Filters








8,820 Hits in 8.1 sec

PebblesDB

Pandian Raju, Rohan Kadekodi, Vijay Chidambaram, Ittai Abraham
2017 Proceedings of the 26th Symposium on Operating Systems Principles - SOSP '17  
We build PebblesDB, a highperformance key-value store, by modifying HyperLevelDB to use the FLSM data structure.  ...  The write amplification problem is due to the Log-Structured Merge Trees data structure that underlies these key-value stores.  ...  The get(key) operation returns the latest value associated with key. Put. The put(key, value) operation stores the mapping from key to value in the store.  ... 
doi:10.1145/3132747.3132765 dblp:conf/sosp/RajuKCA17 fatcat:notn676lmzcxhf5e2tziipcc3m

Scaling concurrent log-structured data stores

Guy Golan-Gueta, Edward Bortnikov, Eshcar Hillel, Idit Keidar
2015 Proceedings of the Tenth European Conference on Computer Systems - EuroSys '15  
Log-structured data stores (LSM-DSs) are widely accepted as the state-of-the-art implementation of key-value stores.  ...  They replace random disk writes with sequential I/O, by accumulating large batches of updates in an in-memory data structure and merging it with the on-disk store in the background.  ...  Updating an item is cast into putting an existing key with a new value, and deleting one is performed by putting a deletion marker, ⊥, as the key's value.  ... 
doi:10.1145/2741948.2741973 dblp:conf/eurosys/Golan-GuetaBHK15 fatcat:grq5uvi6krbvzfgosrquf7ogdy

Reducing the Storage Overhead of Main-Memory OLTP Databases with Hybrid Indexes

Huanchen Zhang, David G. Andersen, Andrew Pavlo, Michael Kaminsky, Lin Ma, Rui Shen
2016 Proceedings of the 2016 International Conference on Management of Data - SIGMOD '16  
Our first contribution is hybrid index, a dual-stage index architecture that achieves both space efficiency and high performance.  ...  An interesting finding is that although the random and mono-inc integer key data sets are the same size, the B+tree and Skip List use more space to store the mono-inc integer keys.  ...  For example, to map multiple values to a single key (for secondary indexes), dynamic data structures often store the same key multiple times with different values.  ... 
doi:10.1145/2882903.2915222 dblp:conf/sigmod/ZhangAPKMS16 fatcat:rh4qexnquvfolddctr3fqory44

Authenticated Key-Value Stores with Hardware Enclaves [article]

Yuzhe Tang, Ju Chen, Kai Li, Jianliang Xu, Qi Zhang
2019 arXiv   pre-print
In this paper, we address this issue and propose a novel authenticated log-structured merge tree (eLSM) based key-value store by leveraging Intel SGX enclaves.  ...  These modern applications increasingly feature update-intensive workloads, whereas existing authenticated data structures (ADSs) designed with in-place updates are inefficient to handle such workloads.  ...  It builds an authenticated LSM tree with small query proofs at selective tree levels.  ... 
arXiv:1904.12068v3 fatcat:u6btos552zhoromcoyhvtm2nmy

Overlay Indexes: Efficiently Supporting Aggregate Range Queries and Authenticated Data Structures in Off-the-Shelf Databases

Diego Pennino, Maurizio Pizzonia, Alessio Papi.
2019 IEEE Access  
We show a data structure, that we call DB-tree, that realizes an overlay index to support a wide range of custom aggregate range queries as well as ADSes, efficiently.  ...  We experimentally evaluate the efficiency of DB-trees showing that our approach is effective, especially if data updates are limited.  ...  Input: A regular data table D with columns x, y and v, an associated DB-tree T on all keys (x, y) with associated values v, and two values y and y (with y < y ).  ... 
doi:10.1109/access.2019.2957346 fatcat:meoy3ujcqvcbdcfd7fewchagsu

Enabling Efficient Updates in KV Storage via Hashing: Design and Performance Evaluation [article]

Yongkun Li, Helen H. W. Chan, Patrick P. C. Lee, Yinlong Xu
2019 arXiv   pre-print
Persistent key-value (KV) stores mostly build on the Log-Structured Merge (LSM) tree for high write performance, yet the LSM-tree suffers from the inherently high I/O amplification.  ...  KV separation mitigates I/O amplification by storing only keys in the LSM-tree and values in separate storage.  ...  We vary one parameter in each test, and use the default values for other parameters. We report the update throughput in Phase P3 and the total write size.  ... 
arXiv:1811.10000v2 fatcat:fmdmbxmojfcr7eoqbydcu4afha

Efficient Data Management with a Flexible Address Space [article]

Chen Chen, Wenshao Zhong, Xingbo Wu
2021 arXiv   pre-print
Extensive evaluations show that a key-value store built on top of it can achieve high performance and efficiency with a simple implementation.  ...  With this mechanism, applications can manage sorted data in a linear address space with minimal complexity.  ...  We build FlexDB, a KV store that demonstrates how to implement efficient data management applications with a flexible address space.  ... 
arXiv:2011.01024v3 fatcat:i4yry6uydngtdognigz4ji62um

A case study in building layered DHT applications

Yatin Chawathe, Sriram Ramabhadran, Sylvia Ratnasamy, Anthony LaMarca, Scott Shenker, Joseph Hellerstein
2005 Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communications - SIGCOMM '05  
We evaluate whether it is feasible to use DHTs as an application-independent building block to implement a key component of Place Lab: its "mapping infrastructure."  ...  Recent research has shown that one can use Distributed Hash Tables (DHTs) to build scalable, robust and efficient applications.  ...  In addition, we implemented a put conditional(key, value, gen); the put succeeds only if the key has not been modified since the generation number gen.  ... 
doi:10.1145/1080091.1080104 dblp:conf/sigcomm/ChawatheRRLSH05 fatcat:og7c6y2qgjdq3gu7smu5tarfxa

A case study in building layered DHT applications

Yatin Chawathe, Sriram Ramabhadran, Sylvia Ratnasamy, Anthony LaMarca, Scott Shenker, Joseph Hellerstein
2005 Computer communication review  
We evaluate whether it is feasible to use DHTs as an application-independent building block to implement a key component of Place Lab: its "mapping infrastructure."  ...  Recent research has shown that one can use Distributed Hash Tables (DHTs) to build scalable, robust and efficient applications.  ...  In addition, we implemented a put conditional(key, value, gen); the put succeeds only if the key has not been modified since the generation number gen.  ... 
doi:10.1145/1090191.1080104 fatcat:pazywlohvrcyvk72hqfp3vltji

Dynamic Provable Data Possession

C. Chris Erway, Alptekin Küpçü, Charalampos Papamanthou, Roberto Tamassia
2015 ACM Transactions on Privacy and Security  
The client later asks the server to prove that the stored data has not been tampered with or deleted (without downloading the actual data).  ...  We present a definitional framework and efficient constructions for dynamic provable data possession (DPDP), which extends the PDP model to support provable updates to stored data.  ...  Each node v of the skip list stores the number of nodes at the bottom level that can be reached from v. We call this value the rank of v and denote it with r(v).  ... 
doi:10.1145/2699909 fatcat:ih3gjwgi5bcdjkeoiwgtzey2vi

An efficient design and implementation of LSM-tree based key-value store on open-channel SSD

Peng Wang, Guangyu Sun, Song Jiang, Jian Ouyang, Shiding Lin, Chen Zhang, Jason Cong
2014 Proceedings of the Ninth European Conference on Computer Systems - EuroSys '14  
Various key-value (KV) stores are widely employed for data management to support Internet services as they offer higher efficiency, scalability, and availability than relational database systems.  ...  To address this inadequacy, we propose LOCS, a system equipped with a customized SSD design, which exposes its internal flash channels to applications, to work with the LSM-tree-based KV store, specifically  ...  Related Work Key-Value Stores.  ... 
doi:10.1145/2592798.2592804 dblp:conf/eurosys/WangSJOLZC14 fatcat:3mdj526mjbas5hmd6avb76dgji

LB+Trees

Jihang Liu, Shimin Chen, Lujun Wang
2020 Proceedings of the VLDB Endowment  
Moreover, we study the benefits of LB + -Tree in two real-world systems: X-Engine, a commercial OLTP storage engine, and Memcached, an open source key-value store.  ...  Our micro-benchmark experiments on a real machine equipped with 3DXPoint memory shows that LB + -Tree achieves up to 1.12-2.92x speedups over state-of-the-art NVM optimized B + -Trees for insertions while  ...  To support the two systems, we modify LB + -Tree to store (8B key pointer, 8B value pointer) entries. We store the keys and values outside the index structure in NVM memory.  ... 
doi:10.14778/3384345.3384355 fatcat:pq5gbuoukjfdvpwzgy3dbhzuhu

Building an efficient key-value store in a flexible address space

Chen Chen, Wenshao Zhong, Xingbo Wu
2022 Proceedings of the Seventeenth European Conference on Computer Systems  
Extensive evaluations show that a keyvalue store built on top of it can achieve high performance and efficiency with a simple implementation.  ...  With these mechanisms, applications can manage sorted data in a linear address space with minimal complexity.  ...  Write (PUT) Each write experiment starts from an empty store. Each client thread inserts 25% (approximately 16 GB) of the dataset to the store following the key distribution.  ... 
doi:10.1145/3492321.3519555 fatcat:ftkg73h3fjhsvfpkvhar773ed4

Decentralized Network Bandwidth Prediction and Node Search

Sukhyun Song
2011 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum  
The algorithm embeds the bandwidth information as distance in an edgeweighted tree, without performing full n-to-n measurements. No central and fixed infrastructure is required.  ...  While the clustering problem is NP-complete in a general graph, our algorithm runs in polynomial time with the bandwidth data predicted in a tree metric space.  ...  Finally, a reduce task "reduces" each group of key-value pairs into a final output value. Many different data-intensive problems can be solved efficiently with this twophase computation.  ... 
doi:10.1109/ipdps.2011.369 dblp:conf/ipps/Song11 fatcat:rkgap37ny5htdgoj3eghpajrf4

FAWN

David G. Andersen, Jason Franklin, Michael Kaminsky, Amar Phanishayee, Lawrence Tan, Vijay Vasudevan
2009 Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles - SOSP '09  
Our evaluation demonstrates that FAWN clusters can handle roughly 350 key-value queries per Joule of energy-two orders of magnitude more than a disk-based system.  ...  FAWN couples low-power embedded CPUs to small amounts of local flash storage, and balances computation and I/O capabilities to enable efficient, massively parallel access to data.  ...  Jason Franklin is supported in part by an NSF Graduate Research Fellowship. Amar Phanishayee was supported by an IBM Fellowship.  ... 
doi:10.1145/1629575.1629577 dblp:conf/sosp/AndersenFKPTV09 fatcat:yn6b4trbiraarmc2vngkmd2dry
« Previous Showing results 1 — 15 out of 8,820 results