- Mark as New
- Bookmark Message
- Subscribe to Message
- Mute Message
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Is saturation level fine as a preparation for additional HEC data stream?
For our indexers, we see the following under 'Storage I/O Saturation (Mount Point)' -
0.90% (/opt/splunk) 6.56% (/indexing/splunk_cold)
We have 14 indexers with roughly the same saturation levels and I wonder if it's healthy.
We would like to direct the HEC data straight to the indexers (instead of going through the HFs) and therefore I wonder if at the I/O level we are ready.
- Mark as New
- Bookmark Message
- Subscribe to Message
- Mute Message
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content

Hi @danielbb
Receiving cooked data from a HF or receiving HEC shouldnt have much impact on the I/O saturation of your disks because Splunk will still write the same amount of data to disk if sent either way. The parsing of HEC data that will be done on your indexers instead of HF may use more CPU/Memory but I do not think disk IO should be affected.
Please let me know how you get on and consider adding karma to this or any other answer if it has helped.
Regards
Will
