Using TAGs to Speed up the ATLAS Analysis Process

In the ATLAS experiment, Tag Data, or short TAG, are event-level metadata -- thumbnail information about events to support efficient identification and selection of events of interest to a given analysis. TAG quantities range from detector status and trigger information to basic physics quantities, e. g. the number of loose electrons candidates and kinematic information for a limited number of these candidates sorted by their transverse momentum. The average TAG size per event is around 1kB, which is a factor 100 smaller than the Analysis Object Data (AOD) used for physics analysis. TAGs are primarily produced from AODs and stored in ROOT files. For easier access and usability TAGs are also stored in a database. Queries to the database can produce again TAG files. In a standard ATLAS analysis job, TAGs can be used to preselect events based on the TAG quantities before accessing the full AOD content. This allows for s significant speed up of the processing time. This paper will discuss the different analysis work flows using TAGs and compare them with other analysis work flows within ATLAS. Further, the performance for preselecting events using either directly AODs, derived AODs or TAG files is measured and compared. Peak performance is estimated on a single machine, while realistic performance is estimated using large scale event processing using data collected by the ATLAS detector on the Grid using the ATLAS HammerCloud test suite.