YARN Resource Manager has a configuration that prevents you from launching jobs when the data node is around 90-95% full. So that is the first level of error you will see. At the HDFS level, you will error since block allocations and writes would fail.
If you have Amabari, then Ambari will be firing alerts much before you reach 100%. I don't think HDFS will fire alerts, instead, you will see failures at the HDFS level.