Speaker
Mr
Sergio Andreozzi
(INFN-CNAF)
Description
Grid computing is concerned with the virtualization, integration and
management of services and resources in a distributed, heterogeneous
environment that supports collections of users and resources across
traditional administrative and organizational domains.
One aspect of particular importance is Grid monitoring, that is the
activity of measuring significant Grid resource-related parameters
in order to analyze usage, behavior and performance of a Grid
system. The monitoring activity can also help in the detection of
fault situations, contract violations and user-defined events.
In the framework of the EGEE (Enabling Grid for E-sciencE) project,
the Grid monitoring system called GridICE has been consolidated and
extended in its functionalities in order to meet requirements from
three main categories of users: Grid operators, site administrators
and Virtual Organization (VO) managers. Besides the specific needs
of these categories, GridICE offers a common sensing, collection and
presentation framework enabling to share common features, while also
offering user-specific needs.
A first common aspect to the different users is the set of
measurements to be performed. Typically, there is a wide number of
base measurements that are of interest for all parties, while a
small number is specific to them. What makes the difference is the
aggregation criteria required to present the monitoring information.
This aspect is intrinsic to the multidimensional nature of
monitoring data. Example of aggregation dimensions identified in
GridICE are: the physical dimension referring to geographical
location of resources, the Virtual Organization (VO) dimension, the
time dimension and the resource identifier dimension.
As an example, considering the entity 'host' and the measure 'number
of started processes in down state', the Grid operator can be
interested in accessing the sum of the measurement values for all
the core machines (e.g., workload manager, computing element,
storage element) in the whole infrastructure, while the Virtual
Organization manager can be interested in the sum of the measurement
values for all the core machines that are authorized to the VO
members. Finally, the site administrator can be interested in
accessing the sum of the measurement values for all machines part of
its site.
Another aspect that is common to all the consumers is being able to
start from summary views and to drill down to details. This feature
can enable to verify the composition of virtual pools or to sketch
the sources of problems.
As regards the distribution of monitoring data, GridICE follows a
2-level hierarchical model: the intra-site level is within the
domain of an administrative site and aims at collecting the
monitoring data at a single logical repository; the inter-site level
is across sites and enables the Grid-wide access to the site
repository. The former is typically performed by a fabric monitoring
service, while the latter is performed via the Grid Information
Service. In this sense, the two levels are totally decoupled and
different fabric monitoring services can be adapted to publish
monitoring data to GridICE, thought the proposed default solution is
the CERN Lemon tool.
Considering the sensing activity, GridICE adopts the whole set of
measures defined in the GLUE Schema 1.2, further it provides
extensions to cover new requirements. The extensions include a more
complete host-level characterization, Grid jobs related attributes
and summary info for batch systems (e.g., number of total slots,
number of worker nodes that are down).
The development activity in the EGEE project has focused on the
following aspects: the redesign of the presentation level took into
consideration the usability principles and compliance with W3C
standards; sensors for measuring parameters related to Grid job have
been re-engineered to scale to the number of jobs envisioned by big
sites (e.g., LCG Tier 1 centers); new sensors have been written to
deal with summary information for computing farms; stability and
reliability of both server and sensors.
The deployment activity covers the whole EGEE framework with several
server instances supporting the work of different Grid sub-domains
(e.g., whole EGEE Grid domain, ROC domain, national domain). Other
Grid projects have adopted GridICE for monitoring their resources
(e.g., EUMedGrid, EUChinaGRID, EELA).
As regards the user experience, GridICE has proven to be useful to
different users in different ways. For instance, Grid operators have
summary views for aspects such as information sources status and
host status. Site administrators appreciate the job monitoring
capability showing the status and computing activity of the jobs
accepted in the managed resources. VO managers use GridICE to verify
the available resources and their status before to start the
submission of a huge number of jobs. Finally, GridICE has been
positively adopted in dissemination activities.
While GridICE has reached a good maturity level in the EGEE project,
many challenges are still open in the dynamic area of Grid systems.
The short term plans are: (1) as regards the discovery process,
there is the need to finalize the transition from the MDS-based
information service to the gLite service discovery plus publisher
services such as R-GMA producers and CEMon; (2) integration with
information present in the Grid Operation Center (GOC) database for
accessing resource planned downtime and other management
information; (3) tailored sensors for the workload management
service; (4) sensors for measuring data transfer activities across
Grid sites.
References:
Dissemination website: http://grid.infn.it/gridice
Publications:
http://grid.infn.it/gridice/index.php/Research/Publications
Summary
C. Aiftimiei, S. Andreozzi, G. Cuscela, N. De Bortoli, G. Donvito,
S. Fantinel, E. Fattibene, G. Misurelli, A. Pierro, G.L. Rubini,
G.Tortone.
Primary authors
Mr
Antonio Pierro
(INFN-Bari)
Mrs
Cristina Aiftimiei
(INFN-LNL)
Mr
Enrico Fattibene
(INFN-CNAF)
Mr
Gennaro Tortone
(INFN-Napoli)
Mr
Giacinto Donvito
(INFN-Bari)
Mr
Giuseppe Misurelli
(INFN-CNAF)
Mr
Guido Cuscela
(INFN-Bari)
Ms
Natascia De Bortoli
(INFN-Napoli)
Mr
Sergio Andreozzi
(INFN-CNAF)
Mr
Sergio Fantinel
(INFN-LNL)
