Wildfire: HTAP for Big Data

Ronald Barber; Vijayshankar Raman; Richard Sidle; Yuanyuan Tian; Pinar Tözün

doi:10.1007/978-3-319-63962-8257-1

Wildfire: HTAP for Big Data

Ronald Barber, Vijayshankar Raman, Richard Sidle, Yuanyuan Tian, Pinar Tözün

Research output: Conference Article in Proceeding or Book/Report chapter › Encyclopedia chapter › Research › peer-review

Abstract

Emerging large-scale real-time analytic applications (real-time inventory/pricing /recommendations, fraud detection, risk analysis, IoT, etc.) require data management systems that can handle fast transactions (OLTP) and analytics (OLAP) simultaneously. Some of them even require analytical queries as part of a transaction. Efficient processing of transactional and analytical requests, however, leads to different design decisions in a system. This article presents the Wildfire system, which targets hybrid transactional and analytical processing (HTAP) for big data. Wildfire leverages Apache Spark to enable large-scale data processing with different types of complex analytical requests and columnar data processing to enable fast transactions and analytics concurrently.

Original language	English
Title of host publication	Encyclopedia of Big Data Technologies
Publisher	Springer
Publication date	2019
ISBN (Electronic)	978-3-319-63962-8
DOIs	https://doi.org/10.1007/978-3-319-63962-8257-1
Publication status	Published - 2019

Access to Document

10.1007/978-3-319-63962-8257-1

https://doi.org/10.1007/978-3-319-63962-8257-1

Cite this

@inbook{ab490dfdc8064e18b58cb4c3b68319cd,

title = "Wildfire: HTAP for Big Data",

abstract = "Emerging large-scale real-time analytic applications (real-time inventory/pricing /recommendations, fraud detection, risk analysis, IoT, etc.) require data management systems that can handle fast transactions (OLTP) and analytics (OLAP) simultaneously. Some of them even require analytical queries as part of a transaction. Efficient processing of transactional and analytical requests, however, leads to different design decisions in a system. This article presents the Wildfire system, which targets hybrid transactional and analytical processing (HTAP) for big data. Wildfire leverages Apache Spark to enable large-scale data processing with different types of complex analytical requests and columnar data processing to enable fast transactions and analytics concurrently.",

author = "Ronald Barber and Vijayshankar Raman and Richard Sidle and Yuanyuan Tian and Pinar T{\"o}z{\"u}n",

note = "Note til JCG: ingen BFI-points for denne publikationstype. /PFOR 13-12-2019 JCG: husk at slette denne note.",

year = "2019",

doi = "10.1007/978-3-319-63962-8257-1",

language = "English",

booktitle = "Encyclopedia of Big Data Technologies",

publisher = "Springer",

address = "Germany",

}

TY - ENCYC

T1 - Wildfire: HTAP for Big Data

AU - Barber, Ronald

AU - Raman, Vijayshankar

AU - Sidle, Richard

AU - Tian, Yuanyuan

AU - Tözün, Pinar

N1 - Note til JCG: ingen BFI-points for denne publikationstype. /PFOR 13-12-2019 JCG: husk at slette denne note.

PY - 2019

Y1 - 2019

N2 - Emerging large-scale real-time analytic applications (real-time inventory/pricing /recommendations, fraud detection, risk analysis, IoT, etc.) require data management systems that can handle fast transactions (OLTP) and analytics (OLAP) simultaneously. Some of them even require analytical queries as part of a transaction. Efficient processing of transactional and analytical requests, however, leads to different design decisions in a system. This article presents the Wildfire system, which targets hybrid transactional and analytical processing (HTAP) for big data. Wildfire leverages Apache Spark to enable large-scale data processing with different types of complex analytical requests and columnar data processing to enable fast transactions and analytics concurrently.

AB - Emerging large-scale real-time analytic applications (real-time inventory/pricing /recommendations, fraud detection, risk analysis, IoT, etc.) require data management systems that can handle fast transactions (OLTP) and analytics (OLAP) simultaneously. Some of them even require analytical queries as part of a transaction. Efficient processing of transactional and analytical requests, however, leads to different design decisions in a system. This article presents the Wildfire system, which targets hybrid transactional and analytical processing (HTAP) for big data. Wildfire leverages Apache Spark to enable large-scale data processing with different types of complex analytical requests and columnar data processing to enable fast transactions and analytics concurrently.

U2 - 10.1007/978-3-319-63962-8257-1

DO - 10.1007/978-3-319-63962-8257-1

M3 - Encyclopedia chapter

BT - Encyclopedia of Big Data Technologies

PB - Springer

ER -

Wildfire: HTAP for Big Data

Abstract

Access to Document

Fingerprint

Cite this