公开(公告)号：US20150106343A1

公开(公告)日：2015-04-16

申请号：US14054984

申请日：2013-10-16

Applicant: NetApp, Inc.

Inventor： Kiran Nenmeli Srinivasan ,  Kishore Kasi Udayashankar ,  Swetha Krishnan

IPC: G06F17/30

CPC classification number: G06F17/30371 ,  G06F3/0608 ,  G06F3/0641 ,  G06F3/067 ,  G06F17/30321 ,  G06F17/30516

Abstract: A system and method for global data de-duplication in a cloud storage environment utilizing a plurality of data centers is provided. Each cloud storage gateway appliance divides a data stream into a plurality of data objects and generates a content-based hash value as a key for each data object. An IMMUTABLE PUT operation is utilized to store the data object at the associated key within the cloud.

Abstract translation: 提供了一种利用多个数据中心的云存储环境中的全局重复数据删除系统和方法。 每个云存储网关设备将数据流划分成多个数据对象，并且生成基于内容的散列值作为每个数据对象的密钥。 使用IMMUTABLE PUT操作来将数据对象存储在云内的关联密钥处。

公开(公告)号：US20150032967A1

公开(公告)日：2015-01-29

申请号：US13951662

申请日：2013-07-26

Applicant: NetApp, Inc.

Inventor： Kishore Kasi Udayashankar ,  Swetha Krishnan ,  Kiran Srinivasan

IPC: G06F12/08

CPC classification number: G06F12/0862 ,  G06F2212/6024 ,  G06F2212/6026

Abstract: Systems and methods which provide for improved prefetching schemes for caching data in a storage network are described. In one embodiment, a dynamically adaptive prefetching mechanism based on block access history information and prior effectiveness of prefetching is provided. Embodiments may take into account prefetch efficiency; a dynamic value indicating the usefulness of past prefetches, prefetch wastage, in conjunction with prefetch resources available at any point in time, to determine the number of blocks to read-ahead during a prefetch. Such embodiments provide improvements over file-based prefetching and previous block schemes, as they provide a finer grain of control over both prefetch block selection, and the number of blocks to prefetch based on block (or block range) access history.

Abstract translation: 描述了提供用于在存储网络中缓存数据的改进的预取方案的系统和方法。 在一个实施例中，提供了基于块访问历史信息和预取的先前有效性的动态自适应预取机制。 实施例可以考虑预取效率; 指示过去预取的有用性的动态值，预取浪费，以及在任何时间点可用的预取资源，以确定在预取期间预读的块的数量。 这些实施例提供了对基于文件的预取和先前块方案的改进，因为它们提供了对预取块选择和基于块（或块范围）访问历史的预取的块的数量的更精细的控制。