Prototype of a File-Based High-Level Trigger in CMS

20th International Conference on Computing in High Energy and Nuclear Physics

物理学;计算机科学

Bauer, G.^6 ; Bawej, T.^2 ; Behrens, U.^1 ; Branson, J.^4 ; Chaze, O.^2 ; Cittolin, S.^4 ; Coarasa, J.A.^2 ; Darlea, G.-L.^6 ; Deldicque, C.^2 ; Dobson, M.^2 ; Dupont, A.^2 ; Erhan, S.^3 ; Gigi, D.^2 ; Glege, F.^2 ; Gomez-Ceballos, G.^6 ; Gomez-Reino, R.^2 ; Hartl, C.^2 ; Hegeman, J.^2 ; Holzner, A.^4 ; Masetti, L.^2 ; Meijers, F.^2 ; Meschi, E.^2 ; Mommsen, R.K.^5 ; Morovic, S.^2,7 ; Nunez-Barranco-Fernandez, C.^2 ; O'Dell, V.^5 ; Orsini, L.^2 ; Ozga, W.^2 ; Paus, C.^6 ; Petrucci, A.^2 ; Pieri, M.^4 ; Racz, A.^2 ; Raginel, O.^6 ; Sakulin, H.^2 ; Sani, M.^4 ; Schwick, C.^2 ; Spataru, A.C.^2 ; Stieger, B.^2 ; Sumorok, K.^6 ; Veverka, J.^6 ; Wakefiled, C.C.^2 ; Zejdl, P.^2

DESY, Hamburg, Germany^1

CERN, Geneva, Switzerland^2

University of California, Los Angeles

CA, United States^3

University of California, San Diego

CA, United States^4

FNAL, Chicago

IL, United States^5

Massachusetts Institute of Technology, Cambridge

MA, United States^6

Institute Rudjer Boskovic, Zagreb, Croatia^7

关键词: DAQ system;    File systems;    High-level triggers;    Level-1 triggers;    Local file systems;    Offline;    Online monitoring;    System implementation;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/513/1/012025/pdf
DOI  :  10.1088/1742-6596/513/1/012025

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The DAQ system of the CMS experiment at the LHC is upgraded during the accelerator shutdown in 2013/14. To reduce the interdependency of the DAQ system and the high-level trigger (HLT), we investigate the feasibility of using a file-system-based HLT. Events of ∼1 MB size are built at the level-1 trigger rate of 100 kHz. The events are assembled by ∼50 builder units (BUs). Each BU writes the raw events at ∼2GB/s to a local file system shared with Q(10) filter-unit machines (FUs) running the HLT code. The FUs read the raw data from the file system, select Q(1%) of the events, and write the selected events together with monitoring meta-data back to a disk. This data is then aggregated over several steps and made available for offline reconstruction and online monitoring. We present the challenges, technical choices, and performance figures from the prototyping phase. In addition, the steps to the final system implementation will be discussed.