公开(公告)号：US09411623B1

公开(公告)日：2016-08-09

申请号：US13849249

申请日：2013-03-22

Applicant: VMware, Inc.

Inventor： Nicholas Michael Ryan ,  Krishna Yadappanavar ,  Prasanna Aithal ,  Sunil Satnur

IPC: G06F9/455

CPC classification number: G06F9/45558 ,  G06F2009/45579

Abstract: A method for coalescing IO requests includes maintaining a queue in a layer of an IO stack of a hypervisor, wherein (i) the queue holds IO requests received from an upper layer of the IO stack without forwarding the IO requests down the IO stack, and (ii) the layer of the IO stack resides above a file system layer of the IO stack. The method further includes receiving, at the layer, an IO request from the upper layer or a notification of a completion of certain IO requests previously transmitted by the layer down the IO stack. The method further includes determining whether any IO requests currently held in the queue should be transmitted down the IO stack based upon a condition; and combining any IO requests in the queue into at least one combined IO request to transmit down the IO stack if the condition is satisfied.

Abstract translation: 用于聚合IO请求的方法包括在管理程序的IO堆栈的层中维护队列，其中（i）队列保持从IO栈的上层接收到的IO请求，而不将IO请求转发到IO堆栈之下，以及 （ii）IO堆栈的层位于IO堆栈的文件系统层之上。 该方法还包括在层上接收来自上层的IO请求或者在先前由层叠在IO堆栈之前传输的某些IO请求的完成的通知。 该方法还包括基于条件确定当前保存在队列中的任何IO请求是否应当被向下传送到IO栈; 并且将队列中的任何IO请求组合成至少一个组合的IO请求以在满足条件的情况下向下传送IO堆栈。

公开(公告)号：US09239729B1

公开(公告)日：2016-01-19

申请号：US14477692

申请日：2014-09-04

Applicant: VMware, Inc.

Inventor： Nicholas Michael Ryan ,  Nishant Yadav

IPC: G06F9/46 ,  G06F9/455 ,  G06F9/445

CPC classification number: G06F9/45533 ,  G06F9/44526 ,  G06F9/45558 ,  G06F2009/45579 ,  G06F2009/45583

Abstract: Exemplary methods, apparatuses, and systems include receiving selection of a virtual disk and a plug-in. The virtual disk includes an extent file storing data used by a virtual machine and a descriptor file including a reference to the extent file and used by a virtualization stack of a host computer to manage the virtual disk. The plug-in is attached to the virtual disk in response to the received selection. Attaching the plug-in includes adding an identification of the plug-in to the descriptor file. The plug-in is notified of the attachment to the virtual disk. A request is received from the plug-in to create a sidecar file to store data or metadata on behalf of the plug-in. The sidecar file is created for the attached plug-in. The sidecar file is attached to the virtual disk.

Abstract translation: 示例性的方法，装置和系统包括接收虚拟盘和插件的选择。 虚拟磁盘包括存储由虚拟机使用的数据的扩展文件和包括对扩展文件的引用并由主计算机的虚拟化堆栈使用的描述符文件来管理虚拟磁盘。 响应于接收到的选择，该插件附加到虚拟磁盘。 附加插件包括将插件的标识添加到描述符文件中。 该插件被通知到虚拟磁盘的附件。 从插件接收请求以创建用于代表插件来存储数据或元数据的侧面文件。 为附加的插件创建侧面文件。 侧面文件附加到虚拟磁盘。

公开(公告)号：US09563785B2

公开(公告)日：2017-02-07

申请号：US14558917

申请日：2014-12-03

Applicant: VMware, Inc.

Inventor： Nicholas Michael Ryan

IPC: G06F21/62 ,  G06F21/78 ,  G06F17/00 ,  H04L9/00

CPC classification number: G06F21/6218 ,  G06F17/00 ,  G06F21/78 ,  G06F2221/2107 ,  H04L9/00

Abstract: Read data blocks are selectively decrypted and write data bocks are selectively encrypted in an input-output path between an application and a file system driver. If a read data block contains all zeroes, the read data block is not decrypted even though the read data block is a block of an encrypted file. Likewise, if a write data block contains all zeroes, the write data block is not encrypted even though the write data block is a block of an encrypted file. In this manner, the handling of zero blocks of an encrypted file is efficiently processed outside the file system without relying on bitmaps or other data structure maintained by the file system that may inform which blocks contain all zeroes.

Abstract translation: 选择性地解密读取数据块并且在应用程序和文件系统驱动程序之间的输入 - 输出路径中选择性地加密写入数据块。 如果读取的数据块包含全部零，即使读取的数据块是加密文件的块，读取的数据块也不被解密。 同样，如果写入数据块包含全部零，则即使写入数据块是加密文件的块，写入数据块也不会被加密。 以这种方式，加密文件的零块的处理在文件系统之外被有效地处理，而不依赖于由文件系统维护的位图或其他数据结构，可以通知哪些块包含所有零。