17529494. LOCK-FREE DATA AGGREGATION ON DISTRIBUTED SYSTEMS simplified abstract (International Business Machines Corporation)
LOCK-FREE DATA AGGREGATION ON DISTRIBUTED SYSTEMS
Organization Name
International Business Machines Corporation
Inventor(s)
Parth Sanjaybhai Shah of Bangalore (IN)
Ranjal Gautham Shenoy of Bangalore (IN)
LOCK-FREE DATA AGGREGATION ON DISTRIBUTED SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17529494 titled 'LOCK-FREE DATA AGGREGATION ON DISTRIBUTED SYSTEMS
Simplified Explanation
The invention is related to distributed systems and methods for fast and lock-free data aggregation. It involves a computer-implemented method where new data is produced at a first producer node in a distributed system consisting of multiple producer nodes, a consumer node, and a global view. The global view is a hierarchical binary tree of cell addresses, and each producer node has a local view of the global view. When new data is produced, the local view of the first producer node is updated with the new data and a local timestamp. If the local timestamp is greater than a global timestamp, a pointer in a cell address of the global view is flipped to point to the new data.
- The invention provides a method for fast and lock-free data aggregation in distributed systems.
- It involves a hierarchical binary tree structure for organizing and accessing data.
- Each producer node has a local view of the global view, allowing for efficient updates.
- The method ensures that the most recent data is always accessible by flipping pointers in the global view.
Potential Applications
- Big data processing and analysis
- Real-time data streaming and aggregation
- Distributed computing and parallel processing
Problems Solved
- Slow and inefficient data aggregation in distributed systems
- Locking and synchronization issues in concurrent data processing
- Difficulty in maintaining a global view of data across multiple nodes
Benefits
- Fast and efficient data aggregation
- Lock-free operation allows for concurrent processing
- Scalable and distributed approach for handling large volumes of data
Original Abstract Submitted
Aspects of the invention include distributed systems and methods that provide data aggregation in a fast, lock-free manner. A non-limiting example computer-implemented method includes producing new data at a first producer node of a distributed system having two or more producer nodes, a consumer node, and a global view. The global view includes a hierarchical binary tree of cell addresses. Each producer node includes a local view of the global view. Responsive to producing the new data, the local view of the first producer node is updated with the new data and a local timestamp and, if the local timestamp is greater than a global timestamp, a pointer in a cell address of the global view is flipped to point to the new data.