| |
|
|
The operations activity of LCG makes use of the infrastructure
funded through the EGEE
project. There is a hierarchical structure
in place to provide operations support. This consists of the following
elements:
- Regional Operations Centres (ROC). There is one of these centres
in each of the 9 regional federations within EGEE, and they act as
the
front line support for operations problems within the region, supporting
all the grid sites in that region.
- Core Infrastructure Centres (CIC). At the moment there are four
of these centres (CERN, CC-IN2P3 in Lyon, CNAF in Bologna, and RAL
in
the UK). These centres provide a grid "operator" on shift
- with the responsibility rotating through the four centres one week
at a time. The "CIC-on-duty" provides the oversight for
the grid operations, using a variety of monitoring tools as well
as direct
problem reports to find and analyse operational problems. Problems
are reported to the grid sites and their supervising ROC for follow
up, the CIC will ensure that problems are followed up and will provide
the escalation process if needed. In the near future (April 2005)
a fifth CIC will come on-line in Russia. In addition, the ASCC in
Taipei
also works as a grid operations centre, and will join this effort.
- Teams of experts at CERN and throughout the project also contribute
to the analysis and resolution of problems according to expertise.
The CICs follow problems in the full grid infrastructure, including
those sites not part of the EGEE project. In that case the oversight
and local support for problem follow up falls to the regional
Tier 1 centres or falls back to CERN.
Access to the operations procedures, checklists and further details
can be seen via the CIC portal maintained at Lyon.
Workshops:
- First
workshop was held in November 2004. Several working groups
were created to address various issues:
- Operations
- Operational security
- User support
- Fabric management
- A second workshop is planned for May 24-26 in Bologna.
|
|