公开(公告)号：US10852996B2

公开(公告)日：2020-12-01

申请号：US15673271

申请日：2017-08-09

Applicant: Amazon Technologies, Inc.

Inventor： Jianhua Fan ,  Benjamin Arthur Hawks ,  Norbert Paul Kusters ,  Nachiappan Arumugam ,  Danny Wei ,  John Luther Guthrie, II

IPC: G06F3/06 ,  G06F11/14

Abstract: A slave storage is provisioned using metadata of a master B-tree and updates to references (e.g., offsets) pertaining to data operations of the master B-tree. Master-slave pairs can be used to provide data redundancy, and a master copy can include the master B-tree with references to corresponding data. When provisioning a slave copy, the master sends a B-tree copy to the slave, which stores the slave B-tree copy, allocates the necessary space on local storage, and updates respective offsets of the slave B-tree copy to point to the local storage. Data from the master can then be transferred to the slave and stored according to a note and commit process that ensures operational sequence of the data. Operations received to the master during the process can be committed to the slave copy until the slave is consistent with the master and able to take over as master in the event of a failure.

公开(公告)号：US10812408B1

公开(公告)日：2020-10-20

申请号：US15081646

申请日：2016-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Surya Prakash Dhoolam ,  Christopher Magee Greenwood ,  Mitchell Gannon Flaherty ,  Danny Wei ,  Nachiappan Arumugam

IPC: H04L12/911

Abstract: A distributed system may implement preventing concentrated selection of resource hosts for placing resources within the distributed system. When a request to place a resource at a resource host is received, an evaluation of load metrics for the resource host is made with respect to rejection criteria. If the rejection criteria is satisfied, then the resource host may reject the request to place the resource. If the rejection criteria is not satisfied, then the resource host may not reject the placement of the resource. Rejection criteria may be provided to resource hosts along with the placement request, in some embodiments. Rejection criteria may be changed, weakened, or removed entirely if initial attempts to place a resource are unsuccessful.

公开(公告)号：US10809920B1

公开(公告)日：2020-10-20

申请号：US15385814

申请日：2016-12-20

Applicant: Amazon Technologies, Inc.

Inventor： Marc Stephen Olson ,  Christopher Magee Greenwood ,  Anthony Nicholas Liguori ,  James Michael Thompson ,  Surya Prakash Dhoolam ,  Marc John Brooker ,  Danny Wei

IPC: G06F3/06 ,  H04L29/06 ,  G06F12/14

Abstract: First information about regions of storage space in a storage environment available for a volume is provided to a service provider, with the storage environment being external to the service provider. The service provider is notified that information usable to locate a storage destination of a portion of the volume is unavailable. Second information that includes the storage destination in the storage environment is obtained from the service provider. A data operation is performed at the storage destination, with the storage destination determined based at least in part from the second information.

公开(公告)号：US10768850B2

公开(公告)日：2020-09-08

申请号：US15967023

申请日：2018-04-30

Applicant: Amazon Technologies, Inc.

Inventor： Kiran-Kumar Muniswamy-Reddy ,  Christopher Magee Greenwood ,  Colin Williams ,  Wells Lin ,  Danny Wei ,  Igor A. Kostic

IPC: G06F3/00 ,  G06F3/06 ,  G06F11/14 ,  H04L29/08

Abstract: Generally described, one or more aspects of the present application correspond to a highly distributed replica of a volume stored in a networked computing environment. First and second replicas of the volume can be synchronously replicated, and some implementations of the tertiary replica can be asynchronously replicated. The highly distributed nature of the tertiary replica supports parallel data transfer of the data of the volume, resulting in faster creation of backups and new copies of the volume.

公开(公告)号：US10705956B1

公开(公告)日：2020-07-07

申请号：US15969604

申请日：2018-05-02

Applicant: Amazon Technologies, Inc.

Inventor： Kristina Kraemer Brenneman ,  Norbert Paul Kusters ,  Jianhua Fan ,  Danny Wei

IPC: G06F12/08 ,  G06F12/0804 ,  G06F9/52 ,  G06F16/23

Abstract: A data storage system stores information indicating a determined sequence for performing operations on a data store. A lock is acquired on a portion of the data store. It is determined that performing the operations comprises performing at least one additional operation on the data store. Uncommitted changes implied by the operations are stored in a transaction buffer according to the determined sequence. Changes implied by the additional operation are determined based on a reentrant call to a data store interface. The logged sequence of changes is applied to the data store and the lock is released.

公开(公告)号：US10484015B2

公开(公告)日：2019-11-19

申请号：US15392806

申请日：2016-12-28

Applicant: Amazon Technologies, Inc.

Inventor： Norbert P. Kusters ,  Nachiappan Arumugam ,  Christopher Nathan Watson ,  Marc John Brooker ,  David R. Richardson ,  Danny Wei ,  John Luther Guthrie, II ,  Leah Shalev

IPC: G06F3/06 ,  G06F11/10 ,  G06F11/20 ,  H03M13/15

Abstract: A data storage system includes multiple head nodes and data storage sleds. The data storage sleds include multiple mass storage devices and a sled controller. Respective ones of the head nodes are configured to obtain credentials for accessing particular portions of the mass storage devices of the data storage sleds. A sled controller of a data storage sled determines whether a head node attempting to perform a write on a mass storage device of a data storage sled that includes the sled controller is presenting with the write request a valid credential for accessing the mass storage devices of the data storage sled. If the credentials are valid, the sled controller causes the write to be performed and if the credentials are invalid, the sled controller returns a message to the head node indicating that it has been fenced off from the mass storage device.

公开(公告)号：US20190324666A1

公开(公告)日：2019-10-24

申请号：US16457095

申请日：2019-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Norbert Paul Kusters ,  Jianhua Fan ,  Shuvabrata Ganguly ,  Danny Wei ,  Avram Israel Blaszka

IPC: G06F3/06

Abstract: A data storage system includes multiple head nodes and data storage sleds. A control plane of the data storage system designates, for a volume partition, one of the head nodes to function as a primary head node storing a primary replica of the volume partition and designates two or more other head nodes to function as reserve head nodes storing reserve replicas of the volume partition. Additionally, the primary head node causes volume data for the volume partition to be erasure encoded and stored on multiple mass storage devices in different ones of the data storage sleds.

公开(公告)号：US20190272222A1

公开(公告)日：2019-09-05

申请号：US16415898

申请日：2019-05-17

Applicant: Amazon Technologies, Inc.

Inventor： Danny Wei ,  Shiow-wen Wendy Cheng

IPC: G06F11/16 ,  G06F12/1072 ,  G06F12/1009

Abstract: A failure of a storage device used to provide a mirrored storage volume can be managed without a full re-mirroring of the volume. The volume can be provided using a set of similar storage devices on each of a master server and a slave server, and a technique such as data striping can be used to store the data for the volume across the various devices. When a storage device becomes unavailable, the data from the corresponding storage device on the other mirrored server can be written to the remaining storage devices on the server experiencing the device failure. The data interface can be virtualized such that the user can continue to send input and output (I/O) requests using the same address information. A translation layer can map the virtualized addresses to the physical addresses where the data is stored.

公开(公告)号：US10110503B2

公开(公告)日：2018-10-23

申请号：US15156058

申请日：2016-05-16

Applicant: Amazon Technologies, Inc.

Inventor： Tate Andrew Certain ,  Roland Paterson-Jones ,  James R Hamilton ,  Sachin Jain ,  Matthew S Garman ,  David N Sunderland ,  Danny Wei ,  Fiorenzo Cattaneo

IPC: G06F15/173 ,  H04L12/911 ,  G06Q10/00 ,  G06Q30/02 ,  G06Q30/04 ,  H04L29/08

Abstract: Commitments against various resources can be dynamically adjusted for customers in a shared-resource environment. A customer can provision a data volume with a committed rate of Input/Output Operations Per Second (IOPS) and pay only for that commitment (plus any overage), for example, as well as the amount of storage requested. The customer can subsequently adjust the committed rate of IOPS by submitting an appropriate request, or the rate can be adjusted automatically based on any of a number of criteria. Data volumes for the customer can be migrated, split, or combined in order to provide the adjusted rate. The interaction of the customer with the data volume does not need to change, independent of adjustments in rate or changes in the data volume, other than the rate at which requests are processed.

公开(公告)号：US20180089780A1

公开(公告)日：2018-03-29

申请号：US15694685

申请日：2017-09-01

Applicant: Amazon Technologies, Inc.

Inventor： Marc J. Brooker ,  Madhuvanesh Parthasarathy ,  Danny Wei ,  Tobias L. Holgers ,  Yu Li

IPC: G06Q50/22 ,  G06F11/00 ,  G06Q10/10

CPC classification number: G06Q50/22 ,  G06F11/00 ,  G06F11/008 ,  G06F11/0727 ,  G06F11/0793 ,  G06Q10/10

Abstract: The relative health of data storage drives may be determined based, at least in some aspects, on data access information and/or other drive operation information. In some examples, upon receiving the operation information from a computing device, a health level of a drive may be determined. The health level determination may be based at least in part on operating information received from a client entity. Additionally, a storage space allocation instruction or operation may be determined for execution. The allocation instruction or operation determined to be performed may be based at least in part on the determined health level.