Thesis /

ROMDOC-THESIS-2017-1064

Advanced visualization system for monitoring in real time the data acquisition network for the ATLAS LHC detector

Bătrâneanu, Silvia-Maria
2012-06-17

Abstract: The data acquisition (TDAQ) system of the ATLAS experiment at CERN comprises approximately 2500 servers interconnected by three separate Ethernet networks, totaling 250 switches. Due to the system’s real-time nature and its complexity, performance requirements go beyond the ones characterizing conventional networks. Health and performance monitoring tools to gather historical and real-time statistics are needed to understand the system’s behavior, to ensure proper operation and to perform efficient troubleshooting. In order to maintain a complete system view, the information cannot be restricted to just network-specific statistics but must include complementary parameters such as environmental statistics, data-taking variables, physical and logical mappings. Non experts may experience difficulties in interpreting this big data volume. Moreover, specific performance issues, such as single component saturation or unbalanced workload, need to be spotted with ease, in real-time, and understood in the context of the full system view. The contribution of this thesis lies in the design, implementation and optimization of an innovative visualization system where the users benefit from the advantages of 3D graphics to visualize the large monitoring variable space associated with our system. This visualization system uses a hierarchical model of the complete system onto which we overlaid geographical, logical and real-time monitoring information. In order to easily understand the current state of subsystems and how they interact, the system performs bottom-up statistics aggregation and error propagation. At every aggregation layer, historical statistics plots are available to track recent component behavior. Advanced navigation techniques, such as navigation paradigms (walking, flying) and predefined viewpoints, have been adapted to the TDAQ system particularities, hence providing intuitive user interaction and navigation scenarios. This allows the user to reach any desired information in a few clicks and navigate inside and between hierarchical levels with ease. Visualizing thousands of objects which are frequently updated makes the 3D scene rendering a challenging task. Multiple low-level optimizations had to be performed in order to reach the optimal frame rate. A full scene update is very disruptive for navigation, and therefore the scene is updated progressively using a targeted update mechanism based on object visibility. The Level of Detail technique is used to hide expensive details when they are not distinguishable and hence speed up the rendering.

Keyword(s): Achiziţii de date, Sisteme -- Teză de doctorat ; Acceleratoare de particule -- Teză de doctorat ; Monitorizare tehnică -- Teză de doctorat
OPAC: See record in BC-UPB Web OPAC
Full Text: see files

Similar records

 

People who viewed this page also viewed:

(259)  Optimizarea conceptuală şi operaţională a instalaţiilor chimice multiscop - Voinescu, Sorin - ROMDOC-BC_UPB-THESIS-2003-000000054 (253)  Scientific Bulletin Series C:Electrical engineering - ROMDOC-Journal-2007-003 (253)  Managementul congestiilor în sistemele electroenergetice în prezenţa surselor regenerabile - Boambă, Claudia-Elena - ROMDOC-THESIS-2021-2325 (253)  Analiza aerosolilor prin tehnici şi metode membrane - Dănciulescu, Valeriu - ROMDOC-THESIS-2017-1399 (251)  Cercetări privind dezvoltarea de interfeţe utilizator virtuale pentru aplicaţii de teleoperare în robotică - Popa, Stelian - ROMDOC-THESIS-2021-2322

 

Rate this document:

Be the first to review this document.

Discuss this document:

Start a discussion about any aspect of this document.