Query Performance Measure

Context:
- It can range from being a Query CPU-Usage Measure to being a Query Cost Measure.
Example(s):
- Database Query Performance.
- Search Query Performance.
See: Microservice Latency, Response Time, CPU Time, Disk Reads.

References

"Querying 8.66 Billion Records, part II - a Performance and Cost Comparison between Starburst Presto and EMR SQL Engines."
- QUOTE: ... I used the same 1TB, TPC-H, ORC-formatted (Optimized Row Columnar) dataset from my previous article. TPC-H is considered an industry standard for measuring database performance and it consists of a standard data set and queries that I executed for these tests. All tests read data from the same 1TB TPC-H data set, stored in AWS S3. This data set contains approximately 8.66 billion records. ...

(Shtok et al., 2016) ⇒ Anna Shtok, Oren Kurland, and David Carmel. (2016). “Query Performance Prediction Using Reference Lists.” ACM Transactions on Information Systems (TOIS) 34, no. 4
- ABSTRACT: The task of query performance prediction is to estimate the effectiveness of search performed in response to a query when no relevance judgments are available. We present a novel probabilistic analysis of the performance prediction task. The analysis gives rise to a general prediction framework that uses pseudo-effective or ineffective document lists that are retrieved in response to the query. These lists serve as reference to the result list at hand, the effectiveness of which we want to predict. We show that many previously proposed prediction methods can be explained using our framework. More generally, we shed new light on existing prediction methods and establish formal common grounds to seemingly different prediction approaches. In addition, we formally demonstrate the connection between prediction using reference lists and fusion of retrieved lists, and provide empirical support to this connection. Through an extensive empirical exploration, we study various factors that affect the quality of prediction using reference lists.