DAOS
SeongJae Park, Madhuparna Bhowmik, Alexandru Uta
Abstract
In data-intensive workloads, data placement and memory management are inherently difficult: the programmer and the operating system have to choose between (combinations of) DRAM and storage, replacement policies, as well as paging sizes. Efficient memory management is based on fine-grained data access patterns driving placement decisions. Current solutions in this space cannot be applied to general workloads and production systems due to either unrealistic assumptions or prohibitive monitoring overheads.
Topics & Concepts
PagingComputer scienceProgrammerDramOperating systemMemory managementStorage managementData accessDatabaseEmbedded systemComputer hardwareSemiconductor memoryParallel Computing and Optimization TechniquesAdvanced Data Storage TechnologiesCloud Computing and Resource Management