These 12 things make me hate Hadoop

Article author C. Oliver Andrew is a professional software consultant, as well as North Carolina, Durham, big data consulting company Software Integrators Open, President and founder. Using Hadoop for a long time, he found that these 12 things really affect the ease of use of Hadoop.

EBay open source new database technology Kylin, support TB to PB level data

EBay has been an open source database technology - Kylin, which uses a distributed processing and HBase data storage technology, the purpose is to allow the SQL Hadoop query returns faster results.

No limit: Pangu Master optimization optimization practice

Pangu is a distributed file system, Ali cloud flying platform. In the flying 5K project, cluster scale rapid expansion to 5000 nodes, the rapid expansion of the scale, on the dawn of the performance brought no small challenge. This share to ensure high performance and optimization scheme of Pangu Master.

ODPS technology framework and application practice

ODPS is a distributed massive data processing platform, which provides rich data processing functions and flexible programming framework. This article from the ODPS challenges, technical architecture, Hadoop migration to ODPS, the application of practical attention to lead us to a preliminary understanding of the status quo and prospects of ODPS.

Hadoop GridGain memory chip acceleration technology

[BDTC lecturer] the father of Hadoop Cutting:Lucene Doug to Hadoop of the open source

Founder Doug Cutting, Lucene, nutch and Hadoop open-source projects, with the work enthusiasm and down-to-earth attitude to create a legend of cloud computing and data field.

1/10 computing resources, 1/3 time consuming, Spark to subvert the MapReduce to maintain the sort records

Spark in memory computing more advantages are well known. However, in many people heart, disk data computing, Hadoop is still hale and hearty. In order to break this misunderstanding, recently Databricks and AWS together to complete a Gray Sort category of Benchmark Daytona, and to create a new record of the test.

Zero based learning Hadoop to get started work line guide (Junior)

LinkedIn open source machine learning tool kit: ml-ease

For developers, ml-ease is a very useful tool in big data machine learning applications, we look forward to feedback from the open source community.

Open source showdown, Apache Drill MapR will introduce enterprise applications

In just two years, Drill Apache has received more than 40 companies to support and contribute, and in recent days, more MapR to join the company's big data platform, as a developer preview version of the show to the user.
  • September 26, 2014
  • Sources:
  • share
Per page A total of 815 data < One... Five Six Seven Eight Nine Ten Eleven Twelve Thirteen ...Eighty-two >      To No. page GO
By CSDN and the "programmer" magazine editor and community co - building, covering large data and Hadoop field, extraction of the most essential Hadoop and big data technology content, four per week to send.

Hadoop community activities

Top_arrow