Install the ML-SPL Performance App
Machine learning requires compute resources and disk space. Each algorithm has a different performance cost, which can be complicated by the number of input fields you select and the total number of events processed. Model files are lookups and do increase bundle replication costs.
For each algorithm implemented in ML-SPL, run time, CPU utilization, memory utilization, and disk activity are measured when fitting models on up to 1,000,000 search results, and applying models on up to 10,000,000 search results, each with up to 50 fields.
Through the Settings tab of the MLTK, users with admin access can configure the settings of the
apply commands. Changes can be made across all algorithms, or for an individual algorithm.
For more information, see Configure algorithm performance costs.
The ML-SPL Performance App for the Machine Learning Toolkit enables users to:
- Ensure you know the impact of making changes to the default performance cost Settings.
- Access performance results for guidance purposes.
- Access performance results for bench-marking purposes.
To learn more about this add-on and to download, see Splunkbase for the ML-SPL Performance App for the Machine Learning Toolkit.
Install the Machine Learning Toolkit
Install the GitHub for Machine Learning App
This documentation applies to the following versions of Splunk® Machine Learning Toolkit: 4.4.0, 4.4.1, 4.4.2, 5.0.0