| Paper |
Title |
Page |
| TUP001 |
Monitoring the LHCb Experiment Computing Infrastructure with NAGIOS
|
96 |
| |
- E. Bonaccorsi, N. Neufeld
CERN, Geneva
|
|
| |
LHCb has a large and complex infrastructure consisting of thousands of servers and embedded computers, hundreds of network devices and a lot of shared infrastructure services such as shared storage, login and time services, databases and many more. All operationallly critical aspects are integrated into the standard Experiment Control System based on PVSSII. This enables non-expert operators to do first-line reactions. At the lower level and in particular for monitoring the infrastructure the Control System itself depends on a secondary infrastructure based on the industry standard NAGIOS has been put in place. We present the design and implementation of the fabric management based on NAGIOS. Care has been taken to complement rather than duplicate functionality available in the Experiment Control System.
|
|
| TUP002 |
Software Management in the LHCb Online System
|
99 |
| |
- N. Neufeld, E. Bonaccorsi, L. Brarda, J. Closier, G. Moine
CERN, Geneva
- H. Degaudenzi
EPFL, Lausanne
|
|
| |
LHCb has a large online IT infrastructure with thousands of servers and embedded systems, network routers and switches, databases and storage appliances. These systems run a large number of different applications on various operating systems. The dominant operating systems are Linux and MS-Windows. This large heterogenous environment, operated by a small number of administrators, requires that new software or updates can be pushed quickly, reliably and as automated as possible. We present here the general design of LHCb's software management along with the main tools: LinuxFC / Quattor and Microsoft SMS, how they have been adapted and integrated and discuss experiences and problems.
|
|
|
Poster
|
|