An incremental memory allocation method for mixed workloads

摘要

This paper proposes and investigates an incremental memory allocation method for mixed database workloads of simple hash-join queries and short read transactions. Traditionally, a DBMS allocates all memory reserved for a query at the beginning of the query execution. However, there may be a prolonged period from the time the query begins to the time that all reserved memory is actually consumed by the query process. We propose to allocate reserved memory to the query incrementally by smaller portions when the query process is actually ready to utilize this memory. Memory that was reserved but not yet allocated to the query can be used temporarily as a shared buffer pool by other components of the workload. Through a series of simulation experiments we demonstrate that the incremental memory allocation for hash-join queries improves the performance of read transactions without penalizing queries.