Filters








41 Hits in 2.7 sec

Columnstore and B+ tree - Are Hybrid Physical Designs Important?

Adam Dziedzic, Jingjing Wang, Sudipto Das, Bolin Ding, Vivek R. Narasayya, Manoj Syamala
2018 Proceedings of the 2018 International Conference on Management of Data - SIGMOD '18  
They also support variety in physical design structures such as B+ tree and columnstore. The benefits of B+ tree for OLTP workloads and columnstore for decision support workloads are well-understood.  ...  However, the importance of hybrid physical designs, consisting of both columnstore and B+ tree indexes on the same database, is not well-studied -a focus of this paper.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers, Craig Freedman, Vassilis Papadimos, and Miodrag Radulovic for their valuable feedback.  ... 
doi:10.1145/3183713.3190660 dblp:conf/sigmod/DziedzicWDDNS18 fatcat:fnrw7ibtlzbqbbsonvx77uo73y

Real-time analytical processing with SQL server

Per-Åke Larson, Adrian Birka, Eric N. Hanson, Weiyun Huang, Michal Nowakiewicz, Vassilis Papadimos
2015 Proceedings of the VLDB Endowment  
This paper describes four such enhancements: column store indexes on inmemory tables, making secondary column store indexes on diskbased tables updatable, allowing B-tree indexes on primary column store  ...  SQL Server 2016 will include enhancements to column store indexes and in-memory tables that significantly improve performance on such hybrid workloads.  ...  This paper describes four enhancements in the SQL Server 2016 release that are designed to improve performance on analytical queries in general and on hybrid workloads, in particular. 1 .  ... 
doi:10.14778/2824032.2824071 fatcat:laalabjbubgy5nwjrvhhklnu4e

The Internals of the Data Calculator [article]

Stratos Idreos, Kostas Zoumpatianos, Brian Hentschel, Michael S. Kester, Demi Guo
2018 arXiv   pre-print
Data structures are critical in any data-driven scenario, but they are notoriously hard to design due to a massive design space and the dependence of performance on workload and hardware which evolve continuously  ...  First, it offers a set of fine-grained design primitives that capture the first principles of data layout design: how data structure nodes lay data out, and how they are positioned relative to each other  ...  FROM MANUAL TO INTERACTIVE DESIGN The Importance of Data Structures.  ... 
arXiv:1808.02066v1 fatcat:jhtjudqdhvg73bl6hyospqpaxe

Parallel processing of very large databases using distributed column indexes

E. V. Ivanova, L. B. Sokolinsky
2017 Programming and computer software  
The development and investigation of efficient methods of parallel processing of very large databases using the columnar data representation designed for computer cluster is discussed.  ...  The column indexes are auxiliary structures that are constantly stored in the distributed main memory of a computer cluster.  ...  The proposed methods are designed for use with solid state drives and multicore processors.  ... 
doi:10.1134/s0361768817030069 fatcat:jr6nrdfyavhafbosqexkbii7p4

Block Binary Search Tree

Shengdun Wang
2019 DEStech Transactions on Engineering and Technology Research  
The paper Columnstore and B+ tree -Are Hybrid Physical Designs Important? [3] proves B+-tree is over-complicated. It distinguishes internal and leaf nodes in order to distinguish key and value.  ...  Design and implementation of BBST BBST is a binary tree with each tree node with a fixed-size array.  ... 
doi:10.12783/dtetr/eeec2018/26850 fatcat:rpmsetgz6vaxrip32mf2drwumq

Adaptive indexing in modern database kernels

Stratos Idreos, Stefan Manegold, Goetz Graefe
2012 Proceedings of the 15th International Conference on Extending Database Technology - EDBT '12  
The main idea is that physical design changes continuously, adaptively, partially, incrementally and on demand while processing queries as part of the execution operators.  ...  Physical design represents one of the hardest problems for database management systems. Without proper tuning, systems cannot achieve good performance.  ...  His best known works are in-depth surveys on query execution, sorting, and B-tree indexing.  ... 
doi:10.1145/2247596.2247667 dblp:conf/edbt/IdreosMG12 fatcat:j2r3q3uskfectfsd2sxr5agc4i

AI Meets AI

Bailu Ding, Sudipto Das, Ryan Marcus, Wentao Wu, Surajit Chaudhuri, Vivek R. Narasayya
2019 Proceedings of the 2019 International Conference on Management of Data - SIGMOD '19  
We present a study of the design space for this classification problem.  ...  Such errors are a major impediment for automated indexing in production systems.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers, our shepherd Matthias Boehm, Anshuman Dutt, and Arnd Christian König for their valuable feedback.  ... 
doi:10.1145/3299869.3324957 dblp:conf/sigmod/DingDM0CN19 fatcat:kaho47sbtbc6tc57c6j3edwwzi

Evolutionary Data Systems [article]

Stratos Idreos and Lukas M. Maas and Mike S. Kester
2017 arXiv   pre-print
In this paper, we present the vision of evolutionary data systems that free systems architects and application designers from the complex, cumbersome and expensive process of designing and tuning specialized  ...  In our initial prototype, we demonstrate solutions that can seamlessly evolve (back and forth) between a key-value store and a column-store architecture in order to adapt to changing workloads.  ...  In addition, within each category there are several variations to how we store and access data (e.g., row-stores, columnstores and hybrids in the SQL solution space).  ... 
arXiv:1706.05714v1 fatcat:q6dcuxk4hnaxfckw5mqutx6zoa

Concurrency control for adaptive indexing

Goetz Graefe, Felix Halim, Stratos Idreos, Harumi Kuno, Stefan Manegold
2012 Proceedings of the VLDB Endowment  
Our design adapts to the fact that an adaptive index is refined continuously, and exploits any concurrency opportunities in a dynamic way.  ...  We show that the design and implementation of adaptive indexing rigorously separates index structures from index contents; this relaxes the constraints and requirements during adaptive indexing compared  ...  There are three differences between a partitioned B-tree and a B-tree partitioned in a traditional parallel database management system.  ... 
doi:10.14778/2180912.2180918 fatcat:bnw2pruxubatthhlk3qnzxg4em

Concurrency Control for Adaptive Indexing [article]

Goetz Graefe, Felix Halim, Stratos Idreos, Harumi Kuno, Stefan Manegold
2012 arXiv   pre-print
Our design adapts to the fact that an adaptive index is refined continuously, and exploits any concurrency opportunities in a dynamic way.  ...  We show that the design and implementation of adaptive indexing rigorously separates index structures from index contents; this relaxes the constraints and requirements during adaptive indexing compared  ...  There are three differences between a partitioned B-tree and a B-tree partitioned in a traditional parallel database management system.  ... 
arXiv:1203.6405v1 fatcat:36d44ujj6nfatmk6qdhgqa5qru

Transactional support for adaptive indexing

Goetz Graefe, Felix Halim, Stratos Idreos, Harumi Kuno, Stefan Manegold, Bernhard Seeger
2014 The VLDB journal  
Our design adapts to the fact that an adaptive index is refined continuously and exploits any concurrency opportunities in a dynamic way.  ...  We show that the design and implementation of adaptive indexing rigorously separates index structures from index contents; this relaxes constraints and requirements during adaptive indexing compared to  ...  B link -trees and foster B-trees Adaptive indexing in the form of adaptive merging, which is discussed in Sect. 4, potentially physically restructures a B-tree's nodes with every query.  ... 
doi:10.1007/s00778-013-0345-7 fatcat:lyhrcbdfqzhibfyuwfjedeujsa

Beyond the Wall

Sam Likun Xi, Oreoluwa Babarinsa, Manos Athanassoulis, Stratos Idreos
2015 Proceedings of the 11th International Workshop on Data Management on New Hardware - DaMoN'15  
JAFAR implements the select operator and allows only qualifying data to travel up the memory hierarchy.  ...  Database systems researchers have proposed several innovative solutions to minimize data movement and to make data access patterns hardware-aware.  ...  This work is partially supported by the Swiss National Science Foundation and by the National Science Foundation under Grant No. IIS-1452595. REFERENCES  ... 
doi:10.1145/2771937.2771945 dblp:conf/damon/XiBAI15 fatcat:64jdkyszwnablgqfqpi37yvg7u

Access Path Selection in Main-Memory Optimized Data Systems

Michael S. Kester, Manos Athanassoulis, Stratos Idreos
2017 Proceedings of the 2017 ACM International Conference on Management of Data - SIGMOD '17  
New designs include columngroup storage, vectorized execution, shared scans, working directly over compressed data, and operating using SIMD and multi-core execution.  ...  Through detailed analytical modeling and experimentation we show that while scans have become useful in more cases than before, both access paths are still useful, and so, access path selection (APS) is  ...  physical design.  ... 
doi:10.1145/3035918.3064049 dblp:conf/sigmod/KesterAI17 fatcat:6fl5342c5bhsvoj7g5sv7hnf2e

Supporting multi-row distributed transactions with global snapshot isolation using bare-bones HBase

Chen Zhang, Hans De Sterck
2010 2010 11th IEEE/ACM International Conference on Grid Computing  
At their core, P-Trees are based on pure (immutable) data structures that use path-copying for updates for fast multi-versioning.  ...  We evaluate P-Trees on OLTP and OLAP benchmarks, and compare them with state-of-the-art data structures and DBMSs.  ...  Acknowledgments This work was supported (in part) by the National Science Foundation (SPX-1822933, XPS-1629444, AF-1910030), Google Research Grants, and the Alfred P.  ... 
doi:10.1109/grid.2010.5697970 dblp:conf/grid/ZhangS10 fatcat:ljaxif5kwfc3fo2nbcucd7dgty

The Design and Implementation of Modern Column-Oriented Database Systems

Daniel Abadi
2012 Foundations and Trends in Databases  
We describe their similarities and di erences and discuss their specific architectural features for compression, late materialization, join processing, vectorization and adaptive indexing (database cracking  ...  We specifically focus on three influential research prototypes, MonetDB [46], VectorWise [18] , and C-Store [88] .  ...  Each DSM column was stored inside a B-tree, where the leaf nodes contained all the column attribute values.  ... 
doi:10.1561/1900000024 fatcat:273xl3xkq5hqldkpqzdr636rsa
« Previous Showing results 1 — 15 out of 41 results