what’s Data orchestration?
Bring your data closer to compute with data orchestration across clusters, regions, clouds, and countries
Data challenges in today’s disaggregated world
Today we see more enterprise architectures shifting to hybrid and multi-cloud environments. And while this shift allows for more flexibility and agility, it also means having to separate compute from storage, creating new challenges in how data needs to be managed and orchestrated across frameworks, clouds, and storage systems.
Data is not local to compute, leading to degraded workload performance.
The same data needs to be accessible to different, popular analytical & ML frameworks.
Running computation where data persists makes scaling extremely limited & expensive.
No self service data
To make data accessible to the users, complex ETL jobs are needed that copy data across different silos.
high Cost of management
Cloud storage egress costs continue to rise due to multiple data storage layers in the cloud.
unreliable s3 performance
Today’s object storage capabilities are not ready for interactive big data workloads.
High availability, storage system data management and disaster recovery is complex.
limiteD DATA security
No unified way to secure data across different clouds and storage systems.
The need for a new layer
To address these data challenges, enterprises are adopting a new layer: the data orchestration layer. A unified data orchestration layer simplifies your data’s cloud journey.
A data orchestration layer fundamentally enables separation of storage and compute. It brings speed and agility to big data and AI workloads and reduces costs by eliminating data duplication and enables users to move to newer storage solutions like object stores.
Alluxio – Data orchestration for The cloud
Alluxio is a compute agnostic, storage agnostic and cloud agnostic solution for big data and machine learning applications.
Data is local to compute, giving you memory-speed access for your big data and AI/ML workloads
Data is accessible through one unified namespace, regardless of where it resides
Data is as elastic as compute so you can abstract and independently scale compute and storage