LOS ALTOS, Calif. and AMSTERDAM, The Netherlands, June 19 – Elasticsearch, Inc., the company on a mission to make data useful to businesses by delivering the world’s most advanced search and analytics engine, today announced the 2.0 release of its Hadoop connector, Elasticsearch for Apache Hadoop, along with certification on Cloudera Enterprise 5. With Cloudera certification, Elasticsearch is now compatible across all Apache-based Hadoop distributions, including HortonWorks and MapR, helping businesses extract immediate insights regardless of where their hundreds of terabytes or even petabytes of data are stored.
Elasticsearch is the search and analytics engine behind the ELK stack, which also utilizes Logstash, a log management tool, and Kibana’s powerful data visualization capabilities to help businesses pull vital information from their data stores. When used in conjunction with Hadoop, organizations no longer need to run a batch process and wait hours to analyze their data — Elasticsearch for Apache Hadoop can pipe data to Elasticsearch for indexing as it’s being generated, making it available for search and analysis in a matter of seconds. Kibana can also be used to explore massive amounts of data in Elasticsearch through easy-to-generate pie charts, bar graphs, scatter plots, histograms, and more.
How Businesses Leverage Elasticsearch and Hadoop
Elasticsearch is becoming the critical piece of pulling data from any environment and getting it into the hands of developers, engineering leads, CTOs, and CIOs who need insight into moving parts of their business at the rate they are happening. Customer examples include:
- Klout, which stores petabytes of its 400 million+ users’ data in a Hadoop Distributed File System and connects it to Elasticsearch. Klout query results, used to build targeted marketing campaigns, are delivered in seconds rather than minutes.
- MutualMind, which enables customers like AT&T, Kraft, Nestle, and Starbucks to monitor their brands on social networks. After its Hadoop batches started taking 15+ minutes, MutualMind moved to Elasticsearch to power its real-time analytics, while utilizing Hadoop for statistical analysis.
- An international financial services firm that uses Elasticsearch to analyze its access logs in just minutes instead of having to wait hours to run MapReduce jobs. Because Elasticsearch provided insights so quickly on the firm’s large amounts of data, they’ve been able to increase the window of data they can analyze from one hour to a full week.
Key Features of Elasticsearch for Apache Hadoop
- The ability to read and write data between Hadoop and Elasticsearch: Lets businesses get immediate, actionable insights by writing their data to Elasticsearch for real-time search and analysis. Complex jobs that would normally take minutes or hours to run in Hadoop can be handled quickly in Elasticsearch and read right back to Hadoop.
- Native integration and support for popular Hadoop libraries: Lets users run queries natively on Hadoop through MapReduce, Hive, Pig, or Cascading APIs.
- Snapshot/Restore: Makes it easy to take a snapshot of data within Elasticsearch — perhaps a year’s worth — and archive it in Hadoop. At any time, the snapshot can be restored back to Elasticsearch for additional analysis.