Databricks Inc.

Shi Xin

Srinath Shankar

Matei Zaharia

Alicja Luszczak

Ali Ghodsi

Michael Paul Armbrust

Tathagata Das

Alexander Behm

Bart Samwel

Juliusz Sompolski

Shoumik Palkar

Timothee Hunter

Bogdan Ionut Ghit

Herman Rudolf Petrus Catharina Van Hövell Tot Westerflier

Sue Ann Hong

Eric Keng-Hao Liang

Sameer Paranjpye

The system is configured to: 1) receive a client request; 2) determine executor(s) to generate a response to the user request; 3) provide each of the executor(s) with an indication; 4) receive for each indication a response including an output of either a cloud output or an in-line output to generate a group of in-line outputs and a group of cloud outputs; 5) determine whether the group of in-line outputs comprises all outputs; and 6) in response to the group of in-line outputs not comprising all the outputs for the client request: a) convert the group of in-line outputs to a converted group of cloud outputs; b) generate metadata for the converted group of cloud outputs and the group of cloud outputs; and c) provide response to the client request including the metadata for the converted group of cloud outputs and the group of cloud outputs.

Fetching query results through cloud object stores

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.

Query watchdog

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.

Structured cluster execution for data streams

A function creation method is disclosed. The method comprises defining one or more database function inputs, defining cluster processing information, defining a deep learning model, and defining one or more database function outputs. A database function is created based at least in part on the one or more database function inputs, the cluster set-up information, the deep learning model, and the one or more database function outputs. In some embodiments, the database function enables a non-technical user to utilize deep learning models.

Function creation for database execution of deep learning model

A system comprises an interface, a processor, and a memory. The interface is configured to receive a query. The processor is configured to: determine a set of nodes for the query; determine whether a node of the set of nodes comprises a first engine node type or a second engine node type, wherein determining whether the node of the set of nodes comprises the first engine node type or the second engine node type is based at least in part on determining whether the node is able to be executed in a second engine; and generate a plan based at least in part on the set of nodes. The memory is coupled to the processor and is configured to provide the processor with instructions.

Integrated native vectorized engine for computation

A system for directory level atomic commits includes an interface and a processor. The interface is configured to receive an indication to provide a set of files. The processor is configured to determine whether a file in a directory has been either 1) atomically committed or 2) written by a non-atomic process and not designated as deleted and provide the file as one file of the set of files in the event that the file in the directory has been either 1) atomically committed or 2) written by a non-atomic process and not designated as deleted.

Directory level atomic commit protocol

A system for cluster resource allocation includes an interface and a processor. The interface is configured to receive a process and input data. The processor is configured to determine an estimate for resources required for the process to process the input data; determine existing available resources in a cluster for running the process; determine whether the existing available resources are sufficient for running the process; in the event it is determined that the existing available resources are not sufficient for running the process, indicate to add new resources; determine an allocated share of resources in the cluster for running the process; and cause execution of the process using the share of resources.

Growing community of inventors

San Francisco, CA, United States of America

Shi Xin