Real-time configuration changes of the ATLAS High Level Trigger

F. Winklmeier
{"title":"Real-time configuration changes of the ATLAS High Level Trigger","authors":"F. Winklmeier","doi":"10.1109/RTC.2010.5750407","DOIUrl":null,"url":null,"abstract":"The ATLAS High Level Trigger (HLT) is a distributed real-time software system that performs the final online selection of events produced during proton-proton collisions at the Large Hadron Collider (LHC). It is designed as a two-stage trigger and event filter running on a farm of commodity PC hardware. Currently the system consists of about 850 processing nodes and will be extended incrementally following the expected increase in luminosity of the LHC to about 2300 nodes. The event selection within the HLT applications is carried out by specialized reconstruction algorithms. The selection can be controlled via properties that are stored in a central database and are retrieved at the startup of the HLT processes, which then usually run continuously for many hours. To be able to respond to changes in the LHC beam conditions, it is essential that the algorithms can be re-configured without disrupting data taking while ensuring a consistent and reproducible configuration across the entire HLT farm. The techniques developed to allow these real-time configuration changes will be exemplified on the basis of two applications: trigger prescales and beamspot measurement. The prescale value determines the fraction of events an HLT algorithm is being executed on, including when it is deactivated. This feature is both essential during the commissioning phase of the HLT as well as for adjusting the mixture of recorded physics events during an LHC run. The primary event vertex distribution, from which the beam spot position and size can be extracted, is measured by a dedicated HLT algorithm on each node and periodically aggregated across the HLT farm and its parameters are published and stored in the conditions database. The result can be fed back to the HLT algorithms to maintain selection efficiency and rejections rates. Finally, the technologies employed to allow the simultaneous database access of thousands of applications in an online environment will be shown.","PeriodicalId":345878,"journal":{"name":"2010 17th IEEE-NPSS Real Time Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 17th IEEE-NPSS Real Time Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RTC.2010.5750407","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

Abstract

The ATLAS High Level Trigger (HLT) is a distributed real-time software system that performs the final online selection of events produced during proton-proton collisions at the Large Hadron Collider (LHC). It is designed as a two-stage trigger and event filter running on a farm of commodity PC hardware. Currently the system consists of about 850 processing nodes and will be extended incrementally following the expected increase in luminosity of the LHC to about 2300 nodes. The event selection within the HLT applications is carried out by specialized reconstruction algorithms. The selection can be controlled via properties that are stored in a central database and are retrieved at the startup of the HLT processes, which then usually run continuously for many hours. To be able to respond to changes in the LHC beam conditions, it is essential that the algorithms can be re-configured without disrupting data taking while ensuring a consistent and reproducible configuration across the entire HLT farm. The techniques developed to allow these real-time configuration changes will be exemplified on the basis of two applications: trigger prescales and beamspot measurement. The prescale value determines the fraction of events an HLT algorithm is being executed on, including when it is deactivated. This feature is both essential during the commissioning phase of the HLT as well as for adjusting the mixture of recorded physics events during an LHC run. The primary event vertex distribution, from which the beam spot position and size can be extracted, is measured by a dedicated HLT algorithm on each node and periodically aggregated across the HLT farm and its parameters are published and stored in the conditions database. The result can be fed back to the HLT algorithms to maintain selection efficiency and rejections rates. Finally, the technologies employed to allow the simultaneous database access of thousands of applications in an online environment will be shown.
ATLAS高电平触发器的实时配置变化
ATLAS高水平触发(HLT)是一种分布式实时软件系统,用于对大型强子对撞机(LHC)质子-质子碰撞过程中产生的事件进行最终在线选择。它被设计成一个运行在商用PC硬件上的两级触发器和事件过滤器。目前,该系统由大约850个处理节点组成,并将随着LHC亮度的预期增加而逐步扩展到大约2300个节点。HLT应用程序中的事件选择由专门的重建算法执行。可以通过存储在中央数据库中的属性来控制选择,并在HLT进程启动时检索这些属性,然后HLT进程通常会连续运行许多小时。为了能够对LHC束流条件的变化做出反应,必须能够在不中断数据采集的情况下重新配置算法,同时确保整个HLT场的配置一致且可重复。为实现这些实时配置变化而开发的技术将以两种应用为基础进行举例说明:触发预刻度和波束点测量。预缩放值确定正在执行HLT算法的事件的比例,包括何时停用该算法。该功能在HLT调试阶段以及在LHC运行期间调整记录的物理事件混合中都是必不可少的。主事件顶点分布,从中可以提取光束光斑的位置和大小,由每个节点上的专用HLT算法测量,并定期在HLT场上聚合,其参数被发布并存储在条件数据库中。结果可以反馈到HLT算法中,以保持选择效率和拒绝率。最后,将展示用于允许在线环境中数千个应用程序同时访问数据库的技术。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信