Aster Data nCluster:
Dynamic Workload Management

Not all Workloads are Created Equal

Data management has become a complex environment as companies rely increasingly on data-driven applications and ultra-fast analytics across all sectors of the organization. Along with traditional back-office decision support and business intelligence, data warehouses are now expected to serve a broad range of applications and users in their daily business operations. These “Big Data” deployments need to be well-managed to optimize performance and maximize hardware investment – in particular to avoid replicating data and systems just to manage different workloads.

Aster Data's Industry-Leading Dynamic Workload Manager

Aster Data provides the first-ever dynamic workload management capability for a massively parallel processing (MPP) system that runs on commodity hardware. Aster Data’s Dynamic Workload Management ensures highly predictable performance and guaranteed service levels for the complex mixed workloads of an enterprise data warehouse and analytic-intensive applications. Intuitive, fine-grained policy controls allow administrators to define and manage diverse workloads to meet the organization’s business priorities. The ability to dynamically reallocate CPU and storage resources based on in-progress transactions ensures that time-critical queries can be processed immediately.

  • Dynamic Workload Management – A unique dynamic workload manager effortlessly balances processing and compute resources to in-progress transactions, allowing administrators to seamlessly adapt to changing priorities in real time. Includes granular rule-based prioritization (pre-admission control) and dynamic resource allocation and re-allocation.

Aster Data's Dynamic Workload Management ensures high user concurrency and predictable service levels

  • Interactive Queries – Sub-second response for hundreds of concurrent queries (e.g., DDL, DML statements) enables near real-time analytical processing for thousands of simultaneous users.
  • Trickle-Feed Loads – Up-to-the-second loading provides access to the freshest data for time-sensitive analytics. Both trickle-feed and bulk loads can execute concurrently with queries.

 

The Best Insights Possible
White Paper: A Revolutionary Approach for Advanced Analytics and Big Data Management
Data Sheet:
Aster Database
Analytic Platform
Technology Brief: Aster Database – Dynamic Workload Management
Aster Data's mixed-workload management enables large numbers of users to not just access the system, but also run simultaneous interactive queries with little or no latency - a key enabler in delivering real-time operational analytics.

IDC
Dan Vesset, Program Vice President, Business Analytics