SIGMOD 2017论文的摘要与看法

最新推荐文章于 2024-06-23 18:39:40 发布

Tiffany6639

最新推荐文章于 2024-06-23 18:39:40 发布

阅读量3.7k

点赞数

分类专栏： paper 文章标签： sigmod

本文链接：https://blog.csdn.net/chunjing6629/article/details/80780843

版权

SIGMOD 2017论文聚焦数据库并发控制，如ACIDRain和Cicada，以及存储与分布式系统，如Azure Data Lake Store和OctopusFS。此外，还探讨了数据流处理、版本维护、并行与分布式查询、树与图处理、新硬件、交互式数据探索和AQP等领域。文章强调了高效存储、并发事务处理、分布式文件系统和实时数据流分析的最新进展。

摘要由CSDN通过智能技术生成

SIGMOD2017

持续更新

3.1 Concurrency并发

ACIDRain: Concurrency-Related Attacks on Database-Backed Web Applications
ACIDRain：对数据库支持的Web应用程序的并发性攻击

Cicada: Dependably Fast Multi-Core In-Memory Transactions
Cicada:依赖于快速的多核内存事务

BatchDB: Efficient Isolated Execution of Hybrid OLTP+OLAP Workloads for Interactive Applications
BatchDB:用于交互式应用程序的混合OLTP+OLAP工作负载的高效隔离执行

Transaction Repair for Multi-Version Concurrency Control
多版本并发控制的事务修复

Concerto: A High Concurrency Key-Value Store with Integrity
Concerto:具有完整性的高并发键值存储

Fast Failure Recovery for Main-Memory DBMSs on Multicores
多核心的主存DBMSs的快速故障恢复

Bringing Modular Concurrency Control to the Next Level
将模块化并发控制引入下一层

3.2 Storage and Distribution 存储与分布式

Azure Data Lake Store: A Hyperscale Distributed File Service for Big Data Analytics
Azure数据池存储:大型数据分析的超规模分布式文件服务

OctopusFS: A Distributed File System with Tiered Storage Management
octopus usfs:一个具有分层存储管理的分布式文件系统

Monkey: Optimal Navigable Key-Value Store
Monkey: 最佳的适合航行的、可驾驶的键值对存储
【单词】：
Navigable：adj. 可航行的；可驾驶的；适于航行的

Wide Table Layout Optimization based on Column Ordering and Duplication

Query Centric Partitioning and Allocation for Partially Replicated Database Systems

Spanner: Becoming a SQL System

3.3 Streams 数据流

Enabling Signal Processing over Data Streams
数组数据的增量视图维护

Complete Event Trend Detection in High-Rate Event Streams
在高速率事件流中的完成事件趋势检测

LittleTable: A Time-Series Database and Its Uses
LittleTable:一个时间序列数据库及其用途

3.4 Versions and Incremental Maintenance 版本和增量维护

Incremental View Maintenance over Array Data
数组数据的增量视图维护

Incremental Graph Computations: Doable and Undoable 增量图计算:可操作和不可操作

DEX: Query Execution in a Delta-based Storage System
DEX:基于delta的存储系统中的查询执行

3.5 Parallel and Distributed Query Processing

Massively Parallel Processing of Whole Genome Sequence Data: An In-Depth Performance Study 全基因组序列数据的大规模并行处理:一项深入的性能研究

Distributed Provenance Compression
分布式来源压缩

Abstract
Network provenance, which records the execution history of network events as meta-data, is becoming increasingly important for network accountability and failure diagnosis. For example, network provenance may be used to trace the path that a message traversed in a network, or to reveal how a particular routing entry was derived and the parties involved in its derivation. A challenge when storing the provenance of a live network is that the large number of arriving messages may incur substantial storage overhead. In this paper, we explore techniques to dynamically compress distributed provenance stored at scale. Logically, compression is achieved by grouping equivalent provenance trees and maintaining only one concrete copy for each equivalence class. To efficiently identify the equivalent provenance, we (1) introduce distributed event-based linear programs (DELPs) to specify distributed network applications, and (2) statically analyze DELPs to allow for quick detection of provenance equivalence at runtime. Our experimental results demonstrate that our approach leads to significant storage reduction and query latency improvement over alternative approaches.

摘要：
网络起源作为元数据记录网络事件的执行历史，对网络可靠性和故障诊断越来越重要。例如，可以使用网络起源跟踪消息在网络中遍历的路径，或者揭示特定的路由条目是如何派生的，以及与之相关的各方。存储实时网络起源时的一个挑战是，大量到达的消息可能导致大量的存储开销。本文探讨了动态压缩规模化存储的分布式种源的技术。从逻辑上讲，压缩是通过对等价种源树进行分组，并为每个等价类维护一个具体副本来实现的。为了有效地识别等价种源，我们(1)引入了基于事件的分布式线性程序(DELPs)来指定分布式网络应用程序，(2)静态分析DELPs，以便在运行时快速检测种源等价性。我们的实验结果表明，与其他方法相比，我们的方法可以显著减少存储和查询延迟。

ROBUS: Fair Cache Allocation for Data-parallel Workloads ROBUS:数据并行工作负载的公平缓存分配

Heterogeneity-aware Distributed Parameter Servers 了解异质性的分布参数服务器

Distributed Algorithms on Exact Personalized PageRank 分布式算法的精确个性化PageRank

Parallelizing Sequential Graph Computations (Best paper award)
并行序列图计算