Buffering Database Operations for Enhanced Instruction Cache Performance

As more and more query processing work can be done in main memory, memory access is becoming a signicant cost component of database operations. Recent database re-search has shown that most of the memory stalls are due to second-level cache data misses and rst-level instruction cache misses. While a lot of research has focused on re-ducing the data cache misses, relatively little research has been done on improving the instruction cache performance of database systems. We rst answer the question \Why does a database system incur so many instruction cache misses? " We demonstrate that current demand-pull pipelined query execution engines suer from signicant instruction cache thrashing between dierent operators. We propose techniques to buer database operations during query execution to avoid instruction cache thrashing. We implement a new light-weight \buer " oper-ator and study various factors which may aect the cache performance. We also introduce a plan renement algorithm that considers the query plan and decides whether it is ben-e cial to add additional \buer " operators and where to put them. The benet is mainly from better instruction locality and better hardware branch prediction. Our techniques can be easily integrated into current database systems without signi cant changes. Our experiments in a memory-resident PostgreSQL database system show that buering techniques can reduce the number of instruction cache misses by up to 80 % and improve query performance by up to 15%. 1