Table of Contents
Query pre-execution
and batching in Paradise: a two-pronged approach to the
efficient processing of queries on tape-resident data
sets
Motivation
Approaches
Paper’s
approach
Example
Related work
Related work (cont.)
Related work (cont.)
Related work (cont.)
System architecture
Extensions to SHORE
SM
Extensions to SHORE
SM (cont.)
Extensions to SHORE
SM (cont.)
The big monster
Query processing
extensions
System-level object
abstraction
Query pre-execution
Cache-conscious tape
scheduling
Query batching
Performance
evaluation
Tertiary benchmark
queries
Single-user query
execution
Overhead
Scale Up
Multi-user query
execution
Batch size
sensitivity
Conclusions
|
Author: Renato
Ferreira Email: renato@cs.umd.edu
Home Page: Tools
and Techniques for Very Large Scale Data Intensive
Applications
|