[DBWorld] Call for Participation: Article Collection in Frontiers in Big Data

CALL FOR PARTICIPATION
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
Article Collection "Automatic Performance Management and Optimization on La=
rge-scale Heterogeneous Clusters"
Frontiers in Big Data Journal
https://fro.ntiers.in/Umfs


Introduction
------------
Modern industrial, government, and academic organizations are collecting ma=
ssive amounts of data at an unprecedented scale and pace, which are then an=
alysed on large compute clusters in order to extract value and deep insight=
s. These insights can drive automated processes for advertisement placement=
, improve customer relationship management, and lead to major scientific br=
eakthroughs. Ensuring good and robust system performance at such a scale is=
 the foundation for successfully performing timely and cost-effective analy=
tics. However, as the new systems have grown in scale and complexity, the a=
dministration and management of system resources have become very expensive=
 with the human factor dominating the total cost of ownership. To make matt=
ers worse, computing clusters are increasingly becoming heterogeneous in na=
ture, both in the compute and the storage tier. Heterogeneity, if not addre=
ssed appropriately, is shown to have detrimental effects on the overall sys=
tem performanc!
 e.

As organizations often own multiple generations of hardware and data centre=
s are starting to use virtualization to consolidate servers, heterogeneous =
environments are becoming common in practice. Computing-wise, nodes can hav=
e CPUs with different capacities and number of cores, making performance-ba=
sed resource allocation and workload scheduling extremely important and cha=
llenging. In addition, the presence of GPUs and FPGAs on modern clusters ha=
s inspired their use by various big data frameworks. On the storage front, =
cluster nodes can have multiple hard drives, SSDs, and large memory, all of=
 different sizes, while emerging storage technologies (e.g., NVMe, SCM) are=
 becoming more popular. At the same time, applications exhibit a variety of=
 I/O patterns: batch-processing applications care about raw sequential thro=
ughput, interactive query processing benefits from lower latency storage me=
dia, whereas other applications display random I/O patterns. Hence, it is d=
esirable to ha!
 ve a vari
 ety of storage types and let each application choose the one that best fit=
s its performance or cost requirements. Administrators and systems will nee=
d mechanisms to manage the fair distribution of scarce storage resources ac=
ross all users, ideally in an automated manner. The goal of this article co=
llection is to report recent advances in automating (fully or partially) an=
y aspects of resource management and performance optimization in the presen=
ce of heterogeneous cluster environments.


Topics of Interest
------------------
The topics of the Article Collection include, but are not limited to, the f=
ollowing:
=E2=80=A2    Automated resource allocation in heterogeneous clusters
=E2=80=A2    Workload and task scheduling in heterogeneous environments =

=E2=80=A2    Performance optimization and tuning of data-parallel applicati=
ons
=E2=80=A2    Automated data management in heterogeneous and emerging storag=
e systems
=E2=80=A2    Automatic parameter tuning in big data processing systems
=E2=80=A2    Automatic big data systems tuning that is robust to workload a=
nd resource uncertainty
=E2=80=A2    Query processing, indexing, and optimization in heterogeneous =
clusters
=E2=80=A2    Data stream processing in heterogeneous environments
=E2=80=A2    Automated provisioning of heterogeneous cluster resources
=E2=80=A2    System administration and manageability


Important Information
---------------------
You are cordially invited to submit a manuscript for consideration and poss=
ible publication. Papers can be original research, reviews, or perspectives=
, among other article types. For more information visit: https://fro.ntiers=
.in/Umfs

If you decide to submit a manuscript within our collection, your contributi=
on will be peer-reviewed and judged based on its originality, interest, cla=
rity, relevance, correctness, language, and presentation (inter alia) by ou=
r editorial board members. Immediately upon publication, your paper will be=
 free to read online, increasing its visibility and citations.
 =

As an Open Access publisher, we charge a small Article Processing Charge fo=
r accepted papers (USD 1150 for long articles; USD 450 for shorter ones). I=
nformation on the publishing fees and financial support for authors can be =
found here: https://www.frontiersin.org/about/publishing-fees.
 =

We encourage authors to submit Abstracts ahead of the full manuscript submi=
ssion.

The deadline for manuscript submission is 31 July 2021 (manuscripts are rev=
iewed as soon as they are submitted and published as soon as they are accep=
ted).

We look forward to working with you.


Kind Regards,

The topic editors:
Herodotos Herodotou, Cyprus University of Technology
Manos Athanassoulis, Boston University
Eduardo Cunha De Almeida, Federal University of Paran=C3=A1
_______________________________________________
Please do not post msgs that are not relevant to the database community at =
large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld