A federated Xrootd cache - INSPIRE

DataBETA

A federated Xrootd cache

Oct 18, 2018

5 pages

Part of Proceedings, 18th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2017) : Seattle, WA, USA, August 21-25, 2017

Published in:

J.Phys.Conf.Ser. 1085 (2018) 3, 032025

Contribution to:

- ACAT 2017

Published: Oct 18, 2018

DOI:

10.1088/1742-6596/1085/3/032025

reference search7 citations

Citations per year

Abstract: (IOP)

With the shift in the LHC experiments from the computing tiered model where data was prefetched and stored at the computing site towards a bring data on the fly, model came an opportunity. Since data is now distributed to computing jobs using XrootD federation of data, a clear opportunity for caching arose. In this document, we present the experience of installing and using a Federated Xrootd Cache (A Xrootd Cache consistent of several independent nodes). There is some fine tuning towards and scaling tests performed to make it fit for the CMS Analysis case. Finally, we show how this federated cache can be expanded into a federation of caches in which the caches can be distributed among computing centers.

CMS
programming
data management
performance
computer: communications

References(8)

Figures(0)

[1]

Predicting dataset popularity for the CMS experiment

- J.Phys.Conf.Ser. 762 (2016) 1, 012048
•
e-Print:
- 1602.07226
•
DOI:
- 10.1088/1742-6596/762/1/012048

[2]

Using Xrootd to Federate Regional Storage

et al.

- J.Phys.Conf.Ser. 396 (2012) 042009
•
DOI:
- 10.1088/1742-6596/396/4/042009

[3]

Proceedings of the 4th WSEAS International Conference on Telecommunications and Informatics TELE-INFO’05 (Stevens Point, Wisconsin, USA:

Dorigo A
,
Elmer P
,
Furano F
,
Hanushevsky A

[4]

CMS Use of a Data Federation

CMS

Collaboration

•

Kenneth Bloom
(
- Nebraska U.
)

for the collaboration.

- J.Phys.Conf.Ser. 513 (2014) 042005
•
DOI:
- 10.1088/1742-6596/513/4/042005

[5]

Controlled overflowing of data-intensive jobs from oversubscribed sites

I. Sfiligoi
(
- UC, San Diego
)
,
F. Wuerthwein
(
- UC, San Diego
)
,
B. Bockelman
(
- Nebraska U.
)
,
D.C. Bradley
(
- Wisconsin U., Madison
)
,
M. Tadel
(
- UC, San Diego
)

et al.

- J.Phys.Conf.Ser. 396 (2012) 032102
•
DOI:
- 10.1088/1742-6596/396/3/032102

[6]

Phedex high-throughput data transfer management system

Rehn J

[7]

Using the GlideinWMS System as a Common Resource Provisioning Layer in CMS

J. Balcas
(
- Vilnius U.
)
,
S. Belforte
(
- INFN, Trieste and
- Trieste U.
)
,
B. Bockelman
(
- Nebraska U.
)
,
D. Colling
(
- Imperial Coll., London
)
,
O. Gutsche
(
- Fermilab
)

et al.

- J.Phys.Conf.Ser. 664 (2015) 6, 062031
•
DOI:
- 10.1088/1742-6596/664/6/062031

[8]

The pilot way to Grid resources using glideinWMS

Igor Sfiligoi
(
- Fermilab
)
,
Daniel C. Bradley
(
- Wisconsin U., Madison
)
,
Burt Holzman
(
- Fermilab
)
,
Parag Mhashilkar
(
- Fermilab
)
,
Sanjay Padhi
(
- UC, San Diego
)

et al.

- WRI World Congress 2 (2009) 428-432
•
DOI:
- 10.1109/CSIE.2009.950