In Chapter 9 of the book Handbook of Healthcare System Scheduling, they present the M/M/1 tandem queue with the following diagram:
And they also mention that the mean sojourn time of the entire system is the sum of the mean sojourn times of Queue 1 and Queue 2. Since Queue 1 and Queue 2 have 1 server each (they are M/M/1 stations), I was wondering if the same property holds when Queue 1 and/or Queue 2 have multiple servers.