TalkingData’s largest data broker, provides data intelligence solutions and processes over 20 terabytes of data and more than one billion session requests per day. TalkingData deployed Alluxio to unify disparate cloud, on-premise, and hybrid data sources for a range of analytics applications. The architecture provides self-service data access for data scientists and engineers, eliminating the need for ETL or manual IT assistance.
Myntra, a division of Flipkart, is a leading fashion retailer in India offering customers a wide range of merchandise through a mobile application. An analytics pipeline in Amazon Web Services (AWS) cloud processes customer data to make recommendations, present ads, and deliver other aspects of a tailored experience. Myntra deployed Alluxio to provide a virtual data layer connecting AWS S3 to the analytics pipeline to accelerate data access and enable faster customer response and interactive business intelligence.
Tencent, based in China, is one of the largest technology companies in the world and a leader in sectors such as social networking, gaming, ecommerce, mobile, and web portal. Tencent News provides a rich, tailored news experience to over 100 million active monthly users. In order to meet the strict Service Level Agreements (SLAs) required by the business for optimal customer experience, the company turned to Alluxio for performance, predictability, and scalability.
Quantitative hedge funds process large data sets with sophisticated financial models to drive investment decisions. Machine Learning is used to continuously improve models and maximize financial return. One firm with billions ($US) of assets under management turned to Alluxio to address the performance and cost challenges of large scale data processing in a hybrid cloud environment. With Alluxio, the number of model runs per day increased by 4x and the cost of compute was reduced by 95%.
Lenovo is the world’s largest personal computer vendor and one of the world’s largest smartphone vendors. The company has invested extensively in global information technology infrastructure, including ten data centers worldwide collecting petabytes of smartphone data. Analyzing data located in multiple data centers world-wide is critical for Lenovo to understand and improve the usability and reliability of their products.
In a real development environment our customers leverage ArcGIS to read and write geospatial data to a plethora of distributed data stores, such as Amazon S3, HDFS, or OpenStack Swift, and some of these data stores are not natively supported by the ArcGIS platform…
By leveraging Alluxio, Mesos, Minio, and Spark we have created an end-to-end data processing solution that is performant, scalable, and cost optimal. We use Alluxio as the unified storage layer to connect disparate storage systems and bring memory performance, with Minio mounted as the under store to Alluxio to keep cold (infrequently accessed) data and to sync data to AWS S3. Apache Spark serves as the compute engine.
At Qunar, we have been running Alluxio in production for over 9 months, resulting in 15x speedup on average, and 300x speedup at peak service times. In addition, Alluxio’s unified namespace enables different applications and frameworks to easily interact with our data from different storage systems.
As the largest Chinese language Internet search provider, Baidu is very experienced with stressing their production data serving systems. In this case study, Shaoshan Liu — senior architect at Baidu — shares his experiences with Alluxio in production, and how the technology has led to dramatic performance gains. With Alluxio, batch queries are transformed into interactive queries. This enables Baidu to discover insights interactively leading to increases in productivity by 10 fold and improvements in customer experience.