Finding extra datapoints not present in the traces

I am wondering if there is any way to get the following data (I did not find these readily available in the 2021 traces):
* All the utilization metrics (CPU and memory) at the node level and container level are relative values (percentages of total capacity). Is there a way to get the absolute values of these metrics (eg: the actual amount of CPU used vs allotted value)?
* Can we find the data on scheduling decisions made? (eg: resources requested by a microservice vs resources allotted)
* Can we find the actual capacities of various machines on the cluster? (eg: CPU size and memory capacity of individual machines)
* Can we find similar traces for offline jobs on these machines in the same timeframe?

Start with the 2021 traces and any repository documentation that defines their available fields. Check each requested category—absolute utilization, scheduling decisions, machine capacities, and offline jobs—and document where the data is present or explicitly unavailable. Done means providing a source or clear answer for every bullet.

Written by the indexing model from the issue text.