公开(公告)号：US12008040B2

公开(公告)日：2024-06-11

申请号：US17362456

申请日：2021-06-29

Applicant: Databricks, Inc.

Inventor： Michael Paul Armbrust ,  Andreas Neumann ,  Mukul Murthy ,  Jonathan Mio

IPC: G06F16/901 ,  G06F16/215 ,  G06F16/22 ,  G06F16/245

CPC classification number: G06F16/9024 ,  G06F16/215 ,  G06F16/2282 ,  G06F16/245

Abstract: A system for dataflow graph processing comprises a communication interface and a processor. The communication interface is configured receive an indication to generate a dataflow graph, wherein the indication includes a set of queries. The processor is coupled to the communication interface and is configured to: determine dependencies of each query in the set of queries on another query; determine a DAG of nodes based at least in part on the dependencies; insert a node in the DAG of nodes to generate an updated DAG to enforce an expectation; determine a dataflow graph based on the updated DAG; and provide the dataflow graph.

公开(公告)号：US11693723B2

公开(公告)日：2023-07-04

申请号：US17537124

申请日：2021-11-29

Applicant: Databricks, Inc.

Inventor： Alicja Luszczak ,  Srinath Shankar ,  Shi Xin

IPC: G06F11/07 ,  G06F11/34 ,  G06F11/30

CPC classification number: G06F11/0757 ,  G06F11/076 ,  G06F11/0721 ,  G06F11/0793 ,  G06F11/3024 ,  G06F11/3419 ,  G06F2201/81 ,  G06F2201/88

Abstract: A system for monitoring job execution includes an interface and a processor. The interface is configured to receive an indication to start a cluster processing job. The processor is configured to determine whether processing a data instance associated with the cluster processing job satisfies a watchdog criterion; and in the event that processing the data instance satisfies the watchdog criterion, cause the processing of the data instance to be killed.

公开(公告)号：US20230141556A1

公开(公告)日：2023-05-11

申请号：US17976361

申请日：2022-10-28

Applicant: Databricks, Inc.

Inventor： Michael Paul Armbrust ,  Tathagata Das ,  Shi Xin ,  Matei Zaharia

IPC: G06F16/2453 ,  G06F16/2455

CPC classification number: G06F16/24542 ,  G06F16/24568

Abstract: A system for executing a streaming query includes an interface and a processor. The interface is configured to receive a logical query plan. The processor is configured to determine a physical query plan based at least in part on the logical query plan. The physical query plan comprises an ordered set of operators. Each operator of the ordered set of operators comprises an operator input mode and an operator output mode. The processor is further configured to execute the physical query plan using the operator input mode and the operator output mode for each operator of the query.

公开(公告)号：US11514045B2

公开(公告)日：2022-11-29

申请号：US16721402

申请日：2019-12-19

Applicant: Databricks Inc.

Inventor： Michael Paul Armbrust ,  Tathagata Das ,  Shi Xin ,  Matei Zaharia

IPC: G06F16/2453 ,  G06F16/2455

Abstract: A system for executing a streaming query includes an interface and a processor. The interface is configured to receive a logical query plan. The processor is configured to determine a physical query plan based at least in part on the logical query plan. The physical query plan comprises an ordered set of operators. Each operator of the ordered set of operators comprises an operator input mode and an operator output mode. The processor is further configured to execute the physical query plan using the operator input mode and the operator output mode for each operator of the query.

公开(公告)号：US11216324B2

公开(公告)日：2022-01-04

申请号：US16793921

申请日：2020-02-18

Applicant: Databricks Inc.

Inventor： Alicja Luszczak ,  Srinath Shankar ,  Shi Xin

IPC: G06F11/07 ,  G06F11/34 ,  G06F11/30

Abstract: A system for monitoring job execution includes an interface and a processor. The interface is configured to receive an indication to start a cluster processing job. The processor is configured to determine whether processing a data instance associated with the cluster processing job satisfies a watchdog criterion; and in the event that processing the data instance satisfies the watchdog criterion, cause the processing of the data instance to be killed.

公开(公告)号：US10606675B1

公开(公告)日：2020-03-31

申请号：US15809907

申请日：2017-11-10

Applicant: Databricks Inc.

Inventor： Alicja Luszczak ,  Srinath Shankar ,  Shi Xin

IPC: G06F11/07 ,  G06F11/34 ,  G06F11/30

Abstract: A system for monitoring job execution includes an interface and a processor. The interface is configured to receive an indication to start a cluster processing job. The processor is configured to determine whether processing a data instance associated with the cluster processing job satisfies a watchdog criterion; and in the event that processing the data instance satisfies the watchdog criterion, cause the processing of the data instance to be killed.

公开(公告)号：US10361928B2

公开(公告)日：2019-07-23

申请号：US15682397

申请日：2017-08-21

Applicant: Databricks Inc.

Inventor： Ali Ghodsi ,  Ion Stoica ,  Matei Zaharia

IPC: G06F15/173 ,  H04L12/24 ,  G06F11/30 ,  H04L12/26

Abstract: A system for cluster management comprises a status monitor and an instance replacement manager. The status monitor is for monitoring status of an instance of a set of instances on a cluster provider. The instance replacement manager is for determining a replacement strategy for the instance in the event the instance does not respond. The replacement strategy for the instance is based at least in part on a management criteria for on-demand instances and spot instances on the cluster provider.

公开(公告)号：US10095735B2

公开(公告)日：2018-10-09

申请号：US15675619

申请日：2017-08-11

Applicant: Databricks Inc.

Inventor： Ali Ghodsi ,  Ion Stoica ,  Matei Zaharia

IPC: G06F7/00 ,  G06F17/30

Abstract: A system for exploring data in a database comprises a query parser, a parameter manager, a query submitter, and a result formatter. The query parser is to receive a base query and determine an input parameter from the base query. The parameter manager is to provide a first request for a value for the input parameter; receive the value for the input parameter; and provide a second request for the value for the input parameter. The query submitter is to determine a first query using the base query and the value for the input parameter; and provide an indication to execute the first query. The result formatter is to receive a result associated with the indication to execute the first query.

公开(公告)号：US09990230B1

公开(公告)日：2018-06-05

申请号：US15052204

申请日：2016-02-24

Applicant: Databricks Inc.

Inventor： Ion Stoica ,  Yandong Mao ,  Eric Liang

IPC: G06F9/46 ,  G06F9/48

CPC classification number: G06F9/4887

Abstract: A system for scheduling a notebook execution includes an interface and a processor. The interface is to receive an indication to schedule a notebook for execution, wherein the indication comprises a scheduled time and a cluster. The processor is to determine whether it is the scheduled time; and in the event that it is the scheduled time: determine whether the cluster is running; and in the event that the cluster is not running, set up the cluster and cause the notebook to execute using the cluster.

公开(公告)号：US09836302B1

公开(公告)日：2017-12-05

申请号：US15010845

申请日：2016-01-29

Applicant: Databricks Inc.

Inventor： Timothee Hunter ,  Ali Ghodsi ,  Ion Stoica

IPC: G06F9/44 ,  G06F17/30 ,  G06F9/445

CPC classification number: G06F8/71 ,  G06F8/54 ,  G06F9/445 ,  G06F9/45512 ,  G06F9/5066 ,  G06F17/30867

Abstract: A system for processing a notebook includes an input interface and a processor. The input interface is to receive a first notebook. The notebook comprises code for interactively querying and viewing data. The processor is to load the first notebook into a shell. The shell receives one or more parameters associated with the first notebook. The shell executes the first notebook using a cluster.