专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09286261B1 Architecture and method for a burst buffer using flash technology 有权
标题翻译：使用闪存技术的突发缓冲区的架构和方法
公开(公告)号：US09286261B1
公开(公告)日：2016-03-15
申请号：US13676000
申请日：2012-11-13
申请人： EMC Corporation , Los Alamos National Security, LLC
发明人： Percy Tzelnic , Sorin Faibish , Uday K. Gupta , John Bent , Gary Alan Grider , Hsing-bung Chen
IPC分类号： G06F15/167
CPC分类号： G06F15/167 , G06F11/108 , G06F17/30218 , G06F2211/1028
摘要： A parallel supercomputing cluster includes compute nodes interconnected in a mesh of data links for executing an MPI job, and solid-state storage nodes each linked to a respective group of the compute nodes for receiving checkpoint data from the respective compute nodes, and magnetic disk storage linked to each of the solid-state storage nodes for asynchronous migration of the checkpoint data from the solid-state storage nodes to the magnetic disk storage. Each solid-state storage node presents a file system interface to the MPI job, and multiple MPI processes of the MPI job write the checkpoint data to a shared file in the solid-state storage in a strided fashion, and the solid-state storage node asynchronously migrates the checkpoint data from the shared file in the solid-state storage to the magnetic disk storage and writes the checkpoint data to the magnetic disk storage in a sequential fashion.
摘要翻译：并行超级计算集群包括互连在用于执行MPI作业的数据链路的网格中的计算节点，以及每个链接到相应的计算节点组的固态存储节点，用于从相应的计算节点接收检查点数据，以及磁盘存储链接到每个固态存储节点，用于将检查点数据从固态存储节点异步迁移到磁盘存储器。每个固态存储节点向MPI作业呈现文件系统接口，并且MPI作业的多个MPI处理以支路方式将检查点数据写入固态存储器中的共享文件，而固态存储节点将检查点数据从固态存储器中的共享文件异步地迁移到磁盘存储器，并将检查点数据以顺序的方式写入磁盘存储器。

2. 发明授权

US09158540B1 Method and apparatus for offloading compute resources to a flash co-processing appliance 有权
标题翻译：将计算资源卸载到闪存协处理设备的方法和装置
公开(公告)号：US09158540B1
公开(公告)日：2015-10-13
申请号：US13676019
申请日：2012-11-13
申请人： EMC Corporation , Los Alamos National Security, LLC
发明人： Percy Tzelnic , Sorin Faibish , Uday K. Gupta , John Bent , Gary Alan Grider , Hsing-bung Chen
IPC分类号： G06F7/38 , G06F11/00 , G06F9/30
CPC分类号： G06F11/108 , G06F11/1438 , G06F2211/1028
摘要： Solid-State Drive (SSD) burst buffer nodes are interposed into a parallel supercomputing cluster to enable fast burst checkpoint of cluster memory to or from nearby interconnected solid-state storage with asynchronous migration between the burst buffer nodes and slower more distant disk storage. The SSD nodes also perform tasks offloaded from the compute nodes or associated with the checkpoint data. For example, the data for the next job is preloaded in the SSD node and very fast uploaded to the respective compute node just before the next job starts. During a job, the SSD nodes perform fast visualization and statistical analysis upon the checkpoint data. The SSD nodes can also perform data reduction and encryption of the checkpoint data.
摘要翻译：固态驱动器（SSD）突发缓冲器节点被插入到并行超级计算集群中，以使得能够在突发缓冲器节点与较慢的更远的磁盘存储之间进行异步迁移，从而使集群存储器能够或从附近的互连固态存储器的快速突发检查点。 SSD节点还执行从计算节点卸载或与检查点数据相关联的任务。例如，下一个作业的数据预先加载到SSD节点，并且在下一个作业开始之前非常快速地上传到相应的计算节点。在作业中，SSD节点可以对检查点数据进行快速可视化和统计分析。 SSD节点还可以执行检查点数据的数据缩减和加密。

3. 发明授权

US08769198B1 System and method for out-of-band cache coherency 有权
标题翻译：带外高速缓存一致性的系统和方法
公开(公告)号：US08769198B1
公开(公告)日：2014-07-01
申请号：US14015583
申请日：2013-08-30
申请人： EMC Corporation
发明人： Roy E. Clark , Humberto Rodriguez , Kiran P. Madnani , ChiiShing Lin , David L. Black , Uday K. Gupta
IPC分类号： G06F12/00 , G06F12/08 , G06F3/06
CPC分类号： G06F12/0815 , G06F12/0866 , G06F12/0868 , G06F2212/1028 , G06F2212/1056 , G06F2212/263 , Y02D10/13
摘要： A method and computer program product for receiving a data read request on a first array for requested data stored on a multi-array storage network that includes the first array and at least a second array. The data read request is processed to determine if the requested data is resident on the first array. If the requested data is resident on the first array, the requested data is obtained from a storage device included within the first array. If the requested data is not resident on the first array, the requested data is obtained from a storage device included within the at least a second array via an out-of-band cache control process.
摘要翻译：一种方法和计算机程序产品，用于在第一阵列上接收存储在包括第一阵列和至少第二阵列的多阵列存储网络上的请求数据的数据读取请求。处理数据读取请求以确定所请求的数据是否驻留在第一个数组上。如果请求的数据驻留在第一阵列上，则从包括在第一阵列内的存储装置获得所请求的数据。如果请求的数据不驻留在第一阵列上，则通过带外高速缓存控制处理从包括在至少第二阵列中的存储设备获得所请求的数据。

4. 发明授权

US09081691B1 Techniques for caching data using a volatile memory cache and solid state drive 有权
标题翻译：使用易失性存储器缓存和固态驱动器缓存数据的技术
公开(公告)号：US09081691B1
公开(公告)日：2015-07-14
申请号：US13624098
申请日：2012-09-21
申请人： EMC Corporation
发明人： Uday K. Gupta , Charles H. Hopkins , Michael B. Evans
IPC分类号： G06F12/16 , G06F12/08 , G06F11/14 , G06F12/02
CPC分类号： G06F12/0891 , G06F11/1441 , G06F12/0246 , G06F12/0804 , G06F12/0815 , G06F12/0866 , G06F2212/214 , G06F2212/7202 , G06F2212/7204
摘要： Described are techniques for performing recovery processing in a data storage system. A providing a flash-based memory is provided with includes cached write data that has not been destaged to a data storage device. It is determined whether said flash-based memory has a threshold amount of storage available thereon. If the flash-based memory does not have the threshold amount of storage available thereon, portions of the cache write data are destaged until said flash-based memory has a threshold amount of storage available thereon. Received data requests are processed in accordance with a first policy different from a second policy used in connection with processing received data requests if said flash-based memory has a threshold amount of storage available thereon.
摘要翻译：描述了在数据存储系统中执行恢复处理的技术。提供了一种提供基于闪存的存储器，其中包括尚未迁移到数据存储设备的高速缓存的写入数据。确定所述基于闪存的存储器是否具有可用的阈值存储量。如果基于闪存的存储器不具有在其上可用的阈值量的存储器，则高速缓存写入数据的部分将被停止，直到所述基于闪存的存储器具有在其上可用的阈值存储量。如果所述基于闪存的存储器具有可用的阈值存储量，则根据与结合处理接收到的数据请求而使用的第二策略不同的第一策略来处理接收到的数据请求。

5. 发明授权

US09652568B1 Method, apparatus, and computer program product for design and selection of an I/O subsystem of a supercomputer 有权
公开(公告)号：US09652568B1
公开(公告)日：2017-05-16
申请号：US13675965
申请日：2012-11-13
申请人： EMC Corporation
发明人： Percy Tzelnic , Sorin Faibish , Uday K. Gupta , John Bent
IPC分类号： G06F13/10 , G06F17/50 , G06F15/177
CPC分类号： G06F17/5022 , G06F15/177 , G06F17/30 , G06F2217/02
摘要： For simulating a parallel supercomputing cluster, a simulation program includes a model of the system of compute nodes and a model of an I/O subsystem that stores checkpoints from the compute nodes. When executed, instructions in the simulation program perform the steps of receiving input parameters defining the compute nodes and the I/O subsystem, computing a total number of computational flops for a time between checkpoints and an amount of disk storage required to store the checkpoint data for different configurations of the parallel supercomputing cluster, and presenting a summary to a user of the computed number of computational flops for a time between checkpoints and an amount of disk storage required to store the checkpoint data for the different configurations of the parallel supercomputing cluster.

6. 发明授权

US09110820B1 Hybrid data storage system in an HPC exascale environment 有权
标题翻译：混合数据存储系统在HPC exascale环境中
公开(公告)号：US09110820B1
公开(公告)日：2015-08-18
申请号：US14230804
申请日：2014-03-31
申请人： EMC Corporation
发明人： John M. Bent , Sorin Faibish , Uday K. Gupta , Percy Tzelnic , Dennis P. J. Ting
IPC分类号： G06F13/38 , G06F13/10 , G06F3/00
CPC分类号： G06F13/10 , G06F3/061 , G06F3/0656 , G06F3/0689
摘要： A computer-executable method, system, and computer program product for managing I/O requests from a compute node in communication with a data storage system, including a first burst buffer node and a second burst buffer node, the computer-executable method, system, and computer program product comprising striping data on the first burst buffer node and the second burst buffer node, wherein a first portion of the data is communicated to the first burst buffer node and a second portion of the data is communicated to the second burst buffer node, processing the first portion of the data at the first burst buffer node, and processing the second portion of the data at the second burst buffer node.
摘要翻译：一种用于管理与数据存储系统通信的计算节点的I / O请求的计算机可执行方法，系统和计算机程序产品，所述数据存储系统包括第一突发缓冲器节点和第二突发缓冲器节点，所述计算机可执行方法系统以及包括在第一突发缓冲器节点和第二突发缓冲器节点上分条数据的计算机程序产品，其中数据的第一部分被传送到第一突发缓冲器节点，并且数据的第二部分被传送到第二突发缓冲器节点，处理第一突发缓冲器节点处的数据的第一部分，以及处理第二突发缓冲器节点处的数据的第二部分。

7. 发明授权

US10628391B1 Method and system for reducing metadata overhead in a two-tier storage architecture 有权
公开(公告)号：US10628391B1
公开(公告)日：2020-04-21
申请号：US14870968
申请日：2015-09-30
申请人： EMC Corporation
发明人： John M. Bent , Sorin Faibish , Dennis Pei Jean Ting , Uday K. Gupta , Percy Tzelnic , Gary Grider , David J. Bonnie
IPC分类号： G06F16/16 , G06F16/185 , G06F16/14 , G06F16/22
CPC分类号： G06F16/185 , G06F16/148 , G06F16/166 , G06F16/2246
摘要： Example embodiments of the present invention relate to a method, a system, and a computer program product for maintaining dynamically loadable namespaces. The method includes presenting, to an application, a file system having a global single namespace (SN) comprising a plurality of dynamically-loadable namespaces (DLNs) maintained in a capacity tier (CT) of object storage of a storage system. In response to a job submitted by the application, dynamically loading a first dynamically-loadable namespace, including the metadata only for the first dynamically-loadable namespace, associated with the job from the capacity tier of object storage into a fast tier (FT) of storage of the storage system.

8. 发明授权

US09779108B1 Lustre file system 有权
公开(公告)号：US09779108B1
公开(公告)日：2017-10-03
申请号：US13931212
申请日：2013-06-28
申请人： EMC Corporation
发明人： Sorin Faibish , Tao Peng , John M. Bent , Uday K. Gupta , James M. Pedone, Jr.
IPC分类号： G06F17/30
CPC分类号： G06F17/30224
摘要： A computer-executable method, system, and computer program product of managing I/O received within a Lustre file system, the computer-executable method, system, and computer program product comprising: receiving a data I/O request, wherein the data I/O request relates to data stored within the Lustre file system; processing the data I/O request in a journal stored on a fast data storage device within the Lustre file system; analyzing the journal to make a determination related to the data I/O request; and responding to the data I/O request.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式