Very High CPU Usage on Search Head, Dashboards and Searches Are very Slow.

Available Languages

Updated:September 28, 2026

Document ID:SPLK044562

Bias-Free Language

The documentation set for this product strives to use bias-free language. For the purposes of this documentation set, bias-free is defined as language that does not imply discrimination based on age, disability, gender, racial identity, ethnic identity, sexual orientation, socioeconomic status, and intersectionality. Exceptions may be present in the documentation due to language that is hardcoded in the user interfaces of the product software, language used based on RFP documentation, or language that is used by a referenced third-party product. Learn more about how Cisco is using Inclusive Language.

Applicability

Splunk Enterprise

Investigation

How to identify :

a. This issue was specifically seen after upgrading Splunk, but this can also occur in other circumstances as well.

b. In the splunkd logs you may see the following warning reported:

WARN DispatchManager - quota enforcement for user=shtabti, sid=hdjshf__slwods__search__search16_1575354423.1191, elapsed_ms=36268, 
cache_size=10000 took longer than 15 seconds. Poor search start performance will be observed. Consider removing some old search job artifacts.

c. Also Flame Graphs from multiple pstacks against splunkd captured during the issue highlights a lot of time in dispatch management and quota enforcement routines.

Resolution

Cause:

Issue is caused by a large number of old search job artefacts under var/run/splunk/dispatch.

Fix:

Remove old search job artefacts on the search head by cleaning up the dispatch directory (var/run/splunk/dispatch) using the splunk clean-dispatch command to improve performance.

See the following documents for details on how to clean up the dispatch directory and how to manage the size of the dispatch directory in future :

Clean up the dispatch directory based on the age of directories

Search artifact lifetime in the dispatch directory