公开(公告)号：US11178014B1

公开(公告)日：2021-11-16

申请号：US15719467

申请日：2017-09-28

Applicant: Amazon Technologies, Inc.

Inventor： Ondrej Sevce ,  Jamie Plenderleith

IPC: H04L29/08 ,  H04L12/26 ,  H04L29/06 ,  H04L12/24 ,  H04L12/715

Abstract: A method includes forming a logical group of network devices from a plurality of network devices based on at least one attribute of the network devices. The method further includes selecting at least one similarity metric for the logical group of network devices. The method also includes determining a value of the similarity metric for each of the network devices of the logical group. The method further includes comparing values of the similarity metric corresponding to each of the network devices of the logical group against a threshold value. The method also includes determining an action to be taken at one or more of the network devices based on the comparison between the values of the similarity metric and the threshold. There may also be multiple interconnected groups, each performing these actions independently and conveying the computed information between each other.

公开(公告)号：US11126623B1

公开(公告)日：2021-09-21

申请号：US15278807

申请日：2016-09-28

Applicant: Amazon Technologies, Inc.

Inventor： Jamie Plenderleith

IPC: G06F16/2453 ,  G06F16/22

Abstract: A database system may receive a query and form a plan for executing the query using a hypothetical index selected based on columns referenced by the query. The database system may compare the hypothetical index to indexes on the computing nodes of the database system. Based on the comparison, the database system may form a new index, based on the hypothetical index, on one of the computing nodes. An additional computing node may be added to the database system for the purpose of maintaining the new index. Subsequent queries having commonality with the first query may be processed on a node maintaining the first index.

公开(公告)号：US11061727B1

公开(公告)日：2021-07-13

申请号：US16554140

申请日：2019-08-28

Applicant: Amazon Technologies, Inc.

Inventor： Monika Marta Gnyp ,  Jamie Plenderleith

IPC: G06F9/50 ,  G06K9/62 ,  G06F12/0802

Abstract: Systems and techniques are described for predicting future overlap in requests for a compute resource to address a system overload before it occurs. Requests for a resource may be tracked in time and grouped based on one or more common characteristics of the requests, such as a time of occurrence of the requests and a period that they repeat. Once grouped, different groups of requests for the resource may be tracked across at least one dimension, such as a periodic time of occurrence, a volume of requests, or a length of time of each occurrence of a group, to generate tracking data. Based on the tracking data, predictions may be generated indicating whether and to what extent the groups of resources will overlap at a future time. Additional resources may be provisioned to process the requests to prevent or reduce the likelihood of a system overload at the future time.

公开(公告)号：US10824641B1

公开(公告)日：2020-11-03

申请号：US15184927

申请日：2016-06-16

Applicant: Amazon Technologies, Inc.

Inventor： Jamie Plenderleith

IPC: G06F16/27 ,  G06F16/242

Abstract: A first database may receive a query comprising a first portion associated with a non-deterministic result. The first non-deterministic portion of the query may be mapped to a second deterministic portion. A second, deterministic query may be formed by replacing the first portion with the second portion. The second version of the query may be executed on the first database, causing the first database to transition from a first state to a second state. The second query may be executed on a second database in the first state, causing the second database to transition to a state equivalent to the second state of the first database.

公开(公告)号：US10764214B1

公开(公告)日：2020-09-01

申请号：US16219338

申请日：2018-12-13

Applicant: Amazon Technologies, Inc.

Inventor： Jamie Plenderleith ,  Marios Dimitriou ,  Donagh Edward Hatton ,  Michael Achola ,  Marco Losito ,  Edouard Stephane Gilles Marie Vincent

IPC: H04L12/939 ,  H04L12/947 ,  H04L12/26 ,  H04L12/24 ,  H04L1/00 ,  H04L12/751

Abstract: Technologies are provided for identifying a source of errors within a computer network that uses cut-through forwarding of network packets. For example, inbound network packets can be received by network devices configured to perform cut-through forwarding. Once the network packets are received, they are processed using cut-through forwarding. If any packet errors are detected, error data associated with the detected errors are stored by the network devices. The error data is transmitted to a monitoring service that uses the error data to create a model of a flow of the errors through the network and to identify a source of the errors. In at least some embodiments, a topology of the network is used by the monitoring service to create the model of the packet error flow.