Amazon Technologies, Inc.

Jamie Plenderleith

Alan Michael Judge

Monika Marta Gnyp

Gianluca Grilli

Alaa Adel Mahdi Hayder

Donagh Edward Hatton

Thomas A Volpe

Kiran Kalkunte Seshadri

Rostislav Babocichin

Guillaume Boissier

Marco Losito

Brian Hayward

Parker J Lord

Michael Achola

James McCann

Sarah Rose Quigley

Suzie Cuddy

Marios Dimitriou

Ondrej Sevce

Edouard Stephane Gilles Marie Vincent

Systems and methods are provided to implement a database connection manager that dynamically routes database query statements to database servers storing replicas of the database. In embodiments, the database connection manager may implement a data access interface that mimics the interface of the database servers, so as to appear to clients as just another database server. In embodiments, various health or performance metrics of the servers are monitored, and the routing may be performed based on the metrics to load balance the servers. In embodiments, the routing may distinguish between read and write statements, so that read statements are routed to servers hosting read-only replicas, and write statements are routed to servers hosting writable replicas. These and other disclosed features improve the functioning of the database, to allow, among other things, the database servers to be dynamically load balanced, and the servers' identities to be hidden from clients.

Database connection manager, metric-based routing and load balancing for replica servers

Systems and methods are provided to implement a database request router that routes queries to database servers storing database replicas. In embodiments, the request router maintains caching state metadata that indicates respective caching states of the database servers. For an incoming query, the request router selects a database server to receive the query based on the caching states of the database servers to improve cache utilization. In embodiments, the caching state metadata indicates whether different database objects used by observed queries are cached at individual servers. The database objects used may be determined from execution plans for the queries, obtained from the database servers. In embodiments, the request router may determine a querying pattern of the database and use it to predict an expected time for certain queries. The request router may generate a priming query ahead of the expected time to prepare database server cache for the expected queries.

Database request router improving server cache utilization

Methods, systems, and computer-readable media for energy-optimizing placement of resources in data centers are disclosed. A resource placement manager determines information descriptive of energy usage by one or more data centers. The one or more data centers comprise a plurality of computing resources in a plurality of corresponding locations. The resource placement manager selects, from the plurality of computing resources in the plurality of corresponding locations, a particular computing resource in a particular location for performing one or more computing tasks. The particular computing resource in the particular location is selected based at least in part on reducing energy usage associated with the one or more data centers according to the information descriptive of energy usage. The particular computing resource in the particular location is used to perform the one or more computing tasks.

Energy-optimizing placement of resources in data centers

A computer system receives a set of messages, and processes the messages using a filter. In some examples, the filter is defined using a pattern matching language such as a regular expression. The system collects a set of representative messages that match the filter. Using the set of representative messages, the system generates a corresponding flow network graph. Using the flow network graph, the system determines a similarity measure that indicates whether a new message resembles other matching messages of the filter. Based on the similarity measure, in various embodiments, the system identifies potential errors in the filter definitions, omissions in the terms of the filter, and message outliers that indicate system anomalies or events of particular interest to the user.

Adaptive data filtering system

Techniques and apparatus for performing integrity verification for data stored on computing systems are described. One technique involves receiving a request to retrieve data from a first data repository. One or more parameters of the request are determined. The data is obtained from the first repository, based on the parameters. Verification information for the data is obtained from a second data repository, based on the parameters. A determination is made as to whether the data obtained from the first data repository has been modified. A message is sent that indicates whether the data obtained from the first data repository has been modified.

Data integrity verification

A system can be configured to determine whether a user is a human or a computer based on whether the user is capable of intuitive-based decision making to identify requested features. The system can generate a challenge that includes a question emphasizing mental shortcuts and associations developed through social and cultural interactions. The challenge also includes one or more media objects that are distinguishable to a human user due to the mental shortcuts and associations that permit selection of the correct media object in light of the question. Intuitive connections between statements and media objects are often difficult to implement within computer programs and algorithms due to the two-stage challenge requiring both comprehension and recognition of important features.

Intuition-based challenges

Techniques for database normalization recommendation and transparent database normalization are described. A normalization engine can analyze the data stored by database tables to determine scenarios in which normalization of the tables may be beneficial. The normalization engine can recommend normalization to an end user, such as during a database migration process. The normalization engine can alternatively perform row-by-row or complete columnar normalization and cause queries issued against normalized tables based on the previous table schema to be automatically rewritten to adhere to the updated data layout.

Transparent database normalization in provider networks

Directional capacity of interfaces for networking devices are dynamically modified. Network traffic utilization of one direction of a network interface may be determined. A modification to a capacity of the networking device to process network traffic in the one direction of the network may be determined. The modification may then be applied to the networking device so that subsequent network traffic is processed according to the modified capacity in the one direction of the interface.

Dynamically configurable networking device interfaces for directional capacity modifications

Techniques for database performance degradation detection and prevention are described. A statement performance monitor observes queries executed against a database engine and clusters the queries into groups of queries. The index utilization of the query groups and execution metrics are tracked over time, and a sudden change of index utilization can be detected. The change can be reported to users and/or new indexes may be automatically generated to serve affected query groups. Additionally, a statement performance monitor may be deployed to statically analyze code to identify modified queries and the resultant change of use of query indexes.

Database performance degradation detection and prevention

Techniques for transparent database table partitioning using proxy-based query rewriting are described. Multiple tables of a single database can be split up and hosted by multiple database instances. A database proxy receives database statements to be executed by the database and can send the statement to the corresponding database instance. For statements referencing multiple tables that are not co-hosted by a same database instance, the proxy rewrites the statements to generate multiple different statements to be sent to individual database instances hosting the referenced tables, and generates a final result based on responses from the database instances.

Transparent database table partitioning using proxy-based query rewriting

Technologies are provided for dynamically adaptive Bloom filters. After processing a lookup operation using a Bloom filter, a feedback message is received which can be used to determine whether the Bloom filter produced a false-positive lookup result. A Bloom filter accuracy score can be updated based on the feedback message. If the accuracy score for the Bloom filter falls below a specified threshold then the Bloom filter can be changed, or replaced with a different Bloom filter. In at least some embodiments, a plurality of Bloom filters can be created. One of the Bloom filters, designated as an active Bloom filter, can be used to process lookup operations. When a feedback message is received, accuracy scores can be updated for each of the Bloom filters. Based on the accuracy scores, the active Bloom filter can be deactivated and another Bloom filter, with a better accuracy score, can be activated.

Dynamically-adaptive bloom-filter

Dynamic modifications to directional capacity of networking device interfaces

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.

Establishment and control of grouped autonomous device networks

Disclosed are various embodiments for generating a physics-based CAPTCHA. In a physics-based CAPTCHA, an object is placed within a scene so that a visually observable change occurs to the object. The scene is animated so that the visually observable change occurs to the object. Before and after imagery can be captured and used as a challenge and a response. Incorrect responses can be generated by altering the scene or object.

Physics-based CAPTCHA

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.

Growing community of inventors

Dublin, Ireland

Jamie Plenderleith