HBase Tables Research Articles

HBase/Phoenix-based Data Collection and Storage for the ATLAS EventIndex

The ATLAS EventIndex is the global catalogue of all ATLAS real and simulated events. During the LHC long shutdown between Run 2 (20152018) and Run 3 (2022-2025) its components were substantially revised, and a new system was deployed for the start of Run 3 in Spring 2022. The new core storage system is based on HBase tables with a Phoenix interface. It allows faster data ingestion rates and scales better than the old system. This paper describes the data collection, the technical design of the core storage, and the properties that make it fast and efficient, namely the compact and optimized design of the events table, which already holds more than 400 billion entries, and all the auxiliary tables, and the EventIndex Supervisor, in charge of orchestrating the whole data collection, now simplified thanks to the Loaders, the Spark jobs that load the data into the new core system. The extractors, in charge of preparing the pieces of data that the loaders will put into the final back-end, have been updated too. The data migration from HDFS to HBase and Phoenix is also described.

XML2HBase: Storing and querying large collections of XML documents using a NoSQL database system

Many big data applications such as smart transportation, healthcare, and e-commerce need to store and query large collections of small XML documents, which has become a fundamental problem. However, existing solutions are inadequate to deliver satisfactory query performance in such circumstances. In this paper, we propose a framework named XML2HBase to address this problem using HBase, a widely deployed NoSQL database. Within this framework, we design a novel encoding scheme called Pathed-Dewey Order and a two-layer mapping method to store XML documents in HBase tables. XML queries, which are represented as XPath expressions, are evaluated through their translation into queries over HBase tables. Based on an in-depth analysis of the characteristics of the proposed approach, we design and integrate four optimization strategies to reduce storage space and query response time. Extensive experiments on two well-known XML benchmarks demonstrate the superior performance of XML2HBase over three state-of-the-art methods.

Enabling Massive XML-Based Biological Data Management in HBase.

Publishing biological data in XML formats is attractive for organizations who would like to provide their bioinformatics resources in an extensible and machine-readable format. In the era of big data, massive XML-based biological data management is emerged as a challengeable issue. With the continuous growth of the XML-based biological data sets, it is usually frustrating to use traditional declarative query languages to provide efficient query capabilities in terms of processing speed and scale. In this study, we report a novel platform to store and query massive XML-based biological data collections. A prototype tool for constructing HBase tables from XML-based biological data collections is first developed, and then a formal approach to transform the XML query model into the MapReduce query model is proposed. Finally, an evaluation of the query performance of the proposed approach on the existing XML-based biological databases is presented, showing that the performance advantages of the proposed solution. The source code of the massive XML-based biological data management platform is freely available at https://github.com/lyotvincent/X2H.

Data-centric Graphical User Interface of the ATLAS Event Index Service

The Event Index service of the ATLAS experiment at the LHC keeps references to all real and simulated events. Hadoop Map files and HBase tables are used to store the Event Index data, a subset of data is also stored in the Oracle database. Several user interfaces are currently used to access and search the data, from a simple command line interface, through a programmable API, to sophisticated graphical web services. It provides a dynamic graph-like overview of all available data (and data collections). Data are shown together with their relations, like paternity or overlaps. Each data entity then gives users a set of actions available for the referenced data. Some actions are provided directly by the Event Index system, others are just interfaces to different ATLAS services. In many cases, specialized views are offered for detailed data inspection, such as histograms, Venn diagrams, etc. This paper documents the current status of the service, its features and performance. The future system evolution to the new Event Index architecture based on the Apache Phoenix is also described as well as possible extension to a more general framework for giving a new, more intuitive access to experiment data.

The ATLAS EventIndex for LHC Run 3

The ATLAS EventIndex was designed in 2012-2013 to provide a global event catalogue and limited event-level metadata for ATLAS analysis groups and users during the LHC Run 2 (2015-2018). It provides a good and reliable service for the initial use cases (mainly event picking) and several additional ones, such as production consistency checks, duplicate event detection and measurements of the overlaps of trigger chains and derivation datasets. The LHC Run 3, starting in 2021, will see increased data-taking and simulation production rates, with which the current infrastructure would still cope but may be stretched to its limits by the end of Run 3. This proceeding describes the implementation of a new core storage service that will be able to provide at least the same functionality as the current one for increased data ingestion and search rates, and with increasing volumes of stored data. It is based on a set of HBase tables, with schemas derived from the current Oracle implementation, coupled to Apache Phoenix for data access; in this way we will add to the advantages of a BigData based storage system the possibility of SQL as well as NoSQL data access, allowing to re-use most of the existing code for metadata integration.

Integrating an openEHR-based personalized virtual model for the ageing population within HBase

BackgroundFrailty is a common clinical syndrome in ageing population that carries an increased risk for adverse health outcomes including falls, hospitalization, disability, and mortality. As these outcomes affect the health and social care planning, during the last years there is a tendency of investing in monitoring and preventing strategies. Although a number of electronic health record (EHR) systems have been developed, including personalized virtual patient models, there are limited ageing population oriented systems.MethodsWe exploit the openEHR framework for the representation of frailty in ageing population in order to attain semantic interoperability, and we present the methodology for adoption or development of archetypes. We also propose a framework for a one-to-one mapping between openEHR archetypes and a column-family NoSQL database (HBase) aiming at the integration of existing and newly developed archetypes into it.ResultsThe requirement analysis of our study resulted in the definition of 22 coherent and clinically meaningful parameters for the description of frailty in older adults. The implemented openEHR methodology led to the direct use of 22 archetypes, the modification and reuse of two archetypes, and the development of 28 new archetypes. Additionally, the mapping procedure led to two different HBase tables for the storage of the data.ConclusionsIn this work, an openEHR-based virtual patient model has been designed and integrated into an HBase storage system, exploiting the advantages of the underlying technologies. This framework can serve as a base for the development of a decision support system using the openEHR’s Guideline Definition Language in the future.

Distributed snapshot maintenance in wide-column NoSQL databases using partitioned incremental ETL pipelines

Wide-column NoSQL databases are an important class of NoSQL (Not only SQL) databases which scale horizontally and feature high access performance on sparse tables. With current trends towards big Data Warehouses (DWs), it is attractive to run existing business intelligence/data warehousing applications on higher volumes of data in wide-column NoSQL databases for low latency by mapping multidimensional models to wide-column NoSQL models or using additional SQL add-ons. For examples, applications like retail management can run over integrated data sets stored in big DWs or in the cloud to capture current item-selling trends. Many of these systems also employ Snapshot Isolation (SI) as a concurrency control mechanism to achieve high throughput for read-heavy workloads. SI works well in a DW environment, as analytical queries can now work on (consistent) snapshots and are not impacted by concurrent update jobs performed by online incremental Extract-Transform-Load (ETL) flows that refresh fact/dimension tables. However, the snapshot made available in the DW is often stale, since at the moment when an analytical query is issued, the source updates (e.g. in a remote retail store) may not have been extracted and processed by the ETL process in time due to high input data volume or slow processing speed. This staleness may cause incorrect results for time-critical decision support queries. To address this problem, snapshots which are supposed to be accessed by analytical queries need to be first maintained by corresponding ETL flows to reflect source updates based on given freshness needs. Snapshot maintenance in this work means maintaining the distributed data partitions that are required by a query. Since most NoSQL databases are not ACID compliant and do not provide full-fledged distributed transaction support, snapshot may be inconsistently derived when its data partitions are updated by different ETL maintenance jobs.This paper describes an extended version of HBelt system [1] which tightly integrates the wide-column NoSQL database HBase with a clustered & pipelined ETL engine. Our objective is to efficiently refresh HBase tables with remote source updates while a consistent snapshot is guaranteed across distributed partitions for each scan request in analytical queries. A consistency model is defined and implemented to address so-called distributed snapshot maintenance. To achieve this, ETL jobs and analytical queries are scheduled in a distributed processing environment. In addition, a partitioned, incremental ETL pipeline is introduced to increase the performance of ETL (update) jobs. We validate the efficiency gain in terms of data pipelining and data partitioning using the TPC-DS benchmark, which simulates a modern decision support system for a retail product supplier. Experimental results show that high query throughput can be achieved in HBelt when distributed, refreshed snapshots are demanded.