Skip to content
About
Main content
Model

The queueing wall (M/M/1)

For one server with random arrivals and random service times, the average response time.

Response time
average response time (waiting plus service)
Service time
the average service time
Utilization
fraction of time the server is busy = arrival rate × average service time

Recurring principle: Queues explode near full load

How it behaves

One input on the horizontal axis, the others held fixed.

Data table
Response time as utilization rises (S = 1)
Utilization ρResponse time R (× S)
01×
0.0121.01×
0.0251.03×
0.0371.04×
0.0491.05×
0.0611.07×
0.0741.08×
0.0861.09×
0.0981.11×
0.111.12×
0.1231.14×
0.1351.16×
0.1471.17×
0.1591.19×
0.1711.21×
0.1841.23×
0.1961.24×
0.2081.26×
0.2211.28×
0.2331.3×
0.2451.32×
0.2571.35×
0.2691.37×
0.2821.39×
0.2941.42×
0.3061.44×
0.3191.47×
0.3311.49×
0.3431.52×
0.3551.55×
0.3671.58×
0.381.61×
0.3921.64×
0.4041.68×
0.4161.71×
0.4291.75×
0.4411.79×
0.4531.83×
0.4661.87×
0.4781.91×
0.491.96×
0.5022.01×
0.5142.06×
0.5272.11×
0.5392.17×
0.5512.23×
0.5642.29×
0.5762.36×
0.5882.43×
0.62.5×
0.6132.58×
0.6252.66×
0.6372.75×
0.6492.85×
0.6612.95×
0.6743.07×
0.6863.18×
0.6983.31×
0.713.45×
0.7233.61×
0.7353.77×
0.7473.96×
0.7594.16×
0.7724.38×
0.7844.63×
0.7964.91×
0.8085.22×
0.8215.58×
0.8335.99×
0.8456.46×
0.8577.02×
0.877.68×
0.8828.47×
0.8949.46×
0.90610.7×
0.91912.3×
0.93114.5×
0.94317.6×
0.95622.5×
0.96831×
0.9850×

Worked examples, recomputed

Every number the mechanisms quote for this relationship is recomputed from it, so none of them disagrees with it.

Where it appears

Each mechanism states it in its own names. The general symbol each name stands for is shown with it.