Datacenter operations using search and analytics

Patent metadata

Field	Value
Publication number	US-10528628-B2
Application number	US-201715708745-A
Country	US
Kind code	B2
Filing date	Sep 19, 2017
Priority date	Aug 20, 2014
Publication date	Jan 7, 2020
Grant date	Jan 7, 2020

Abstract

A datacenter management system uses data collection proxies to collect performance data and configuration data for different physical and virtual entities in the datacenter. A schema is used to represent the different entities, entity relationships, and entity properties in the datacenter. A search engine identifies the intent of a natural language based search query based on the schema and a datacenter dictionary. The search engine then searches the data based on the search query intent. A dictionary manager converts both periodic and aperiodic data into a time series. This allows the search engine to operate as a time machine identifying both performance data and configuration data for any selectable time period.

First claim

The invention claimed is:

1. A method, comprising:
receiving, by a computing device, a natural language based search query for information associated with managing operation of a datacenter;
performing, by the computing device, a predicate pushdown of the natural language based search query to access hierarchal relationships of physical entities and hierarchal relationships of virtual entities relevant to the natural language based search query;
performing a natural language based search, by the computing device, of data pertaining to operation of the data center based on the predicate pushdown; and
generating, by the computing device, results of the search other than results from a keyword based search.

2. The method of claim 1 , wherein performing the predicate pushdown comprises converting a join into a union.

3. The method of claim 2 , wherein converting the join into the union includes combining a plurality of parsers in response to the natural language based search query comprising a compound query.

4. The method of claim 3 , wherein performing the predicate pushdown includes pushing down a disjunction that is part of the compound query.

5. The method of claim 4 , wherein performing the predicate pushdown includes pushing down the disjunction in response to the compound query joining two tables having a same primary key.

6. The method of claim 1 , further comprising running persistent queries for creating alerts.

7. The method of claim 1 , further comprising converting configuration data and performance data associated with aperiodic events of the physical entities and the virtual entities into a time series; and
wherein performing the natural language based search comprises computing a predicate on the time series and a scalar.

8. The method of claim 7 , further comprising combining the configuration data and the performance data associated with the aperiodic events with configuration data and performance data associated with periodic events.

9. An apparatus, comprising:
a processing device configured to:
receive a natural language based search query for information associated with managing operation of a datacenter;
perform a predicate pushdown of the natural language based search query to access hierarchal relationships of physical entities and hierarchal relationships of virtual entities relevant to the natural language based search query;
perform a natural language based search of data pertaining to operation of the data center based on the predicate pushdown; and
generate results of the search other than results from a keyword based search.

10. The apparatus of claim 9 , wherein the processing device is further configured to identify and display events associated with the natural language based search query that occurred after the generation of results in response to a user login for a same user that sent the natural language based search query.

11. The apparatus of claim 9 , wherein the processing resource is further configured to provide suggestions while receiving the natural language based search query based on a datacenter library that includes names of the physical entities and the virtual entities.

12. The apparatus of claim 11 , wherein the processing resource is further configured to:
store the natural language based search query and the results as a search history;
weight the search history based on frequency of requests for the physical entities and the virtual entities; and
provide suggestions for a subsequent search query based on the datacenter library and the weighted search history.

13. The apparatus of claim 9 , wherein the processing resource is further configured to:
provide a visualization of a topology for a network configured in the datacenter;
display a series of layers representing at least one of the physical entities and the virtual entities associated with the network; and
highlight a logical entity in the display based on the search results.

14. The apparatus of claim 13 , wherein the processing resource is further configured to receive a selection of two different virtual entities from the display and, in response, display a logical and physical network topology containing the two selected virtual entities.

15. The apparatus of claim 13 , wherein the processing resource is further configured to:
display a slider associated with the topology; and
receive a user input to the slider and, in response, provide a visualization of the topology for a different time period.

16. A non-transitory machine-readable medium storing instructions executable by a processing device to:
receive a natural language based search query for information associated with managing operation of a datacenter;
perform a predicate pushdown of the natural language based search query to access hierarchal relationships of physical entities and hierarchal relationships of virtual entities relevant to the natural language based search query;
perform a natural language based search of data pertaining to operation of the data center based on the predicate pushdown; and
generate results of the search other than results from a keyword based search.

17. The medium of claim 16 , further including instructions to display a representation of the hierarchal relationships of physical entities and the hierarchal relationships of virtual entities relevant to the natural language based search query as an object relational graph.

18. The medium of claim 17 , further including instructions to use the object relational graph to identify the hierarchal relationships of physical entities and the hierarchal relationships of virtual entities.

19. The medium of claim 18 , further including instructions to map a plurality of vendor models to a plurality of data models comprising the object relational graph.

20. The medium of claim 19 , wherein the plurality of data models include:
entity data models that each include performance and configuration data for a respective one of the physical entities or the virtual entities;
relationship data models that each bind respective entity data models together; and
graph data models that identify logical relationships between respective physical entities and virtual entities.

Assignees

• Vmware Inc

Inventors

• Agarwal Shiv
• Gupta Apurv
• Gupta Mukul
• Sharma Abhijit
• Toshniwal Rohit

Classifications

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title