In February the Cluster had a couple of downtimes since the build of the 19″ Pi rack has begun. As you may have heard I gifted myself a Prusa Mini+ 3D Printer in order to „print“ a special 19″ case. Since I had to modify the uplap.pro design for my Waveshare PoE HATs the downtimes where needed for prototyping and measurements of the parts I printed.
The cluster still consists of 4 Raspberry Pi 4 (8GB RAM models) running Raspberry Pi OS 64 Bit Beta. K3S is running in version V1.20.2. Pods are running BOINC client version 7.16.11. The BOINC Cluster is volunteering for Rosetta@Home, Einstein@Home, LHC@Home. Computing preferences for all Projects are identical (use 100% of available CPUs, 90% of available CPU Time, 100% of available RAM). Resource Share for the Projects are: Rosetta@Home 35%, Einstein@Home 35%, LHC@Home 25%.
I summarized the finished tasks from 01.02.2021 to 28.02.2021. Aborted tasks or tasks with runtime 0:00 have been removed from this analysis. Statistics have been collected with BoincTasks and summarized in Excel. 1422 Tasks have been completed in total. Results:
Project | Application | Tasks done | Avg (h) | Min (h) | Max (h) |
Einstein@Home | einsteinbinary_BRP4 | 974 | 2,33 | 1,77 | 2,85 |
Rosetta@Home | Rosetta | 260 | 7,93 | 2,26 | 9,33 |
LHC@Home | SixTrack | 188 | 7,41 | 0,00 | 19,56 |
I started to fiddle around with different resource assignments for the BOINC pods but I was still not able to customize a pod setup to run 4 CPU and 4 boinc tasks in parallel. Basically this works not from scratch since the monitoring suite with Prometheus and also the K3S system have reserved some resources for themselves. I might continue to find a descent resource customizing here.