutella system
91    -not scalable
92    -huge network traffic
93    -not fast routing
94    -no guarantee that all data will be located
95    
96  -Example systems: FastTrack (Kazaa, Morpheus), Gnutella2, JXTA  -Example systems: Gnutella \cite{gnutellaurl}, Fastrack family (Kazaa, Morpheus) \cite{fasttrackurl}, JXTA Search \cite{botros01jxtasearch}, Gnutella2 \cite{gnutella2url, shareazaurl},
97    YAPPERS \cite{ganesan02yappers}
98    
99  1.5  Social Discovery Systems (SDS)  1.5  Social Discovery Systems (SDS)
100  Notice: pros and cons are not presented here  Notice: pros and cons are not presented here
# Line 105  Notice: pros and cons are not presented Line 103  Notice: pros and cons are not presented
103  -as in real social life, nodes who have returned relevant results in the past, will have a high quality value in future query lookups  -as in real social life, nodes who have returned relevant results in the past, will have a high quality value in future query lookups
104  -with every lookup query, a node determines how proficient a given node is to another node's objectives  -with every lookup query, a node determines how proficient a given node is to another node's objectives
105    
106  -Example systems: Alpine Network  -Example systems: Alpine Network \cite{alpineurl}
107    
108    
109  1.6. Skip Graphs (based on skip lists)  1.6. Skip Graphs (based on skip lists)
# Line 144  Notice: pros and cons are not presented Line 142  Notice: pros and cons are not presented
142  -we don't have to create 'mini-blocks' for Gzz p2p, since bitTorrent itself partitions data into several blocks for us  -we don't have to create 'mini-blocks' for Gzz p2p, since bitTorrent itself partitions data into several blocks for us
143  -my initial suggestion for our p2p data obtaining scheme: use Kademlia for data lookup and bitTorrent/MFTP-like tool for downloading the data  -my initial suggestion for our p2p data obtaining scheme: use Kademlia for data lookup and bitTorrent/MFTP-like tool for downloading the data
144    
145  See http://bitconjurer.org/BitTorrent/ for details.  See http://bitconjurer.org/BitTorrent/ for details. \cite{bittorrenturl}
146    
147  1.9. PeerNet  1.9. PeerNet \cite{eriksson03peernet}
148  Notice: pros and cons are not presented here  Notice: pros and cons are not presented here
149  -Peernet is a p2p based *network layer* for large networks  -Peernet is a p2p based *network layer* for large networks
150  -Peernet makes an explicit distinction between node identity and address  -Peernet makes an explicit distinction between node identity and address

Legend:
Removed from v.1.41  
changed lines
  Added in v.1.42

savannah-hackers-public@gnu.org
ViewVC Help
Powered by ViewVC 1.1.26