The state of the art in distributed query processing
ACM Computing Surveys (CSUR)
Database-aware semantically-smart storage
FAST'05 Proceedings of the 4th conference on USENIX Conference on File and Storage Technologies - Volume 4
Enabling database-aware storage with OSD
MSST '07 Proceedings of the 24th IEEE Conference on Mass Storage Systems and Technologies
Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Breaking the memory wall in MonetDB
Communications of the ACM - Surviving the data deluge
Principles of Distributed Database Systems
Principles of Distributed Database Systems
MapReduce and parallel DBMSs: friends or foes?
Communications of the ACM - Amir Pnueli: Ahead of His Time
MapReduce: a flexible data processing tool
Communications of the ACM - Amir Pnueli: Ahead of His Time
The Star Schema Benchmark and Augmented Fact Table Indexing
Performance Evaluation and Benchmarking
Dremel: interactive analysis of web-scale datasets
Proceedings of the VLDB Endowment
Communications of the ACM
Workload-aware database monitoring and consolidation
Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
HotOS'13 Proceedings of the 13th USENIX conference on Hot topics in operating systems
Fast crash recovery in RAMCloud
SOSP '11 Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles
MEMSCALE: in-cluster-memory databases
Proceedings of the 20th ACM international conference on Information and knowledge management
Cache-conscious data placement in an in-memory key-value store
Proceedings of the 15th Symposium on International Database Engineering & Applications
| Hi-index | 0.00 |
A shared-nothing architecture is state-of-the-art for deploying a distributed analytical in-memory database management system: it preserves the in-memory performance advantage by processing data locally on each node but is difficult to scale out. Modern switched fabric communication links such as InfiniBand narrow the performance gap between local and remote DRAM data access to a single order of magnitude. Based on these premises, we introduce a distributed in-memory database architecture that separates the query execution engine and data access: this enables a) the usage of a large-scale DRAM-based storage system such as Stanford's RAMCloud and b) the push-down of bandwidth-intensive database operators into the storage system. We address the resulting challenges such as finding the optimal operator execution strategy and partitioning scheme. We demonstrate that such an architecture delivers both: the elasticity of a shared-storage approach and the performance characteristics of operating on local DRAM.