18374944. ELASTIC COLUMN STORE WITH MINIMAL IMPACT ON WORKLOAD USING SMART EVICTION AND FAST REPOPULATION simplified abstract (Oracle International Corporation)

ELASTIC COLUMN STORE WITH MINIMAL IMPACT ON WORKLOAD USING SMART EVICTION AND FAST REPOPULATION

Organization Name

Oracle International Corporation

Inventor(s)

Hariharan Lakshmanan of Brisbane CA (US)

Teck Hua Lee of Newark CA (US)

Vinita Subramanian of Campbell CA (US)

Gary Smith of Auburn CA (US)

Lijian Wan of Mountain View CA (US)

Shasank Kisan Chavan of Mountain View CA (US)

Venkat Raman Senapati of Sunnyvale CA (US)

ELASTIC COLUMN STORE WITH MINIMAL IMPACT ON WORKLOAD USING SMART EVICTION AND FAST REPOPULATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18374944 titled 'ELASTIC COLUMN STORE WITH MINIMAL IMPACT ON WORKLOAD USING SMART EVICTION AND FAST REPOPULATION

Simplified Explanation

The patent application describes techniques for implementing an in-memory columnar data store that can dynamically adjust its size based on performance prediction data generated from database workload information. The system allocates memory for various components in a database system and determines optimal memory allocations for the in-memory columnar data store based on performance predictions.

• The system maintains allocations of volatile memory for multiple memory-consuming components in a database system.
• Performance prediction data is received for each memory-consuming component, containing predictions for different memory allocation sizes.
• A target memory allocation is determined for the in-memory columnar data store based on the performance predictions.
• An incrementally adjusted amount of memory is calculated for the in-memory columnar data store and allocated accordingly.

Potential Applications

This technology could be applied in various database management systems to optimize memory usage and improve performance based on workload predictions.

Problems Solved

1. Efficient memory management in database systems. 2. Dynamic adjustment of memory allocations based on performance predictions.

Benefits

1. Improved performance in database operations. 2. Optimal memory allocation for different components. 3. Enhanced scalability and flexibility in memory usage.

Potential Commercial Applications

Optimizing memory usage in large-scale database systems for enterprises.

Possible Prior Art

One possible prior art could be techniques for dynamic memory allocation in computer systems based on workload predictions.

Unanswered Questions

How does the system handle unexpected changes in workload that were not predicted?

The system may need to have mechanisms in place to dynamically adjust memory allocations in real-time based on actual workload changes.

What impact does this dynamic memory allocation have on overall system stability and reliability?

It would be important to assess the potential risks and trade-offs of dynamically adjusting memory allocations on system stability and reliability.

Original Abstract Submitted

Techniques are provided for implementing an in-memory columnar data store that is configured to either grow or shrink in response to performance prediction data generated from database workload information. A system maintains allocations of volatile memory from a given memory area for a plurality of memory-consuming components in a database system. The system receives for each memory-consuming component, performance prediction data that contains performance predictions for a plurality of memory allocation sizes for the memory-consuming components. The system determines a target memory allocation for an in-memory columnar data store based on the performance predictions. The system determines an incrementally adjusted amount of memory for the in-memory columnar data store and causes the incrementally adjusted amount to be allocated to the in-memory columnar data store.