Latency Breakdown Explorer
Try Change Queuing delay (ms) from 10 to 200.
Observe Compare Illustrative baseline RTT and Dominant component with queuing delay at 10 and 200 ms.
Explain Explain why queuing delay at 200 ms dominates the illustrative baseline RTT.
Calculate in panel
Reset
Technical boundaries. The explorer adds propagation, processing, and queuing delays for one illustrative RTT. The assumed range adds and subtracts the selected jitter, with a minimum of zero.
Run it: The explorer below splits one RTT into propagation, processing, and queuing; the edge-fog latency simulator underneath shows how moving that processing changes the total. Pick a Network Profile such as Cellular WAN or Congested and a Workload, then switch the Focus Tier between Edge, Fog, and Cloud and read the Request-Response Timeline and Latency Results. That makes this lab’s “local edge processing” remedy concrete: the same job that misses a control deadline over the WAN can meet it when the compute sits at the edge.
viewof propagation_ms = Inputs. range ([1 , 200 ], {value : 25 , step : 1 , label : "Propagation delay (ms)" })
viewof processing_ms = Inputs. range ([0 , 50 ], {value : 5 , step : 1 , label : "Processing delay (ms)" })
viewof queuing_ms = Inputs. range ([0 , 500 ], {value : 10 , step : 1 , label : "Queuing delay (ms)" })
viewof jitter_ms = Inputs. range ([0 , 100 ], {value : 15 , step : 1 , label : "Jitter +/- (ms)" })
total_rtt = propagation_ms + processing_ms + queuing_ms
max_rtt = total_rtt + jitter_ms
min_rtt = Math . max (0 , total_rtt - jitter_ms)
latency_rating = total_rtt < 50 ? "Typically excellent" : total_rtt < 150 ? "Typically good" : total_rtt < 300 ? "Typically acceptable" : "Typically poor"
rating_color = total_rtt < 50 ? "#16A085" : total_rtt < 150 ? "#3498DB" : total_rtt < 300 ? "#E67E22" : "#E74C3C"
bar_max = 500
prop_width = (propagation_ms / bar_max * 100 ). toFixed (1 )
proc_width = (processing_ms / bar_max * 100 ). toFixed (1 )
queue_width = (queuing_ms / bar_max * 100 ). toFixed (1 )
html `<div style="background: #f8f9fa; border-left: 3px solid #3498DB; padding: 1em; border-radius: 4px; margin-top: 0.5em;">
<h4 style="margin-top:0;">RTT Breakdown</h4>
<div style="display: flex; height: 30px; border-radius: 4px; overflow: hidden; margin-bottom: 0.5em;">
<div style="background: #2C3E50; width: ${ prop_width} %; color: white; font-size: 11px; display: flex; align-items: center; justify-content: center;"> ${ propagation_ms > 15 ? propagation_ms + 'ms prop' : '' } </div>
<div style="background: #16A085; width: ${ proc_width} %; color: white; font-size: 11px; display: flex; align-items: center; justify-content: center;"> ${ processing_ms > 5 ? processing_ms + 'ms proc' : '' } </div>
<div style="background: #E67E22; width: ${ queue_width} %; color: white; font-size: 11px; display: flex; align-items: center; justify-content: center;"> ${ queuing_ms > 10 ? queuing_ms + 'ms queue' : '' } </div>
</div>
<table style="width:100%; border-collapse: collapse; font-size: 0.95em;">
<tr><th scope="col" style="text-align:left; padding: 3px 8px;">Latency quantity</th><th scope="col" style="text-align:left; padding: 3px 8px;">Value</th></tr>
<tr><td style="padding: 3px 8px;"><strong>Illustrative baseline RTT</strong></td><td style="padding: 3px 8px;"> ${ total_rtt} ms</td></tr>
<tr><td style="padding: 3px 8px;"><strong>Assumed RTT range</strong></td><td style="padding: 3px 8px;"> ${ min_rtt} ms - ${ max_rtt} ms</td></tr>
<tr><td style="padding: 3px 8px;"><strong>Dominant component</strong></td><td style="padding: 3px 8px;"> ${ propagation_ms >= processing_ms && propagation_ms >= queuing_ms ? 'Propagation' : queuing_ms >= processing_ms ? 'Queuing' : 'Processing' } delay</td></tr>
<tr style="border-top: 1px solid #ccc;"><td style="padding: 3px 8px;"><strong>Rating for interactive IoT</strong></td><td style="padding: 3px 8px; color: ${ rating_color} ; font-weight: bold;"> ${ latency_rating} ( ${ total_rtt} ms)</td></tr>
</table>
<p style="margin: 0.5em 0 0 0; font-size: 0.85em; color: #666;">Set queuing delay to 200+ ms to see how congestion dominates total latency, regardless of link speed.</p>
</div>`
Back to the chapter