公开(公告)号：US09298733B1

公开(公告)日：2016-03-29

申请号：US13536289

申请日：2012-06-28

Applicant: Sorin Faibish ,  John M. Bent ,  Jeffrey M. Nick ,  Gary Grider ,  Aaron Torres

Inventor： Sorin Faibish ,  John M. Bent ,  Jeffrey M. Nick ,  Gary Grider ,  Aaron Torres

IPC: G06F17/30

CPC classification number: G06F17/302 ,  G06F17/30224

Abstract: Techniques are provided for storing files in a parallel computing system based on a user-specification. A plurality of files generated by a distributed application in a parallel computing system are stored by obtaining a specification from the distributed application indicating how the plurality of files should be stored; and storing one or more of the plurality of files in one or more storage nodes of a multi-tier storage system based on the specification. The plurality of files comprise a plurality of complete files and/or a plurality of sub-files. The specification can optionally be processed by a daemon executing on one or more nodes in a multi-tier storage system. The specification indicates how the plurality of files should be stored, for example, identifying one or more storage nodes where the plurality of files should be stored.

Abstract translation: 提供了基于用户规范在并行计算系统中存储文件的技术。 由并行计算系统中的分布式应用生成的多个文件通过从分布式应用获得指定如何存储多个文件的规范来存储; 以及基于所述规范，将所述多个文件中的一个或多个存储在多层存储系统的一个或多个存储节点中。 多个文件包括多个完整文件和/或多个子文件。 该规范可以可选地由在多层存储系统中的一个或多个节点上执行的守护进程来处理。 该规范指示如何存储多个文件，例如，识别应该存储多个文件的一个或多个存储节点。

公开(公告)号：US09087075B1

公开(公告)日：2015-07-21

申请号：US13536331

申请日：2012-06-28

Applicant: Sorin Faibish ,  John M. Bent ,  Percy Tzelnic ,  Zhenhua Zhang ,  Gary Grider

Inventor： Sorin Faibish ,  John M. Bent ,  Percy Tzelnic ,  Zhenhua Zhang ,  Gary Grider

IPC: G06F17/30

CPC classification number: G06F17/30212

Abstract: Improved techniques are provided for storing files in a parallel computing system using a list-based index to identify file replicas. A file and at least one replica of the file are stored in one or more storage nodes of the parallel computing system. An index for the file comprises at least one list comprising a pointer to a storage location of the file and a storage location of the at least one replica of the file. The file comprises one or more of a complete file and one or more sub-files. The index may also comprise a checksum value for one or more of the file and the replica(s) of the file. The checksum value can be evaluated to validate the file and/or the file replica(s). A query can be processed using the list.

Abstract translation: 提供了改进的技术，用于使用基于列表的索引来在并行计算系统中存储文件以识别文件副本。 文件和文件的至少一个副本存储在并行计算系统的一个或多个存储节点中。 文件的索引包括至少一个列表，其包括指向文件的存储位置的指针和该文件的至少一个副本的存储位置。 该文件包括完整文件和一个或多个子文件中的一个或多个。 索引还可以包括文件中的一个或多个文件和文件副本的校验和值。 可以评估校验和值以验证文件和/或文件副本。 可以使用列表处理查询。

公开(公告)号：US08719590B1

公开(公告)日：2014-05-06

申请号：US13525919

申请日：2012-06-18

Applicant: Sorin Faibish ,  Percy Tzelnic

Inventor： Sorin Faibish ,  Percy Tzelnic

IPC: G06F12/14

CPC classification number: H04L63/0428 ,  G06F21/10 ,  G06F21/602 ,  G06F2221/0748 ,  H04L9/085 ,  H04L9/0894 ,  H04L12/4641 ,  H04L67/10

Abstract: Cloud infrastructure of an information processing system comprises one or more processing devices implementing a plurality of virtual machines. The cloud infrastructure is configured to receive a processing job from a tenant, to obtain a first key specific to the tenant, to determine a second key utilizing information supplied by the tenant, and to encrypt one or more results of the processing job utilizing a combination of the first key and the second key. At least a portion of the second key is determined by at least one application that is run on at least one virtual machine of the cloud infrastructure in conjunction with performance of the processing job. The encrypted results of the processing job may be stored in a virtual memory of the cloud infrastructure and transmitted to the tenant.

Abstract translation: 信息处理系统的云基础设施包括实现多个虚拟机的一个或多个处理设备。 云基础架构被配置为从租户接收处理作业，以获得租户特有的第一密钥，以利用租户提供的信息来确定第二密钥，并且利用组合来加密处理作业的一个或多个结果 的第一个键和第二个键。 结合执行处理作业，由至少一个在云基础设施的一个虚拟机上运行的应用程序确定第二个密钥的至少一部分。 处理作业的加密结果可以存储在云基础设施的虚拟存储器中并被传送给租户。

公开(公告)号：US08555014B1

公开(公告)日：2013-10-08

申请号：US12005640

申请日：2007-12-27

Applicant: James M. Pedone, Jr. ,  Sorin Faibish ,  Xiaoye Jiang ,  Per Brashers ,  Jason R. Glasgow

Inventor： James M. Pedone, Jr. ,  Sorin Faibish ,  Xiaoye Jiang ,  Per Brashers ,  Jason R. Glasgow

IPC: G06F12/00

CPC classification number: G06F9/468 ,  G06F3/0611 ,  G06F3/0622 ,  G06F3/0659 ,  G06F3/067

Abstract: Embodiments of the present invention provide a method of managing access of multiple client computers to a storage system that supports a limited number of logins. The method comprises, in response to a request to enable a subset of the clients to access resources of the storage system to perform a task, automatically configuring the storage system to provide the subset of the clients access to the resources, and, when the task is completed, automatically re-configuring the storage system so that the subset of the clients is no longer provided with access to the resources of the storage system.

Abstract translation: 本发明的实施例提供了一种管理多个客户端计算机到支持有限数量登录的存储系统的访问的方法。 该方法包括响应于使得客户端子集能够访问存储系统的资源以执行任务的请求，自动地配置存储系统以提供客户端子集对资源的访问，以及当任务 完成后，自动重新配置存储系统，以便客户端的子集不再被提供给存储系统资源的访问。

公开(公告)号：US08402226B1

公开(公告)日：2013-03-19

申请号：US12818577

申请日：2010-06-18

Applicant: Sorin Faibish ,  John Forecast ,  Peter Bixby ,  Philippe Armangau ,  Sitaram Pawar

Inventor： Sorin Faibish ,  John Forecast ,  Peter Bixby ,  Philippe Armangau ,  Sitaram Pawar

IPC: G06F13/00 ,  G06F13/28

CPC classification number: G06F12/0804 ,  G06F12/0868

Abstract: Based on a count of the number of dirty pages in a cache memory, the dirty pages are written from the cache memory to a storage array at a rate having a component proportional to the rate of change in the number of dirty pages in the cache memory. For example, a desired flush rate is computed by adding a first term to a second term. The first term is proportional to the rate of change in the number of dirty pages in the cache memory, and the second term is proportional to the number of dirty pages in the cache memory. The rate component has a smoothing effect on incoming I/O bursts and permits cache flushing to occur at a higher rate closer to the maximum storage array throughput without a significant detrimental impact on client application performance.

Abstract translation: 基于高速缓冲存储器中脏页数的计数，脏页以高速缓冲存储器中的脏页数的变化率成比例的速率从高速缓冲存储器写入存储阵列 。 例如，通过将第一项添加到第二项来计算所需的刷新速率。 第一项与高速缓冲存储器中脏页数的变化率成比例，第二项与高速缓冲存储器中的脏页数成比例。 速率组件对传入的I / O突发具有平滑效果，并允许高速缓存刷新以更高的速率发生，更接近最大存储阵列吞吐量，而不会对客户端应用程序性能造成重大的不利影响。

公开(公告)号：US08166005B2

公开(公告)日：2012-04-24

申请号：US10945653

申请日：2004-09-21

Applicant: Peter C. Bixby ,  Xiaoye Jiang ,  Uday K. Gupta ,  Sorin Faibish

Inventor： Peter C. Bixby ,  Xiaoye Jiang ,  Uday K. Gupta ,  Sorin Faibish

IPC: G06F7/00 ,  G06F11/00

CPC classification number: G06F17/30067 ,  Y10S707/966

Abstract: Servers in a storage system store a nested multilayer directory structure, and a global index that is an abstract of the directory structure. The global index identifies respective portions of the directory structure that are stored in respective ones of the servers, and the global index identifies paths through the directory structure linking the respective portions. Upon performing a top-down search of the directory structure in response to a client request and finding that a portion of it is offline, the global index is searched to discover portions of the directory structure that are located below the offline portion. The global index may also identify the respective server storing each of the respective portions of the directory structure, and may indicate whether or not each of the respective portions of the directory structure is known to be offline.

Abstract translation: 存储系统中的服务器存储嵌套的多层目录结构，以及作为目录结构的抽象的全局索引。 全局索引标识存储在相应服务器中的目录结构的各个部分，并且全局索引通过链接相应部分的目录结构来标识路径。 在响应于客户机请求并发现其一部分脱机时对目录结构进行自顶向下搜索时，搜索全局索引以发现位于离线部分下方的目录结构的部分。 全局索引还可以标识存储目录结构的各个部分的相应服务器，并且可以指示目录结构的各个部分中的每一个是否已知脱机。

公开(公告)号：US07962657B1

公开(公告)日：2011-06-14

申请号：US11966615

申请日：2007-12-28

Applicant: Eyal Zimran ,  Sorin Faibish ,  Jason Glasgow

Inventor： Eyal Zimran ,  Sorin Faibish ,  Jason Glasgow

IPC: G06F15/16

CPC classification number: G06F3/061 ,  G06F3/0635 ,  G06F3/067

Abstract: Embodiments of the present invention are directed to techniques for selecting a data path over which to exchange information between a client device and a storage system by making a selection between a file system server (NAS) data path type (a first data path type) and a direct (SAN) data path type (a second data path type) based on one or more adjustable path selection factors and/or information regarding components of the computer system. For example, a data path may be selected based on a type of an input/output operation to be executed (i.e., whether the operation is a read operation or write operation) and/or any other suitable path selection factor.

Abstract translation: 本发明的实施例涉及用于通过在文件系统服务器（NAS）数据路径类型（第一数据路径类型）和第二数据路径类型之间进行选择来选择在客户端设备和存储系统之间交换信息的数据路径的技术 基于一个或多个可调节路径选择因素的直接（SAN）数据路径类型（第二数据路径类型）和/或关于计算机系统的组件的信息。 例如，可以基于要执行的输入/输出操作的类型（即，操作是读操作还是写操作）和/或任何其他合适的路径选择因素来选择数据路径。

公开(公告)号：US07865485B2

公开(公告)日：2011-01-04

申请号：US10668467

申请日：2003-09-23

Applicant: Sachin Mullick ,  Jiannan Zheng ,  Xiaoye Jiang ,  Sorin Faibish ,  Peter Bixby

Inventor： Sachin Mullick ,  Jiannan Zheng ,  Xiaoye Jiang ,  Sorin Faibish ,  Peter Bixby

IPC: G06F7/00 ,  G06F17/00 ,  G06F12/00 ,  G06F17/30

CPC classification number: G06F17/30171 ,  G06F11/1466 ,  G06F2201/84

Abstract: A write interface in a file server provides permission management for concurrent access to data blocks of a file, ensures correct use and update of indirect blocks in a tree of the file, preallocates file blocks when the file is extended, solves access conflicts for concurrent reads and writes to the same block, and permits the use of pipelined processors. For example, a write operation includes obtaining a per file allocation mutex (mutually exclusive lock), preallocating a metadata block, releasing the allocation mutex, issuing an asynchronous write request for writing to the file, waiting for the asynchronous write request to complete, obtaining the allocation mutex, committing the preallocated metadata block, and releasing the allocation mutex. Since no locks are held during the writing of data to the on-disk storage and this data write takes the majority of the time, the method enhances concurrency while maintaining data integrity.

Abstract translation: 文件服务器中的写接口提供对并发访问文件数据块的权限管理，确保文件树中间接块的正确使用和更新，扩展文件时预分配文件块，解决并发读取的访问冲突 并写入同一个块，并允许使用流水线处理器。 例如，写入操作包括获得每个文件分配互斥（互斥锁），预先分配元数据块，释放分配互斥体，发出用于写入文件的异步写入请求，等待异步写入请求完成，获得 分配互斥体，提交预先分配的元数据块，以及释放分配互斥体。 由于在将数据写入磁盘存储器期间没有锁定，并且此数据写入占用大部分时间，因此该方法在保持数据完整性的同时增强了并发性。

公开(公告)号：US07676587B2

公开(公告)日：2010-03-09

申请号：US11011345

申请日：2004-12-14

Applicant: Sorin Faibish ,  Xiaoye Jiang ,  Dennis Ting ,  Yehoshoua Sasson ,  Arthur O. Harris

Inventor： Sorin Faibish ,  Xiaoye Jiang ,  Dennis Ting ,  Yehoshoua Sasson ,  Arthur O. Harris

IPC: G06F15/13

CPC classification number: H04L29/12009 ,  H04L29/12018 ,  H04L61/10 ,  H04L67/1002 ,  H04L67/1097 ,  H04L69/324

Abstract: Network servers in a cluster share the same network protocol address for incoming client requests, and in a data link layer protocol a reply of a client to a request from a server is returned to this same server. For example: (1) ports of the servers are clustered into one single network channel used for incoming and outgoing requests to and from the servers; or (2) ports of the servers are clustered into one single network channel used for incoming requests to the servers and a separate port of each of the servers is used for outgoing requests from each of the servers; or (3) logical ports of the servers are clustered into one network channel used for requests to the servers and a separate logical port of each of the servers is used for outgoing requests from each of the servers.

Abstract translation: 集群中的网络服务器为传入的客户端请求共享相同的网络协议地址，而在数据链路层协议中，客户端对服务器的请求的回复将返回到同一个服务器。 例如：（1）服务器的端口被聚集成一个单一的网络信道，用于进出服务器的传入和传出请求; 或（2）服务器的端口被集群到用于到服务器的传入请求的单个网络信道中，并且每个服务器的单独端口用于来自每个服务器的传出请求; 或（3）服务器的逻辑端口被集群到用于对服务器的请求的一个网络信道中，并且每个服务器的单独的逻辑端口用于来自每个服务器的传出请求。

公开(公告)号：US07653612B1

公开(公告)日：2010-01-26

申请号：US11692881

申请日：2007-03-28

Applicant: Sairam Veeraswamy ,  Sorin Faibish

Inventor： Sairam Veeraswamy ,  Sorin Faibish

IPC: G06F17/30

CPC classification number: G06F17/30171 ,  Y10S707/99931

Abstract: A shallow file is adapted for intensive read-only access to data of a primary file. The primary file resides in another file system or file server. The shallow file includes the data block mapping metadata of the primary file and a link to the primary file. To open the shallow file, the file system manager of the shallow file obtains a read lock on the primary file from the file system manager of the primary file. Then the file system manager of the shallow file may use the data block mapping in the shallow file to access the file data from the primary file in storage without participation of the file system manager of the primary file. This permits offloading of data protection services for secure and efficient storage of a backup copy of the file data.

Abstract translation: 浅文件适用于对主文件的数据进行强读取访问。 主文件位于另一个文件系统或文件服务器中。 浅文件包括数据块映射主文件的元数据和到主文件的链接。 要打开浅文件，浅文件的文件系统管理器从主文件的文件系统管理器获取主文件上的读锁定。 然后浅文件的文件系统管理器可以使用浅文件中的数据块映射来访问存储中的主文件的文件数据，而不需要主文件的文件系统管理器的参与。 这允许卸载数据保护服务，以安全和高效地存储文件数据的备份副本。