TY - GEN
T1 - BlinkDB
T2 - 8th ACM European Conference on Computer Systems, EuroSys 2013
AU - Agarwal, Sameer
AU - Mozafari, Barzan
AU - Panda, Aurojit
AU - Milner, Henry
AU - Madden, Samuel
AU - Stoica, Ion
PY - 2013
Y1 - 2013
N2 - In this paper, we present BlinkDB, a massively parallel, approximate query engine for running interactive SQL queries on large volumes of data. BlinkDB allows users to trade-off query accuracy for response time, enabling interactive queries over massive data by running queries on data samples and presenting results annotated with meaningful error bars. To achieve this, BlinkDB uses two key ideas: (1) an adaptive optimization framework that builds and maintains a set of multi-dimensional stratified samples from original data over time, and (2) a dynamic sample selection strategy that selects an appropriately sized sample based on a query's accuracy or response time requirements. We evaluate BlinkDB against the well-known TPC-H benchmarks and a real-world analytic workload derived from Conviva Inc., a company that manages video distribution over the Internet. Our experiments on a 100 node cluster show that BlinkDB can answer queries on up to 17 TBs of data in less than 2 seconds (over 200 x faster than Hive), within an error of 2-10%.
AB - In this paper, we present BlinkDB, a massively parallel, approximate query engine for running interactive SQL queries on large volumes of data. BlinkDB allows users to trade-off query accuracy for response time, enabling interactive queries over massive data by running queries on data samples and presenting results annotated with meaningful error bars. To achieve this, BlinkDB uses two key ideas: (1) an adaptive optimization framework that builds and maintains a set of multi-dimensional stratified samples from original data over time, and (2) a dynamic sample selection strategy that selects an appropriately sized sample based on a query's accuracy or response time requirements. We evaluate BlinkDB against the well-known TPC-H benchmarks and a real-world analytic workload derived from Conviva Inc., a company that manages video distribution over the Internet. Our experiments on a 100 node cluster show that BlinkDB can answer queries on up to 17 TBs of data in less than 2 seconds (over 200 x faster than Hive), within an error of 2-10%.
UR - http://www.scopus.com/inward/record.url?scp=84877703682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84877703682&partnerID=8YFLogxK
U2 - 10.1145/2465351.2465355
DO - 10.1145/2465351.2465355
M3 - Conference contribution
AN - SCOPUS:84877703682
SN - 9781450319942
T3 - Proceedings of the 8th ACM European Conference on Computer Systems, EuroSys 2013
SP - 29
EP - 42
BT - Proceedings of the 8th ACM European Conference on Computer Systems, EuroSys 2013
Y2 - 15 April 2013 through 17 April 2013
ER -