tailieunhanh - High-Performance Parallel Database Processing and Grid Databases- P2

High-Performance Parallel Database Processing and Grid Databases- P2: Parallel databases are database systems that are implemented on parallel computing platforms. Therefore, high-performance query processing focuses on query processing, including database queries and transactions, that makes use of parallelism techniques applied to an underlying parallel computing platform in order to achieve high performance. | 30 Chapter 1 Introduction SUMMARY This chapter focuses on three fundamental questions in parallel query processing namely why what and C asphio onc additional question based on the technological support. The more complete questions and their answers are summarized as follows. W7zy is parallelism necessary in database processing Because there is a largevoltnne of daaatobe processed anilrcitsonahle improved processm da is iseeqeu-ed. . What can be aodieooi by parallelism in database processing The objectives of parallel database processing are z linear speed up and ii linear scale up. Surorlinear speed upandsoporlineor scale up mayhappen occasionally but theyaremoraoO asiSe safect didme tdoi iSis mdinladgdt. How is parallelism pprforn io qdtoeaopooocedaino s There are four differeiHfnaihsol nrrallelisin avrolabluUop dataOasupepcnoSi ing z interquery pasallrlisni 0 iiOrdquerypesallelisin parallelism and iv mtecopesaSion darallelisicTrSdaeinay be sdmbinedin parallel processing rtadoicbsse job iairnlaa toachiove abetteraerformanae result. What facilities ofparalle l oomputing oorabe uaeOS There are four diffesent para eldaiabdsearch thctureo il saared-memoro ii shared-disk zzz eri d- ioeiib aad -tvlsUfaad-romelhino -s d itea reo Distributed computingmfrastructure is fast evolving. The architecture was monolithic in 1970s and since then during the last three decades developments have been exponential. uhraranilecturc leas open to distributed and latelyolrtualieotr ia tochalbresrs e remgmhesSiaa-cdidlhe form of Grid computing. dha Mea otGiid -sfo rnkc computin. a commodity. Computer uoersedoulddo abietf acoass alerdsouscossitoeiee b ouad the globe without Pieuwing the location cd Sic eesousce. And apayras-you-oa strategy can be apalied incomdutingi simao- ia -he state-oS-ale-leagaspnO electricity distributiun sraategies. Date storages have reached I te i t 5SUf because of the incrouao .