Right now the load averages are non-scaled, which, unless the number of cores is known, is meaningless, as one cannot conclude if a node is "overloaded" without scaled data.
Description
Description
Event Timeline
Comment Actions
Or alternatively, upgrade diamond to include https://github.com/python-diamond/Diamond/pull/366
Comment Actions
Hmm, this will add an extra metric for all hosts, prod and labs. @fgiunchedi is that ok?