CloudCmp: comparing public cloud providers

By Ang Li, Xiaowei Yang, Srikanth Kandula, Ming Zhang. ACM/SIGCOMM Internet Measurement Conference, 2010

1,075 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/6080c84a2222da9b8b770c11706a47dab57b18d4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

Citations in the corpus

Cloud monitoring: A survey (2013, methodology): “Cloud CMP [116,117] is a tool developed by Duke University and Microsoft Research aimed at comparing the cost effectiveness of different Cloud Providers.”
Sharing the Data Center Network (2011, background): “Recent measurements demonstrate considerable variation in network performance metrics – medium instances in EC2 experience throughput that can vary by 66% [25, 43].”
Resource Central: Understanding and Predicting Workloads for Improved Resource Management in Large Cloud Platforms (2017, background): “Other works studied cloud platform performance [16] and how users implement their front-end services in the cloud [11].”
Jockey: guaranteed job latency in data parallel clusters (2012, background): “In public infrastructures, such as EC2 and Azure, such contention is even higher than in our cluster [13, 25].”
Inside dropbox: understanding personal cloud storage services (2012, background): “Some studies present a comparison among different storage providers [13, 17]: by running benchmarks, they focus on the user achieved performance, but miss the characterization of the typical usage of a cloud service, and the impact of user and system behavior on personal storage applications.”
Computation Offloading Toward Edge Computing (2019, background): “The latency of public cloud providers is usually over 100 ms [9], which would be disastrous for latency-sensitive applications, such as autonomous driving and real-time video analytics [10].”
Towards predictable datacenter networks (2011, background): “Categories and Subject Descriptors: C.2.3 [ComputerCommunication Networks]: Network Operations General Terms: Algorithms, Design, Performance Keywords: Datacenter, Allocation, Virtual Network, Bandwidth”
Edge Computing: Vision and Challenges (2016, neutral): “Latency: Latency is one of the most important metrics to evaluate the performance, especially in interaction applications/services [34], [35].”
Towards wearable cognitive assistance (2014, background): “[18] report that average RTT from 260 global vantage points to their optimal Amazon EC2 instances is nearly 74 ms, and a wireless first hop would add to this amount.”
SMICloud: A Framework for Comparing and Ranking Cloud Services (2011, neutral): “Other works such as CloudCmp [9] proposed frameworks to compare the performance of different Cloud services such as Amazon EC2, Windows Azure and Rackspace.”
End-to-end Performance Isolation Through Virtual Datacenters (2014, background): “In recent years, cloud providers have moved from simply offering on-demand compute resources to providing a broad selection of services.”
All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021, background): “Due to the variable and unpredictable high latency [443]– [446], cloud offloading cannot always reach the optimal bal-”
Empirical prediction models for adaptive resource provisioning in the cloud (2012, background): “The time it takes to instantiate a new virtual machine (VM) instance on demand is relatively small, for instance, 5–15 minutes [1] as compared to a traditional month-long procurement process.”