1 / 5

High-Performance Querying on RAW Data: Efficient Database Management and Analysis Strategies

This article discusses advanced techniques for querying RAW data, overcoming obstacles like vendor lock-in and inefficient ETL processes. It details the benefits of using a database to run queries directly on RAW data files, and how to leverage relational DBMS alongside MapReduce engines for optimal performance. Through declarative querying and flexible data management, the approach allows for seamless integration of complex data structures. Application examples, like Higgs analysis with RAW data, illustrate the significant performance improvements achieved, making data reporting and analysis both efficient and effective.

kyne
Télécharger la présentation

High-Performance Querying on RAW Data: Efficient Database Management and Analysis Strategies

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. High-Performance Queryingon RAW data Anastasia Ailamaki EPFL

  2. create a database to run queries RAW DATA FILES LOAD INTO DB REPORT RESULTS QUERY APPLICATIONS Source: “An Overview of Business Intelligence Technology”. S. Chaudhuri, U. Dayal, V. Narasayya. CACM August 2011 data-to-query time too long data “locked” in vendor private data: no move, no copy

  3. run queries to create a database Relational DBMS MapReduce Engine Data Virtualization and Harmonization … Enterprise Search Engine … External Data Sources Operational Databases … Reporting Server Spreadsheet invest only in interesting data

  4. easy for you to say • No ETL • Declarative querying is king • Complex data: tables; arrays; hierarchies • large-scale vertical integration • Flexibility: multiple file formats; no static schemas; … • Efficiency!

  5. Higgs analysis with RAW SELECT event.jet… FROM goodruns.CSV, atlas001.root WHERE csv.RunNumber == root.RunNumber AND root.EF_2mu13 == TRUE AND … join scan csv filter scan root Code Generate the Access Paths Code Generate the Query ROOT CSV Build Position and Data Caches … containing “good” run numbers RAW is 100x faster … containing physics events

More Related