Toward real-time data query systems in HEP

被引:2
作者
Pivarski, Jim [1 ]
Lange, David [1 ]
Jatuphattharachat, Thanat [2 ]
机构
[1] Princeton Univ, Phys Dept, Princeton, NJ 08544 USA
[2] Comp Engn Chulalongkorn Univ, Krung Thep Maha Nakhon 10330, Thailand
来源
18TH INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH (ACAT2017) | 2018年 / 1085卷
基金
美国国家科学基金会;
关键词
D O I
10.1088/1742-6596/1085/3/032044
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Exploratory data analysis tools must respond quickly to a user's questions, so that the answer to one question (e.g. a visualized histogram or fit) can influence the next. In some SQL-based query systems used in industry, even very large (petabyte) datasets can be summarized on a human timescale (seconds), employing techniques such as columnar data representation, caching, indexing, and code generation/JIT-compilation. This article describes progress toward realizing such a system for High Energy Physics (HEP), focusing on the intermediate problems of optimizing data access and calculations for "query sized" payloads, such as a single histogram or group of histograms, rather than large reconstruction or data-skimming jobs. These techniques include direct extraction of ROOT TBranches into Numpy arrays and compilation of Python analysis functions (rather than SQL) to be executed very quickly. We will also discuss the problem of caching and actively delivering jobs to worker nodes that have the necessary input data preloaded in cache. All of these pieces of the larger solution are available as standalone GitHub repositories, and could be used in current analyses.
引用
收藏
页数:7
相关论文
共 9 条
[1]  
[Anonymous], NUCL INSTRUM METH A
[2]  
Bockelman B, 2017, J PHYS C SERIES
[3]  
Bockelman B, 2017, ROOT BULKAPI FASTREA
[4]   APACHE DRILL: Interactive Ad-Hoc Analysis at Scale [J].
Hausenblas, Michael ;
Nadeau, Jacques .
BIG DATA, 2013, 1 (02) :100-104
[5]  
Jatuphattharachat T, 2017, FEMTO MESOS
[6]  
Pivarski J, 2017, OAMAP TOOLSET COMPUT
[7]  
Pivarski J, 2017, FAST ACCESS COLUMNAR
[8]  
Pivarski J., 2017, Uproot: minimalist root i/o in pure Python and numpy
[9]  
The Apache Arrow team, 2016, AP ARR POW COL MEM A