公开(公告)号：US10715460B2

公开(公告)日：2020-07-14

申请号：US14642445

申请日：2015-03-09

Applicant: Amazon Technologies, Inc.

Inventor： Marc John Brooker ,  Christopher Magee Greenwood ,  Surya Prakash Dhoolam ,  James Michael Thompson ,  Marc Stephen Olson ,  Mitchell Gannon Flaherty

IPC: H04L12/911 ,  G06F9/50 ,  G06F9/455

Abstract: A distributed system may implement opportunistic resource migration to optimize resource placement. Resources may be placed amongst different resource hosts of a distributed system. An evaluation of the current placement may be performed according placement criteria that improve placement of the resources at the distributed system. Based on the evaluation, the prospective migration of resources that exceed an improvement threshold may be identified as candidate resources to migrate. Migration for the candidate resources may be opportunistically performed. In some embodiments, a priority may be assigned to the candidate resources according to which the candidate resources are selected for performing migration.

公开(公告)号：US10594620B1

公开(公告)日：2020-03-17

申请号：US15078856

申请日：2016-03-23

Applicant: Amazon Technologies, Inc.

Inventor： Christopher Magee Greenwood ,  Gary Michael Herndon, Jr. ,  Mitchell Gannon Flaherty ,  Surya Prakash Dhoolam

IPC: H04L29/08 ,  G06F9/50 ,  H04L12/911 ,  G06F9/455 ,  G06F11/00

Abstract: A distributed system may implement analyzing bit vectors for resource placement. Bit vectors may be maintained or generated for currently hosted resources in a distributed system according to placement criteria so that individual bit values of a bit vector indicate whether a corresponding one of the placement criteria is satisfied for the current placement of the resource. A resource may be identified for migration and a possible placement determined for the resource. A bit vector may be generated for the possible placement and compared with the bit vector for the current placement of the resource to determine whether the possible placement improves the placement of the resource with respect to the placement criteria.

公开(公告)号：US10564870B1

公开(公告)日：2020-02-18

申请号：US15058860

申请日：2016-03-02

Applicant: Amazon Technologies, Inc.

Inventor： Christopher Magee Greenwood ,  Gary Michael Herndon, Jr. ,  Surya Prakash Dhoolam ,  Mitchell Gannon Flaherty

IPC: G06F3/06

Abstract: The allocation of resources, such as for data storage, can be performed based at least in part upon predicted values for utilization and growth, among other such values. Various features can be used to predict the initial utilization and growth rate for a data volume, and these predicted values can be used to determine where to place the volumes. The features can include, for example, customer usage history, volume type, volume purpose, type of attached virtual machine, and the like. The ability to predict actual usage can enable capacity to be allocated based on an as-needed basis instead of providing large blocks of allocated capacity that would go largely unused. Similar predictions can be used to determine whether and where to migrate data volumes so as to maintain sufficient capacity across a group of resources.

公开(公告)号：US20190179661A1

公开(公告)日：2019-06-13

申请号：US16279980

申请日：2019-02-19

Applicant: Amazon Technologies, Inc.

Inventor： Surya Prakash Dhoolam ,  Mitchell Gannon Flaherty ,  Christopher Magee Greenwood ,  Gary Michael Herndon, JR. ,  Rahul Karnik ,  Sriram Venugopal

IPC: G06F9/455 ,  G06F3/06

Abstract: Data volumes hosted for customers in a multi-tenant environment can be moved advantageously throughout the environment to improve performance and reduce cost. A data volume can serve I/O for a virtual machine instance, and it can be advantageous for the virtual machine and the data volume to be in the same network locality, or share at least some of the same network state and interconnection. Since there is limited capacity in a network locality, data volumes not attached to virtual machines can be moved to other locations in the environment. This can include moving data volumes to other local network topologies or snapshotting data volumes and writing the snapshots to another storage service. If the data volume is again needed for I/O, the data volume can moved, allocated, or reattached as necessary.

公开(公告)号：US20190158422A1

公开(公告)日：2019-05-23

申请号：US16257499

申请日：2019-01-25

Applicant: Amazon Technologies, Inc.

Inventor： Christopher Magee Greenwood ,  Surya Prakash Dhoolam ,  Mitchell Gannon Flaherty ,  Nishant Satya Lakshmikanth

IPC: H04L12/911 ,  H04L12/26

Abstract: A distributed system may implement analyzing resource placement fragmentation for capacity planning. Capacity planning may determine when, where, and how much capacity to implement for a distributed system that hosts resources. Placement constraints for resources may, over time, create fragmentation or stranded capacity which is available yet unusable to host new resources. Analyzing capacity fragmentation across a distributed system may allow a determination of available capacity that is actually available to host additional resources. In some embodiments, future resource placements may be estimated in order to perform capacity fragmentation analysis to determine available capacity.

公开(公告)号：US10216534B1

公开(公告)日：2019-02-26

申请号：US14968354

申请日：2015-12-14

Applicant: Amazon Technologies, Inc.

Inventor： Surya Prakash Dhoolam ,  Mitchell Gannon Flaherty ,  Christopher Magee Greenwood ,  Gary Michael Herndon, Jr. ,  Rahul Karnik ,  Sriram Venugopal

IPC: G06F9/455 ,  G06F3/06

Abstract: Data volumes hosted for customers in a multi-tenant environment can be moved advantageously throughout the environment to improve performance and reduce cost. A data volume can serve I/O for a virtual machine instance, and it can be advantageous for the virtual machine and the data volume to be in the same network locality, or share at least some of the same network state and interconnection. Since there is limited capacity in a network locality, data volumes not attached to virtual machines can be moved to other locations in the environment. This can include moving data volumes to other local network topologies or snapshotting data volumes and writing the snapshots to another storage service. If the data volume is again needed for I/O, the data volume can moved, allocated, or reattached as necessary.

公开(公告)号：US10185507B1

公开(公告)日：2019-01-22

申请号：US15385829

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

Abstract: A first location in one or more storage nodes is determined, with the first location being associated with a first block of a plurality of blocks associated with a storage volume. First information that maps the first block to the first location is generated. At least a portion of data is obtained from the first block at the first location. A second location in the one or more storage nodes is determined, with the second location being associated with a second block. Second information that maps the second block to the second location is included in the first information. A second computer system, different from the first computer system, is enabled, by providing at least a portion of the first information, to perform an operation to the storage volume.

公开(公告)号：US09582377B1

公开(公告)日：2017-02-28

申请号：US14663005

申请日：2015-03-19

Applicant: Amazon Technologies, Inc.

Inventor： Surya Prakash Dhoolam ,  Gary Michael Herndon, Jr.

IPC: G06F11/00 ,  G06F11/20 ,  G06F9/50

CPC classification number: G06F11/201 ,  G06F9/5011 ,  G06F11/00 ,  G06F2201/85

Abstract: A remirror buffer can be used in failover situations so as to backup storage volumes in a service provider. The remirror buffer is dynamically resized to meet current usage metrics captured from a data center. A risk boundary can be defined through which resource hosts are grouped together so as to determine the usage metrics. The risk boundary can be based on a topology of the data center, such as a room/rack/sharing of power supplies, or other characteristics of the resource hosts.

Abstract translation: 可以在故障转移情况下使用重映像缓冲区，以便在服务提供商中备份存储卷。 动态调整镜像缓冲区以满足从数据中心捕获的当前使用度量。 可以定义风险边界，将资源主机分组在一起，以确定使用度量。 风险边界可以基于数据中心的拓扑结构，例如房间/机架/电源共享或资源主机的其他特性。