Data Fabric Search (DFS) is the next generation of Splunk’s search platform. DFS executes the following vision: Splunk should be able to leverage compute assets from anywhere and access and execute on data regardless of type and origin. Inspired by the above mantra DFS scales Splunk searches both in terms of volume and cardinality. In this session you will learn how DFS searches scale to trillion scale event volume or billion scale cardinality - capabilities previously impossible. DFS is not limited to local but by supporting scaled federated executions also powers remote splunk deployments. The Search Pipeline of DFS has been build grounds up based on lambda architecture which provides massive scale, high throughput and performance gains. At the end some of the performance and scale numbers which has been achieved internally will be shared.

Speaker(s)
Ari Bhattacharjee, Distinguished Engineer, Splunk
Sourav Pal, Senior Principal Engineer, Splunk

Slides PDF link - https://conf.splunk.com/files/2019/slides/FN2124.pdf?podcast=1577146201

Product: Splunk Enterprise

Track: Foundations/Platform

Level: Good for all skill levels