WOBTree:a write-optimized B+-tree for non-volatile memory

来源 :计算机科学前沿 | 被引量 : 0次 | 上传用户:shi893932393
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
The emergence of non-volatile memory (NVM) has introduced new opportunities for performance optimizations in existing storage systems.To better utilize its byte-addressability and near-DRAM performance,NVM can be attached on the memory bus and accessed via load/store memory instructions rather than the conventional block interface.In this scenario,a cache line (usually 64 bytes) becomes the data transfer unit be-tween volatile and non-volatile devices.However,the failure-atomicity of write on NVM is the memory bit width (usually 8 bytes).This mismatch between the data transfer unit and the atomicity unit may introduce write amplification and compro-mise data consistency of node-based data structures such as B+-trees.In this paper,we propose WOBTree,a Write-Optimized B+-Tree for NVM to address the mismatch problem without expensive logging.WOBTree minimizes the update granular-ity from a tree node to a much smaller subnode and carefully arranges the write operations in it to ensure crash consistency and reduce write amplification.Experimental results show that compared with previous persistent B+-tree solutions,WOB-Tree reduces the write amplification by up to 86× and im-proves write performance by up to 61× while maintaining sim-ilar search performance.
其他文献
需求响应(DR)作为电力需求侧管理(DRM)的重要措施,对提升电网安全、优化电力资源配置具有重要意义,目前已得到深化应用.为明确各类用户负荷特性和评估其参与DR的潜力,需要对电力用户进行分类.首先,综合考虑用户属性、用电时间规律等因素,建立基于集合经验模态分解(EEMD)和模糊C均值聚类(FCM)的需求响应用户负荷曲线分类模型.利用EEMD将某电网82组负荷数据分别分解为本征模态分量和趋势分量;然后,采用FCM对平稳的本征模态分量进行聚类.结果表明:EEMD-FCM模型在迭代12次后目标函数值稳定收敛于6
滚动轴承作为大多数旋转机械的重要零部件,其工作状态直接影响设备的工作寿命.针对传统故障诊断方法自适应性差、特征提取过于依赖人工经验的问题,提出一种基于双向门控循环单元的轴承故障诊断方法.该方法直接将原始振动信号作为模型输入,自动进行故障特征提取与故障诊断.结合轴承外圈故障、内圈故障及滚动体故障等9种故障状况,对所提方法进行了验证.实验结果表明,其故障诊断准确率可达99.56%,诊断效果优于门控循环单元、长短期记忆网络等算法,且泛化能力好.
针对直接空冷机组在变工况时被控对象发生改变造成背压跟踪设定值效果变差的情况,提出了一种基于GPC模糊增益调度的控制方式.首先,对机组背压影响因素进行分析,确定各典型工况下风机转速与背压的动态模型;然后,设计各个典型工况之间的模糊增益调度规则,确定工况变化后对应的隶属度函数;最后,将GPC广义预测控制与模糊增益调度控制相结合,设计出新型的GPC模糊增益调度控制.仿真结果表明,在变工况的情况下,GPC模糊增益调度控制与传统GPC相比具有更好的控制效果,对现场背压控制具有一定的指导作用.
盐雾环境下的污秽物具有较高的可溶盐含量,可造成绝缘子绝缘性能下降,进而危及电力系统的安全运行.以XWP2-160型瓷双伞绝缘子和FXBW-110/120-2型复合绝缘子为研究对象,基于场致荷电机理,利用多物理场耦合软件COMSOL对其积污特性进行数值模拟,探索了盐密ESDD的计算方法,并验证了其合理性.利用该方法研究了盐雾环境下风速、雾滴粒径、电压类型对瓷及复合绝缘子积污特性的影响,分析了污秽沿绝缘子伞裙的分布规律.结果表明:复合绝缘子的积污量大于同条件下瓷双伞绝缘子积污量,盐雾环境频发地区可优先考虑瓷双
Traditional first-order logic has four definitions for quantifiers,which are defined by universal and existential quan-tifiers.In L3-valued (three-valued) first-order logic,there are eight kinds of definitions for quantifiers;and corresponding Gentzen ded
本文针对组合浮囊型浮式防波堤结构,提出了三种不同组合的结构方案,并通过Flow-3D软件进行数值计算,对比分析了在中等水深的长周期波条件下的消浪性能.并得到以下结论:浮囊按矩形布置的组合型式比按三角形布置的组合型式消浪效果更好;无论是矩形布置还是三角形布置,双层浮囊排列的浮式防波堤在D/d>0.5或B/L>0.3的情况下均可以达到消减一半波能的目的;相比箱板式浮式防波堤,板阻式可以通过扰动底部水质点运动进一步提高浮式防波堤的消浪性能.同时,针对板阻式结构,由于下部浮囊在横断面方向不是整排布置,本文引入关于
In this paper,a binary-extensible quality status en-coding scheme,named IQSCT (IoT quality status code table),is proposed for the PCB-based product with available recovery options in remanufacturing.IQSCT is achieved by code evolu-tion based on binary log
A sememe is defined as the minimum semantic unit of languages in linguistics.Sememe knowledge bases are built by manually annotating sememes for words and phrases.HowNet is the most well-known sememe knowledge base.It has been extensively utilized in many
LNG船舶通航因特殊监管要求,具有一定排他性.前期研究表明基于目前一般通航规则,单个港址LNG泊位数量不宜超过4个,超过后,船舶通航效率较低、运营监管风险较高.本文采用多智能体泊位组联合运营仿真建模,采用控制变量法,定量评估了码头高负荷状态下不同LNG船舶监管条件和航行距离对LNG运输船舶通航效率的影响,以及采用一定优化通航组织方式对通航效率提升的效果.结果表明,LNG泊位数量4个、独立单向航道、LNG船舶航行监管距离在20海里左右时,系统运营效率相对的较高;进一步采取LNG船舶组队进出港或设置独立双向L
Multi-user collaborative editors are useful computer-aided tools to support human-to-human collabora-tion.For multi-user collaborative editors,selective undo is an essential utility enabling users to undo any editing operations at any time.Collaborative e