Amazon Technologies, Inc.

Aaron Ben Fernandes

Gaurav Gupta

Harsha Ramalingam

Jacob Carr

Brian Thomas Kachmarck

Naveen Anand Subramaniam

Brandon William Porter

Vishal Parakh

Michael James McInerny

Anton Vladilenovich Goldberg

Karthik Tamilmani

Andrew Christopher Schleit

Robert Stanley Bailes

Sean Robert Connell

Ravishankar Bhagavandas

Huihui Li

Michael David Decker

Nicolas Valere Choumitsky

Arjan Xeka

Zehua Wang

Jiabin Li

Described are techniques for reducing inaccurate values in databases by managing the order in which processes are enqueued and executed. A modification process to modify a first value in a database may be received. A precomputation process that modifies values dependent on the first value may be enqueued prior to enqueuing of the modification process to ensure that the modification process does not occur if the precomputation process fails. The modification process may be executed prior to executing the precomputation process to ensure that the precomputation process acts to modify the dependent values using the modified version of the first value.

Systems for consistent modification of stored values

A system obtains a first data chunk and a second data chunk of a plurality of data chunks associated with a first data snapshot of a computing system. A hash record is assigned to a data chunk, and used to create a hash value that is written to a first lookup table. The hash function is selected from a plurality of hash functions. The system creates a first archive by saving the plurality of data chunks and the first lookup table to a datastore. The system writes a second hash record for the individual data chunks to a second lookup table using the same hash functions that were used for the first lookup table. Dissimilar hash values between the first lookup table and the second lookup table are identified, and a second archive that includes data chunks with different data from the corresponding data chunks from the first data snapshot is created based on the data chunks with the dissimilar hash values.

Reducing hash collisions in large scale data deduplication

Items within a data set can be redistributed to different partitions of a distributed data store according to modified hash values. A redistribution event may, in some embodiments, trigger the redistribution of a data set. Modified hash values for items in the data set may be generated according to a secondary hashing scheme to be used for identifying the location of a new partition to store the item instead of hash values based on current key values that identify a current partition that stores the item. Access can be provided to items based on the modified hash values to determine the new partition that stores the item after redistribution.

Redistributing a data set amongst partitions according to a secondary hashing scheme

Methods, systems, and computer-readable media for real-time call tracing in a service-oriented system are disclosed. A request comprising a trace signature is received at a service in a service-oriented system. The trace signature comprises a representation of one or more upstream services in an upstream call path associated with the request. Based at least in part on the trace signature, the service determines one or more actions to perform with respect to the request.

Real-time call tracing in a service-oriented system

A computing resource service provider may provide customers with access to various services provided by a set of service endpoints. During certain intervals of time increased network traffic may cause an increase in the consumption of computing resources of the set of service endpoints. A throttling trigger may be detected that may cause one or more routing devices to reroute network traffic to one or more lower tier routing devices. The lower tier routing devices may maintain throttling information and forward network traffic to the set of service endpoints.

Shaping network traffic using throttling decisions

A data computation rate is calculated for use by components in a computational data system. The data computation rate defines the frequency at which a computation, or other types of processing, is performed on or using certain data, such as a data value in a database. The data computation rate might be calculated based upon a current or historical data consumption rate that defines the frequency at which a consumer requests or has requested data, a data update rate that defines the current or historical frequency at which the data that is utilized to generate the processed data is or has been modified, a consumer-specified tolerance, and/or other information. The computed data consumption rate might then be utilized to specify the frequency at which the data should be processed by components in the computational data system.

Optimizing computational data systems

Techniques are described for employing precomputed results of applying rules to content items, the rules applicable to determine whether content items may be electronically published. On receiving a request for a content item, rules applicable to the content item may be identified. A datastore of precomputed results of rule application may be accessed to determine whether the datastore includes a result of applying a current or previous version of each rule. If the datastore includes a current result, the current result may be employed in determine whether the content item may be presented. If the datastore includes a previous result, the previous result may be so employed. If the datastore includes a previous result or no appropriate result, a job may be queued to calculate the current result asynchronously relative to the request for the content item.

Rule evaluation based on precomputed results

Growing community of inventors

Redmond, WA, United States of America

Aaron Ben Fernandes