Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
The concept of live objects in an active web, where users can build applications using a 'drag and drop' method. The technical challenges of creating a system with large numbers of live objects and overlapping groups, and proposes solutions for simplifying the system and ensuring efficient communication between objects. The document also touches upon the concept of power laws and their implications for system design.
Typology: Study Guides, Projects, Research
1 / 45
This page cannot be seen from the preview
Don't miss anything!
Krzys Ostrowski, Ken Birman, Danny DolevKrzys Ostrowski, Ken Birman, Danny Dolev
Cornell University, Hebrew University
(*) Others are also involved in some aspects of this project… I’ll
mention them when their work arises…
Imagine a world of Live Objects
^ Imagine
a world of Live Objects….
…. and an Active Web created with “drag and drop”
User builds applications much like powerpoint User
builds applications much like powerpoint
p^
p
Build a disaster response system…… in the field (with no programming needed!) Coordinated planning and plan execution Create role-playing simulations, games Integrate data from web services intodatabases, spreadsheets Visualize complex distributed state Track business processes, status of major^ projects, even state of an application
The drag and drop worldThe drag and drop world^
It needs a global namespace of objects It^
needs a global namespace of objects• Video feeds, other data feeds, live maps, etc…• Our thinking: download them from a repository or
g^
p^
y
(rarely) build new ones ^ Users make heavy use of live documents, share
h^
k^
d^
f l^
b
other kinds of live objects And this gives rise to a world with^ • Lots of live traffic, huge numbers of live objects• Any given node may be “in” lots of object groups
Control Events Background Radar Images ATC events Radar track updates
Background Radar Images
Multicast groupssupporting live
Radar
track updates Weather notifications
objects Nodes running live applications
Existing technologies won’t work…Existing technologies won’t work…^ Kind of technology
Why we rejected it
IP multicast, pt-to-pt TCP
Too many IPMC addrs.
Too many TCP streams
Software group multicastl^
i^
(“h^
i h ”)
Protocols designed for just one group at a time;
h^
d
I^
bili^
i^ l^
d^
l
solutions (“heavyweight”)
overheads soar.
Instability in large deployments
Lightweight groups
Nodes get undesired traffic, data sent indirectly
P bli h
b
ib
b
U^
t bl
i^
l^
d^
l^
t^ d t
t i di
tl
Publish-subscribe bus
Unstable in large deployments, data sent indirectly
Content-filtering eventnotification.
Very expensive.
Nodes see undesired traffic.
High latency paths are common
notification.
High latency paths are common
Peer-to-peer overlays
Similar to content-filtering scenario
First, we’ll look at group overlap and will show that we
,^
g^
p^
p
can simplify a system with overlap and focus on a single“cover set” with a regular, hierarchical overlap
2.^
Next, we’ll design a simple fault-tolerance protocol forhigh-speed data delivery in such systems
3.^
We’ll look at its performance (and arrive at surprisinginsights that greatly enhance scalability under stress)g
g^
y^
y^
)
4.^
Last, ask how our solution can be enhanced to addressneed for stronger reliability
security
need for stronger reliability, security
Likely to arise in a data center that replicates services and automates layout of services on nodes
^ Likely because users will have different interests^ Likely
because users will have different interests…
Remove tiny groups and collapse identical ones 1.^
Remove tiny groups and collapse identical ones
2.^
Pick a big, busy group1.^ Look for another big, busy group with extensive overlap
1.^
Look for another big, busy group with extensive overlap
2.^
Given multiple candidates, take the one that creates thelargest “regions of overlap”
3.^
Repeat within overlap regions (if large enough) A^
B
A^
B
Nodes only in group A
Nodes only in group B
Nodes inA and B
in general, it wouldn
’t work!
^ … in general, it wouldn t work! ^ But many studies suggest that groups would havepower-law popularity distributionspower law popularity distributions
Each step of the algorithm
“concentrates” load
^ Each step of the algorithm
concentrates
load
Initial groups
Remove small oridentical groups
Run algorithm
… but not always… but not always^
It works very poorly with
“uniform random”
^ It works very poorly with
uniform random
topic popularity It works incredibly well with artificially generated It works incredibly well with artificially generatedpower-law popularity of a type that might arisein some real systems, or with artificial group layouts (as seen in IBM Websphere) But the situation for human preferential
h^
l^
h
attachment scenarios is unclear right now…we’re studying it
