I'm testing for feasibility of influxdb performance.
DB schema as following.
Measurements : 100
Series : 30M with one Tag and five fields.
Traffic generation : 30K write points data per second with wrk2 HTTP load
Used influxdb default configuration but max cache memory was 50G.
32 Cores CPU, 512G physical memory, 2T SSD disk
As you can see the attachment, InfluxDB shard size shows big saw teeth,
looks like fully compaction every 7~8 hour.
I hope that I can make it smaller it. *Is it configurable?*
Actually it seems affect write and query blocking because InfluxDB perform
any compaction after that Go routines is increased up to 20 times,
at that time the 'PointReq' is 0 for long time up to 15 Min.
Thank you in advance
Remember to include the InfluxDB version number with all issue reports
You received this message because you are subscribed to the Google Groups
To unsubscribe from this group and stop receiving emails from it, send an email
To post to this group, send email to email@example.com.
Visit this group at https://groups.google.com/group/influxdb.
To view this discussion on the web visit
For more options, visit https://groups.google.com/d/optout.