Nov 4 – 8, 2019
Adelaide Convention Centre
Australia/Adelaide timezone

Upgrade of CMS non-event data infrastructure for the Run 3 High Level Trigger

Nov 7, 2019, 3:30 PM
1h
Hall F (Adelaide Convention Centre)

Hall F

Adelaide Convention Centre

Poster Track 1 – Online and Real-time Computing Posters

Speaker

Remi Mommsen (Fermi National Accelerator Lab. (US))

Description

The CMS experiment at CERN is working to improve the selection capability of the High Level Trigger (HLT) system, in view of the re-start of the collisions for Run 3. One key factor on this scope is to enhance the ability of the Trigger to track the detector evolution during the data taking, along with the LHC Fill cycles. In particular, the HLT performance is sensitive to two areas of varying conditions: the evolution of the LHC luminous region parameters, changing frequently during the fill cycle, and the radiation-induced effects on the detectors, that become relevant within long data collection runs. In this context, the CMS Condition Database system has to fulfil the new requirements imposed, supporting the capability to deliver updates during the LHC fill with the required time granularity. In this contribution, we present the solution that CMS has implemented on the combined system HLT-Condition Database for these purposes. The main strategy, that substantially confirms the adoption of Oracle RDBMS technology ( for the data storage ) and Frontier Web Proxy Caches ( for the read access Tier ) will be described. The requirements of Latency, Consistency, and Reproducibility imposed by the HLT multi-process architecture will be discussed in detail. The results of the integration and stress tests will be also provided.

Consider for promotion Yes

Primary authors

Remi Mommsen (Fermi National Accelerator Lab. (US)) Giacomo Govi (University of Wisconsin Madison (US))

Presentation materials