Splunk® Machine Learning Toolkit

User Guide

Acrobat logo Download manual as PDF


Acrobat logo Download topic as PDF

Deep dive: Using ML to detect outliers in server response time

The goal of this deep dive is to identify periods of time where web applications have unusually slow response times.

Slow website response times can be damaging to customer experience, driving users to other services and potentially damaging your brand.

Data sources

The following data sources are suitable for this deep dive:

  • Any tomcat:access:log logs

Algorithms

For best results, use the DensityFunction algorithm.

As an alternative approach, try stats or the DBSCAN algorithm.

Train the model

Before you begin training the model, do the following things:

  • Change the index, source type, and response_time metric type to identify errors for your environment.
  • You must pick a search window that has enough data to be representative of your environment. Search over 30 days at a minimum for this analytic. The more data the better.

Enter the following search into the search bar of the app you where want the analytic in production:

index=tomcat_logs sourcetype="tomcat:access:log" 
| timechart span=5m avg(response_time) as avg_resp_time 
| eval HourOfDay=strftime(_time,"%H") 
| fit DensityFunction avg_resp_time by HourOfDay as outlier into response_time_outlier_model

This search counts the response time over 5 minute time intervals, enriches the data with the hour of day, and then trains an anomaly detection model to detect unusual response times by the hour of day.

After you run this search and are confident that it is generating results, save it as a report and schedule the report to periodically retrain the model. As a best practice, train the model every week. Schedule training for a time when your Splunk platform instance has low utilization.

Model training with MLTK can use a high volume of resources.

After training the model you can select Settings in the top menu bar, then select Lookups, then select Lookup table files. and search for your trained model.

This image shows the pathway in an example Splunk system to reach the Lookup table files. From the top navigation bar the Settings menu is open and the Lookups option is highlighted. Selecting Lookups opens the page from which you can create and configure lookups. On this screen the Lookup table files option is highlighted.

Make sure that the permissions for the model are correct. By default, models are private to the user who has trained them, but since you have used the app: prefix in your search, the model is visible to all users who have access to the app the model was trained in.

Apply the model

Now that you have set up the model training cycle and have an accessible model, you can start applying the model to data as it is coming into the Splunk platform. Use the following search to apply the model to data:

index=tomcat_logs sourcetype="tomcat:access:log" 
| timechart span=5m avg(response_time) as avg_resp_time 
| eval HourOfDay=strftime(_time,"%H") 
| apply response_time_outlier_model

This search can be used to populate a dashboard panel or can be used to generate an alert.

When looking to flag outliers as alerts, you can append | search outlier=1 to our search, which will filter your results to show only those that have been identified as outliers. This search can then be saved as an alert that triggers when the number of results is greater than 0, which can be run on a scheduled basis such as hourly.

Tune the model

When training and applying your model, you might find that the number of outliers being identified is not proportionate to the data: that the model is either flagging too many or too few outliers. The DensityFunction algorithm has a number of parameters that can be tuned to your data, creating a more manageable set of alerts.

The DensityFunction algorithm has a threshold option that is set at 0.01 by default, which means it will identify the least likely 1% of the data as an outlier. This threshold can be configured as the apply stage, so it can be increased or decreased depending on the tolerance for outliers, as shown in the following search:

index=tomcat_logs sourcetype="tomcat:access:log" 
| timechart span=5m avg(response_time) as avg_resp_time 
| eval HourOfDay=strftime(_time,"%H") 
| apply response_time_outlier_model threshold=0.005 
| search outlier=1

Additional fields can also be extracted and used during the fit and apply stages. For example, if your data has hourly and daily variance, such as significantly more errors during working hours on a weekday, you can include the hour of the day and the day of the week in the by clause to more finely tune your model to your data, as shown in the following search:

index=tomcat_logs sourcetype="tomcat:access:log" 
| timechart span=5m avg(response_time) as avg_resp_time 
| eval HourOfDay=strftime(_time,"%H"), DayOfWeek=strftime(_time,"%a") 
| fit DensityFunction avg_resp_time by "HourOfDay,DayOfWeek" into app:response_time_outlier_model

Make sure that all additional fields that are used for training your model are also included in your model apply search.

Common questions when running this deep dive

Can I use this approach to find outliers in server response time from other data sources?

The timechart, eval, and fit and apply stages of the search can run against other data sources with relative ease. You must provide the base search to find outliers in other log types.

Can I use a host or app name field in the DensityFunction model training by clause?

While the host or even user fields might provide an added layer of granularity to your searches by creating baselines at an entity level, they can quickly increase the processing time and requirements for DensityFunction. Typically if there are more than 1000 different combinations of elements in the by clause, DensityFunction is not the best approach. You can take an alternative approach using stats and lookups. There is a great example of this approach from IG Group at .conf21 on how to handle high cardinality data. See, Anomaly Detection, Sealed with a KISS.

Calculating a 5 minute aggregate is taking a long time to compute. Is there anything I can do?

Although you are aggregating over 5 minute time spans for the search here, you might find that your search performs better if you look at larger time frame aggregates, such as hourly.

I'm finding too many outliers in my data. What can I do?

See the Tune the model section. In particular, look at how the threshold option can be used to tune the detection sensitivity.

I don't understand how DensityFunction is identifying outliers. How can I find out more about what the algorithm is doing with my data?

You can use the summary command for information about the models generated using DensityFunction. You can see the distribution type the model has mapped your data to, some statistics about the data distribution, and a cardinality field that tells you how many records have been used to train the model. A couple of key metrics to investigate are the cardinality and the Wasserstein distance metric. For cardinality, the higher this number is the better. For the Wasserstein distance metric, which tells you how closely the probability distribution matches your actual data, the lower the number the better.

Are there any gotchas I need to know about?

There are occasions when DensityFunction incorrectly identifies outliers when data is mapped to the beta distribution with certain parameters, for example, alpha=beta=0.5. In this scenario you need to ignore results from DensityFunction and select the distribution type when fitting the model, rather than letting it run in auto as it does by default. For example, by setting dist_type=normal in the fit search.

Learn more

See the following Splunk blog posts on outlier detection:

To learn about implementing analytics and data science projects using Splunk platform statistics, machine learning, and built-in and custom visualization capabilities, see Splunk for Analytics and Data Science.

Last modified on 17 June, 2022
PREVIOUS
Deep dive: Using ML to detect outliers in error message rates
  NEXT
Deep dive: Using ML to identify network traffic anomalies

This documentation applies to the following versions of Splunk® Machine Learning Toolkit: 4.5.0, 5.0.0, 5.1.0, 5.2.0, 5.2.1, 5.2.2, 5.3.0, 5.3.1


Was this documentation topic helpful?


You must be logged into splunk.com in order to post comments. Log in now.

Please try to keep this discussion focused on the content covered in this documentation topic. If you have a more general question about Splunk functionality or are experiencing a difficulty with Splunk, consider posting a question to Splunkbase Answers.

0 out of 1000 Characters