Welcome!

Open Source Authors: Jayaram Krishnaswamy, Michelle Drolet, Ignacio M. Llorente, Shelly Palmer, Si Chen

News Feed Item

Cloudera Impala Delivers Superior Performance on Open Hadoop Data Over Proprietary Analytic DBMSs

Emerges as Fastest, Most Functional and Proven Way to Run SQL on Hadoop Data

PALO ALTO, CA -- (Marketwired) -- 01/13/14 -- Cloudera, the leader in Apache Hadoop™ based data management platforms, today released the results of performance benchmark testing for its open source interactive SQL query engine, Cloudera Impala. Impala queries across data in an open Hadoop columnar storage format (Parquet) ran on average 2x faster than identical queries on a commercial analytic database management system (DBMS) over its proprietary storage format.

Cloudera delivers an enterprise data hub -- a next-generation platform for secure, powerful, real-time processing and analysis of data at scale. An enterprise data hub must provide data governance and lineage services, support enterprise-grade backup and disaster recovery and offer a wide range of ways to work with the data that it manages. It must support the tools and interfaces on which existing applications and tools rely. Critical among those is real-time SQL access for analytics.

Impala Delivers

Launched in October 2012 and released for general availability in May 2013, Impala enables high speed, interactive SQL analysis of Hadoop data at petabyte scale. Today Impala has emerged as the fastest, most functional and proven way to run SQL on Hadoop data for open source users and enterprise customers alike. The platform has continued to evolve rapidly with deepening support for the ANSI-SQL standard, certified integrations to leading business intelligence tools, sophisticated workload management and consistently superior performance.

Impala deployments continue to proliferate in the enterprise: to date, the platform has been downloaded by more than 5,000 unique organizations globally, demonstrating its appeal and significance. Cloudera continues to work closely with its enterprise customers and the open source community to refine and advance Impala's enterprise features, like Apache Sentry (incubating), the fine-grained, role-based authorization module released this year. Further establishing Impala's leadership in the industry, Hadoop-based solutions from other vendors integrate the Cloudera-created SQL query engine into their own offerings in response to customer demand.

Analytic DBMS Performance on Open Data in the Enterprise Data Hub

Running a diverse set of analytic queries on identical hardware, Impala has successfully eclipsed the performance of a popular proprietary parallel DBMS. The same benchmarks also showed Impala has maintained or widened its performance advantage against the latest release of Apache Hive (0.12).

Furthermore, it has done so on data in an open Hadoop data format. With these results, customers are able to exceed their SQL performance experiences from proprietary databases but preserve the flexibility they enjoy with the Hadoop stack.

The Proof Is In the Data: Impala Shows BI-Class Speed for Mainstream Workloads

To evaluate Impala's query performance against a popular analytic database (referred to as "DBMS-Y"), Cloudera ran a series of 20 queries based on the industry-standard benchmark TPC-DS. The results showed that:

  • Impala ran consistently faster than DBMS-Y: across 20 queries, Impala ran on average 2X to DBMS-Y, outperforming DBMS-Y in 17 of the 20 queries. For some queries, Impala was over 4x faster.

Queries over open data beat those over proprietary data: Even though Impala queries were done on openHadoop data in the Parquet format, and DBMS-Y queries were done on data in its own proprietary format. Impala was still faster.

  • Impala scales linearly and predictably: In tests, Impala maintained identical response times with increased user concurrency and on larger data sets by simply adding new machines at the same rate as the concurrency and data growth.
  • Furthermore, Impala is still more than an order of magnitude faster than Hive: on identical hardware Impala queries ran an average of 24x faster than those run on Apache Hive 0.12 using ORCfile.

No Sleight of hand, no gimmicks

Cloudera is committed to leading the industry as a high integrity business that provides unbiased information to customers and users. Dozens of users have download Cloudera's 100% open source platform, run their own performance evaluations, and shared them publicly. Cloudera places no confidentiality clauses or other proprietary restrictions on the use of its distribution. In addition, Cloudera has made the queries, configuration, hardware specifications, and data available for use for the open source community to review and evaluate. Information can be found at http://www.cloudera.com/impalaishellafast/

"Interactive exploratory business intelligence is a mainstay workload of the Enterprise Data Hub," said Mike Olson, founder, chief strategy officer and chairman of the Board at Cloudera. "We are proud of how quickly Impala has evolved and the rate at which it is being adopted. With thousands of users now running Impala in production, its significance is indisputable. One year ago, when we released Impala to open source, we knew that it had the potential to eventually play on the same field as some very mature analytic DBMSs, but the results of these performance benchmark tests exceed our very high expectations. In the coming months, we will unveil new enhancements to the platform that will further advance its performance, ease of use and security, extending Impala's benefits for open source users and our enterprise customers."

Learn More About Cloudera Impala
For a more detailed account of the methodology and results from Cloudera's Impala performance benchmark testing against Hive and a proprietary DBMS, visit the Cloudera blog: http://blog.cloudera.com/blog/2014/01/impala-performance-dbms-class-speed

For more information about Cloudera Impala and how to download for free, visit: http://cloudera.com/content/cloudera/en/products/cdh/impala.html

About Cloudera
Cloudera is revolutionizing enterprise data management by offering the first unified Platform for Big Data: The Enterprise Data Hub. Cloudera offers enterprises one place to store, process and analyze all their data, empowering them to extend the value of existing investments while enabling fundamental new ways to derive value from their data. Founded in 2008, Cloudera was the first and is still today the leading provider and supporter of Hadoop for the enterprise. Cloudera also offers software for business critical data challenges including storage, access, management, analysis, security and search. With over 15,000 individuals trained, Cloudera is a leading educator of data professionals, offering the industry's broadest array of Hadoop training and certification programs. Cloudera works with over 800 hardware, software and services partners to meet customers' big data goals. Leading organizations in every industry run Cloudera in production, including finance, telecommunications, retail, internet, utilities, oil and gas, healthcare, biopharmaceuticals, networking and media, plus top public sector organizations globally. www.cloudera.com

Connect with Cloudera
Read our blog: http://www.cloudera.com/blog/
Follow us on Twitter: http://twitter.com/cloudera
Visit us on Facebook: http://www.facebook.com/cloudera

Cloudera, Cloudera Platform for Big Data and CDH are trademarks or registered trademarks of Cloudera in the United States and in jurisdictions throughout the world. All other company and product names may be trade names or trademarks of their respective owners.

Add to Digg Bookmark with del.icio.us Add to Newsvine

More Stories By Marketwired .

Copyright © 2009 Marketwired. All rights reserved. All the news releases provided by Marketwired are copyrighted. Any forms of copying other than an individual user's personal reference without express written permission is prohibited. Further distribution of these materials is strictly forbidden, including but not limited to, posting, emailing, faxing, archiving in a public database, redistributing via a computer network or in a printed form.