公开(公告)号：US11968280B1

公开(公告)日：2024-04-23

申请号：US17456546

申请日：2021-11-24

Applicant: Amazon Technologies, Inc.

Inventor： Vinayak Sood ,  Mandakini Saroop ,  Shu Song ,  Tejas Mahadeo Ghadge ,  Tyson Charles Olychuck ,  Dinesh Saheblal Gupta ,  Jia Liu

IPC: G06F8/33 ,  G06F8/41 ,  H04L67/133 ,  H04L67/564 ,  H04L67/5651 ,  H04L67/60

CPC classification number: H04L67/60 ,  H04L67/133 ,  H04L67/564 ,  H04L67/5651

Abstract: Systems and methods are described controlling ingestion of data items within a data stream by executions of a serverless function on a serverless compute system. A poller device can act as an intermediary between the data stream and the serverless function, iteratively retrieving data items from the data stream and passing them in invocations of the serverless function. To allow for fine-grained control of ingestion without requiring implementation of complex logic at the poller device, the poller device can enable the serverless function to pass instructions controlling subsequent operation of the poller device. Each execution of the serverless function may determine whether subsequent operation of the poller device should be altered, and if so, instruct the poller device accordingly. The poller device can then modify its operation pursuant to the instructions, enabling highly granular control of streaming data ingestion without inhibiting existing benefits of serverless computing.

公开(公告)号：US11442943B1

公开(公告)日：2022-09-13

申请号：US17007778

申请日：2020-08-31

Applicant: Amazon Technologies, Inc.

Inventor： Tyson Charles Olychuck ,  Xiaoyu Meng ,  Deepak Verma

IPC: G06F16/2455 ,  G06F11/14

Abstract: A first group processing attempt may be performed on a first record group in a stream of ordered data records. The first group processing attempt may fail, and the first record group may be split into at least a second record group and a third record group. A second group processing attempt may be performed on the second record group, and a third group processing attempt may be performed on the third record group. For the second, the third and following record groups, each record group that is not processed successfully may be split into two or more other record groups and additional group processing attempts may be performed on the two or more other record groups until the error-causing record is isolated as a single record. Processing of the error-causing record may be bypassed after it is isolated as a single record.

公开(公告)号：US11388210B1

公开(公告)日：2022-07-12

申请号：US17305139

申请日：2021-06-30

Applicant: Amazon Technologies, Inc.

Inventor： Vinayak Sood ,  Jia Liu ,  Mandakini Saroop ,  Tejas Mahadeo Ghadge ,  Himanshu Sharma ,  Nithin Vommi ,  Tyson Charles Olychuck ,  Dinesh Saheblal Gupta ,  Peng Sun

IPC: H04L29/06 ,  H04L65/61 ,  H04L67/567 ,  H04L67/566 ,  H04L65/65

Abstract: Systems and methods are described implementing streaming analytics on a serverless compute system. A user can specify a data stream against which analytics should be conducted, serverless functions to be used to conduct the analysis, and criteria for the analytics, such as windowing criteria and aggregation criteria. The windowing criteria can specify windows of items within the stream that should be collectively analyzed. The aggregation criteria can specify how to group items within each window during analysis. A poller device can read data items from the stream, window and group the items according to the windowing and aggregation criteria, and invoke serverless functions to conduct streaming analytics on the data items. The poller device can further maintain state between invocations.