Lorenzo Corneo1, Maximilian Eder2, Nitinder Mohan2, Aleksandr Zavodovski1, Suzan Bayhan3, Walter Wong4, Per Gunningberg1, Jussi Kangasharju4, Jörg Ott2
Uppsala University1, Technical University of Munich2, University of Twente3, University of Helsinki4
This repository contains useful code to replicate the results that are included in our publication Surrounded by the Clouds: A Comprehensive Cloud Reachability Study, which is accepted at The Web Conference 2021. Check the paper out here📃📃
In the early days of cloud computing, datacenters were sparsely deployed at distant locations far from end-users with high end-to-end communication latency. However, today's cloud datacenters have become more geographically spread, the bandwidth of the networks keeps increasing, pushing the end-users latency down. In this paper, we provide a comprehensive cloud reachability study as we perform extensive global client-to-cloud latency measurements towards 189 datacenters from all major cloud providers. We leverage the well-known measurement platform RIPE Atlas, involving up to 8500 probes deployed in heterogeneous environments, e.g., home and offices. Our goal is to evaluate the suitability of modern cloud environments for various current and predicted applications. We achieve this by comparing our latency measurements against known human perception thresholds and are able to draw inferences on the suitability of current clouds for novel applications, such as augmented reality. Our results indicate that the current cloud coverage can easily support several latency-critical applications, like cloud gaming, for the majority of the world’s population.
We used up to 8500 RIPE Atlas probes in our measurements. Here is their density distribution.
We targeted virtual machines hosted in 189 datacenters around the world.
The raw dataset is available at mediaTUM with detailed information on how to set it up. We encourage to cite this dataset in academic publications upon usage.
@inproceedings{corneo2021surrounded,
author = {Corneo, Lorenzo and Eder, Maximilian and Mohan,
Nitinder and Zavodovski, Aleksandr and Bayhan, Suzan
and Wong, Walter and Gunningberg, Per and
Kangasharju, Jussi and Ott, J\"{o}rg},
title = {Surrounded by the Clouds: A Comprehensive Cloud
Reachability Study},
year = 2021,
isbn = 9781450383127,
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3442381.3449854},
doi = {10.1145/3442381.3449854},
abstract = { In the early days of cloud computing, datacenters
were sparsely deployed at distant locations far from
end-users with high end-to-end communication
latency. However, today’s cloud datacenters have
become more geographically spread, the bandwidth of
the networks keeps increasing, pushing the end-users
latency down. In this paper, we provide a
comprehensive cloud reachability study as we perform
extensive global client-to-cloud latency
measurements towards 189 datacenters from all major
cloud providers. We leverage the well-known
measurement platform RIPE Atlas, involving up to
8500 probes deployed in heterogeneous environments,
e.g., home and offices. Our goal is to evaluate the
suitability of modern cloud environments for various
current and predicted applications. We achieve this
by comparing our latency measurements against known
human perception thresholds and are able to draw
inferences on the suitability of current clouds for
novel applications, such as augmented reality. Our
results indicate that the current cloud coverage can
easily support several latency-critical
applications, like cloud gaming, for the majority of
the world’s population.},
booktitle = {Proceedings of the Web Conference 2021},
pages = {295–304},
numpages = 10,
keywords = {Internet measurements, Cloud reachability},
location = {Ljubljana, Slovenia},
series = {WWW '21}
}
The data consists of a 60GB SQLite3 database that contains all the
measurements taken with the RIPE Atlas platform. The dataset includes
both pings, traceroutes and information regarding the ownership of
the identified IP addresses.
In order to reproduce our results, some non-default Python libraries need to be installed with the following command:
pip install -r requirements.txt
In order to make the results replication smoother, we provide
pre-fetched data and avoid extremely time-consuming queries to the
SQLite3 database. However, these pre-fetcehd data were extracted by
the very same databese. In order to access such data, unzip
data/data.zip and delete the compressed file (if you wish). Then,
run the following command, from the folder's root, to generate all the
figures from the paper.
sh generate_figures.sh
The output of the script will be placed in the figures/ folder and
each figure will be named after the figure identifier from the paper.
Please feel free to contact me for further details at lorenzo.corneo@it.uu.se.