A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf
.
Filters
Experiences with CoralCDN: A Five-Year Operational View
2010
Symposium on Networked Systems Design and Implementation
This paper describes CoralCDN's usage scenarios and a number of experiences drawn from its multi-year deployment. ...
CoralCDN is a self-organizing web content distribution network (CDN). ...
We are grateful to David Mazières for his significant contributions and support during the design and operation of CoralCDN. ...
dblp:conf/nsdi/Freedman10
fatcat:mxp5vq3ahbfq5appajpzyhbfba
Rake: Semantics Assisted Network-Based Tracing Framework
2013
IEEE Transactions on Network and Service Management
In the CoralCDN (a content distributed network) experiments, Rake links messages with much higher accuracy than WAP5, a state-of-the-art blackbox approach. ...
In the Hadoop (a distributed computing cluster platform) experiments, Rake helps reveal several previously unknown issues that may lead to performance degradation, including a RPC (Remote Procedure Call ...
experiments including a content distribution network -CoralCDN [17] and Hadoop. ...
doi:10.1109/tnsm.2012.091912.120224
fatcat:i4j5rmwkurg5dasfgfvmspmdpy
On Tackling Flash Crowds with URL Shorteners and Examining User Behavior after Great East Japan Earthquake
2012
IEICE transactions on communications
We developed a new URL shortener, named rcdn.info, just after the earthquake; rcdn.info redirects users to a replica created on a CoralCDN, if the original site is likely to become overloaded. ...
We also conduct a thorough analysis of the request log and present several views that capture user behavior in the emergency from various aspects. ...
Consequently, users in Japan would experience poor latency with CoralCDN. ...
doi:10.1587/transcom.e95.b.2210
fatcat:c476ayu4uzckbf6fd3bj5bqube
Great east Japan earthquake viewed from a URL shortener
2011
Proceedings of the Special Workshop on Internet and Disasters - SWID '11
In this paper, we describe our experience of developing and operating the URL shortener in the aftermath of the giant earthquake. ...
Since the flash crowds were a serious problem in an emergency, we had to develop it as quickly as possible with a spirit of so-called agile software development. ...
CONCLUSIONS This paper describes our experience with a new URL shortener coupled with CoralCDN in the aftermath of the Great East Japan Earthquake. ...
doi:10.1145/2079360.2079368
fatcat:epergzllkjfl7ec3rjp3nlck3i
Rake: Semantics assisted network-based tracing framework
2011
2011 IEEE Nineteenth IEEE International Workshop on Quality of Service
In the CoralCDN (a content distributed network) experiments, Rake links messages with much higher accuracy than WAP5, a state-of-the-art blackbox approach. ...
In the Hadoop (a distributed computing cluster platform) experiments, Rake helps reveal several previously unknown issues that may lead to performance degradation, including a RPC (Remote Procedure Call ...
experiments including a content distribution network -CoralCDN [17] and Hadoop. ...
doi:10.1109/iwqos.2011.5931314
dblp:conf/iwqos/ZhaoCCZG11
fatcat:atpejss4fzg4fktcy66rni43ue
Aggregation and Degradation in JetStream: Streaming Analytics in the Wide Area
2014
Symposium on Networked Systems Design and Implementation
We implemented a range of analytic queries on web request logs and image data. Queries could be expressed in a few lines of code. ...
Our adaptive control mechanisms are responsive enough to keep end-to-end latency within a few seconds, even when available bandwidth drops by a factor of two, and are flexible enough to express practical ...
We repeated a similar experiment, but with degradation enabled. ...
dblp:conf/nsdi/RabkinASPF14
fatcat:j7bryvrplza2tfyeh4sqaispaa
An Architectural Design for Brokered Collaborative Content Delivery System
[article]
2013
arXiv
pre-print
With the recent emergence of cloud computing, we show that this system can also be adopted to run on the cloud. ...
This situation enforces the content providers to scale their infrastructure in order to cope with the extra provisioning of network traffic, storage and other resources. ...
Even though it was originally designed to handle flash crowds, a term to describe the phenomenon of temporary load spikes in an underprovisioned content server, five-year usage analysis of CoralCDN shows ...
arXiv:1012.3347v2
fatcat:pkc6mb7cwzcgno72fltl67h47y
Network Delay-Aware Load Balancing in Selfish and Cooperative Distributed Systems
2013
2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum
During the experimental evaluation, we show that the distributed algorithm is efficient, therefore it can be used in networks with dynamically changing loads. ...
Additionally, even if the network is organizationally distributed, with individual organizations optimizing performance of their requests, the network remains efficient. ...
Authors acknowledge helpful discussions with Maciej Drozdowski. ...
doi:10.1109/ipdpsw.2013.21
dblp:conf/ipps/SkowronR13
fatcat:wj5pxhq42jdtnohtt2jqmv6hhq
Network delay-aware load balancing in selfish and cooperative distributed systems
[article]
2012
arXiv
pre-print
During the experimental evaluation, we show that the distributed algorithm is efficient, therefore it can be used in networks with dynamically changing loads. ...
Additionally, even if the network is organizationally distributed, with individual organizations optimizing performance of their requests, the network remains efficient. ...
In CoralCDN the popular content is replicated among multiple servers (which can be viewed as relaying the requests); the requests for content are relayed only between the servers with constrained pairwise ...
arXiv:1212.0421v1
fatcat:l5eiiycwqnhc5h5h6bqizaf6um
dFault: Fault Localization in Large-Scale Peer-to-Peer Systems
[chapter]
2010
Lecture Notes in Computer Science
Informed with a log of failed queries called symptoms and some available information about the hosts in the DHT, dFault identifies the potential root causes (hosts and overlay links) that with high likelihood ...
We describe the design of dFault, and show that it can accurately localize the root causes of faults with modest amount of information collected from individual nodes using a real prototype deployed over ...
First, the application issues a get or a put operation for a specific key K to the local DHT host A it interacts with. ...
doi:10.1007/978-3-642-16955-7_13
fatcat:nx242tzbb5cf7fir7pw3evdlv4
An adaptable storage slicing algorithm for content delivery networks
2015
2015 IFIP/IEEE International Symposium on Integrated Network Management (IM)
A users' viewing experience is crucial for a successful service deployment. ...
Figure 2 . 2 - 22 QoS/QoE layered model
Figure 3 . 3 1 depicts an abstract view of a CDN.
Figure 3 . 1 - 31 An abstract view of a CDN operations and service expansion. ...
Appendix II Surrogate placement strategies In scenarios we conducted these experiments, we used an AS network topology with 3037 nodes and links of 100 Mbit/s. ...
doi:10.1109/inm.2015.7140355
dblp:conf/im/MoreiraAKSCS15
fatcat:u2d3ub67zrgozhao4ft6pgyk6y
Rethinking Enterprise Network Control
2009
IEEE/ACM Transactions on Networking
Our deployment experiences have significantly affected Ethane's design. ...
We have deployed and managed two operational Ethane networks, one in the Stanford University Computer Science Department supporting over 300 hosts, and another within a small business of 30 hosts. ...
Lockwood, and A. Akella for their valuable input. T. Hinrichs and J. Mitchell were heavily involved in the design of FSL. D. Mazières, N. Zeldovich, J. Rexford, S. Goldberg, C. Kim, and A. ...
doi:10.1109/tnet.2009.2026415
fatcat:zzqpgsnjcncg7pkvhnrd54brf4
Leveraging Internet Background Radiation for Opportunistic Network Analysis
2015
Proceedings of the 2015 ACM Conference on Internet Measurement Conference - IMC '15
Alex, a later addition to my advising team, provided much appreciated insight, structure, and experience. Above all, I am thankful for my advisors' patience. ...
I am thankful for Hovav Shacham's xiii guidance my first year of graduate school. My research would not have been possible without the help of the people who provided me with data and tools. ...
We feel that our data is representative of IBR, and that researchers using other darknets will experience similar results when using IBR to make Internet-wide inferences. ...
doi:10.1145/2815675.2815702
dblp:conf/imc/BensonDcSK15
fatcat:xjiswtal4ng3pono2wptto57pq
On the Performance of Content Delivery Clouds
[chapter]
Next Generation Content Delivery Infrastructures
Content providers interact with the service in a limited number of ways, such as enabling their content to be served, viewing traffic reports, and receiving usage-based billing. ...
The experiment time comprises epochs of 2 hours, with each epoch consisting of a set of user sessions. ...
") and make them accessible as scalable, on-demand services over a network (the "Cloud"). ...
doi:10.4018/978-1-4666-1794-0.ch002
fatcat:rwv64xh4arebvhekp6fymkce7e
Improving Content Delivery and Service Discovery in Networks
2017
At the same time, users are shifting away from a homogeneous desktop computing environment to using a heterogeneous mix of devices, such as smartphones, tablets and thin clients, all of which allow users ...
This implies that countries with lower bandwidth do indeed view shorter-form content, whether they are restricted due to their content providers, or whether they experience a poor quality of video watching ...
of our experiments. ...
doi:10.7916/d8z89ccc
fatcat:k4ingsyn7na2rl7scdbk4l4oe4
« Previous
Showing results 1 — 15 out of 17 results