System and method for analyzing big data activities

• US 9,983,973 B2
• Filed: 02/18/2016
• Issued: 05/29/2018
• Est. Priority Date: 02/18/2015
• Status: Active Grant

• Current Assignee: Unravel Data Systems, Inc.
• Original Assignee: Unravel Data Systems, Inc.
• Inventors: Babu, Shivnath, Agarwal, Kunal
• Primary Examiner(s): Le, Dieu-Minh
• Application Number:
  US15/047,554
• Publication Number:
  US 20160239399A1
• Time in Patent Office: 831 Days
• Field of Search: 714 471, 714 37, 714 381, 714 3813
• CPC Class Codes: G06F 11/302 where the computing system component is a software system
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 16/122 using management policies backup systems G06F11/1446; file migration policies for HSM systems G06F16/185
• CPC Class Codes: G06F 16/182 Distributed file systems

Abstract

A system and method for analyzing big data activities are disclosed. According to one embodiment, a system comprises a distributed file system for the entities and applications, wherein the applications include one or more of script applications, structured query language (SQL) applications, Not Only (NO) SQL applications, stream applications, search applications, and in-memory applications. The system further comprises a data processing platform that gathers, analyzes, and stores data relating to entities and applications. The data processing platform includes an application manager having one or more of a MapReduce Manage, a script applications manager, a structured query language (SQL) applications manager, a Not Only (NO) SQL applications manager, a stream applications manager, a search applications manager, and an in-memory applications manager. The application manager identifies if the applications are one or more of slow-running, failed, killed, unpredictable, and malfunctioning.

Claims

1. A system, comprising:

a processor and a memory;

an application manager running on the processor that identifies resources used by an application for big data running on a cluster and provides MapReduce attempt success and failure totals for a workload;

a workflow manager running on the processor that identifies problems with the application by providing a status of how each workflow is performing against a service level agreement;

a deep events application running on the processor that provides root-cause analysis and solutions for application problems and system-level problems;

a live alerts application running on the processor that provides alerts on the application, each workflow, users, tables, and queues;

an information tag application running on the processor that tags the application, each workflow, the tables, the users, and entities;

an entity search application running on the processor that indexes and associates cluster activity with the application, each workflow, the tables, the users, the queues, machines, and the entities; and

a planner running on the processor that simulates execution of the workload to identify a cheapest and a fastest infrastructure for the workload.

2. The system of claim 1, wherein the application manager provides table names, amount of data, a number of records, and a number of tasks.

3. The system of claim 1, wherein the application manager further provides a MapReduce timeline includes filters to display map, reduce, failed, killed, and successful tasks.

4. The system of claim 1, wherein the application manager further provides a skew view that shows a distribution of time and size of map and reduce tasks to identify a skew.

5. The system of claim 1, wherein the workflow manager further provides a view into each workflow to provide a comparison graph showing duration, resources used, data processed, and number of applications across various instances of each workflow.

6. The system of claim 1, wherein the workflow manager further provides a duration breakdown showing how time is spent in stages and phases of each workflow.

7. The system of claim 1, further comprising:

an operations viewer running on the processor that shows how queues are being used at any point in time; and

a resource manager running on the processor that determines which queues are over-utilized and under-utilized.

8. The system of claim 1, further comprising a leaderboard that breaks down cluster usage by users, data, resources, and queues.

9. The system of claim 1, further comprising a data manager running on the processor that generates a top-N list to show which tables, columns, joins, and queries are used the most.

10. The system of claim 1, further comprising a pattern analyzer running on the processor that identifies important tables and columns in the workload.

11. The system of claim 1, wherein the application is one of a script application, a structured query language (SQL) application, a Not Only (NO) SQL application, a stream application, a search application, and an in-memory application.

12. The system of claim 1, wherein the system determines if the application is one or more of slow-running, failed, killed, unpredictable, and malfunctioning.

13. The system of claim 1, further comprising a service manager running on the processor provides a status of various services running on a big data platform.

14. The system of claim 1, further comprising an inefficiencies analyzer running on the processor that provides a list of applications that have caused inefficiencies such as resource wastage and inefficient join.