Measurement point: Stealth NYC, 32 Avenue of the Americas.
Published investigation. Updates run automatically.
01 / Network path
Network path.
Endpoint measurements / ICMP IPv4
Latency over time.
Successful endpoint RTT recordings from up to one hour before the event.
Enter time range
Times use the selected timezone; choices include recorded samples and intervals across the available chart.
Successful RTT recording Event interval
09 Nov 2026 19:55 – 09 Nov 2026 21:34 UTC. Hover or tap to inspect; drag across the chart to zoom. On touchscreens, first choose Select time range. Escape or Reset zoom restores the full range. Missing recordings are gaps; this is not an application availability or packet-loss chart.
Select a recording to explore nearby path observations.
View recorded values
Successful ICMP IPv4 RTT recordings.
Recorded at (UTC)
RTT
1.613 ms
1.150 ms
1.580 ms
1.162 ms
1.579 ms
12.197 ms
1.160 ms
1.599 ms
1.696 ms
1.570 ms
1.591 ms
1.571 ms
1.632 ms
1.244 ms
1.621 ms
1.119 ms
1.572 ms
1.162 ms
1.690 ms
1.331 ms
1.587 ms
1.128 ms
1.169 ms
1.618 ms
1.548 ms
1.575 ms
1.146 ms
1.563 ms
1.591 ms
1.138 ms
1.155 ms
1.641 ms
1.162 ms
1.596 ms
1.585 ms
1.401 ms
1.664 ms
1.672 ms
19.235 ms
1.148 ms
1.165 ms
1.571 ms
1.574 ms
1.154 ms
1.166 ms
1.174 ms
1.637 ms
1.630 ms
1.140 ms
1.184 ms
1.160 ms
1.134 ms
1.671 ms
1.148 ms
1.117 ms
1.674 ms
1.616 ms
1.614 ms
1.119 ms
1.692 ms
1.149 ms
1.167 ms
1.667 ms
1.163 ms
1.186 ms
1.588 ms
4.609 ms
1.618 ms
1.582 ms
1.145 ms
1.601 ms
1.593 ms
1.157 ms
1.608 ms
1.611 ms
1.151 ms
1.585 ms
1.598 ms
1.175 ms
1.156 ms
1.659 ms
1.660 ms
1.579 ms
1.137 ms
1.142 ms
1.604 ms
11.531 ms
1.593 ms
1.595 ms
6.259 ms
1.638 ms
1.166 ms
1.742 ms
1.124 ms
1.555 ms
1.605 ms
1.597 ms
1.161 ms
1.607 ms
1.698 ms
1.167 ms
2.665 ms
1.161 ms
1.595 ms
1.242 ms
1.610 ms
1.228 ms
1.576 ms
1.650 ms
1.592 ms
1.130 ms
1.696 ms
1.609 ms
1.613 ms
1.139 ms
1.135 ms
1.563 ms
1.124 ms
1.625 ms
1.623 ms
13.535 ms
1.128 ms
1.643 ms
1.570 ms
1.554 ms
1.587 ms
1.170 ms
1.146 ms
1.130 ms
1.730 ms
1.573 ms
7.865 ms
1.145 ms
1.591 ms
1.632 ms
1.637 ms
1.576 ms
1.584 ms
1.170 ms
2.507 ms
6.515 ms
1.655 ms
1.606 ms
18.964 ms
1.586 ms
1.144 ms
1.157 ms
1.605 ms
1.594 ms
1.190 ms
1.692 ms
1.574 ms
1.625 ms
1.125 ms
1.161 ms
1.607 ms
1.140 ms
1.261 ms
1.143 ms
1.138 ms
1.600 ms
1.219 ms
1.594 ms
1.577 ms
1.172 ms
1.585 ms
1.208 ms
6.415 ms
1.122 ms
1.573 ms
1.118 ms
1.295 ms
1.585 ms
1.176 ms
1.663 ms
1.141 ms
1.205 ms
1.171 ms
1.158 ms
2.004 ms
1.563 ms
1.145 ms
1.589 ms
1.146 ms
1.563 ms
1.649 ms
1.887 ms
1.138 ms
1.136 ms
1.597 ms
1.154 ms
1.591 ms
1.567 ms
9.573 ms
1.114 ms
1.180 ms
1.585 ms
1.130 ms
1.749 ms
1.605 ms
Network path / recorded observations
Network path observations.
15 observations
Choose a measurement type to see the closest of the available sampled observations to the selected chart point. Each probe is separate and may follow a different path.
Before
ICMP traceroute · Recorded address 1
Recorded trace · destination not reached by this trace
RTT is the round trip to each responding hop, not the delay of the preceding link. TTL order may omit routers and does not prove direct links. A missing reply is not proof of packet loss. ASN labels are dated address associations; they do not establish the forwarding path or the operator at the event time. Up to three recorded traces per method and period are selected across the archive. Where no individual trace is available, a comparison may summarize a window; MTR observations aggregate multiple probes. Address aliases are independent across measurement types.
Same method / same recorded address
Compare the traces.
Compare one selected trace from before the event with one during it. Values are individual replies, not a statistical comparison.
ICMP traceroute · Recorded address 1
Before: UTC · During: UTC
Same destination address and probe method. A matching TTL does not establish the same forwarding path.
TTL
Before RTT
During RTT
Responding address
1
0.121 msAS8002 · Stealth
0.135 msAS8002 · Stealth
Same responder
2
0.192 msAS8002 · Stealth
0.183 msAS8002 · Stealth
Same responder
3
3.666 msAS13335 · Cloudflare
0.664 ms
Same responder
TCP traceroute / 443 · Recorded address 1
Before: UTC · During: UTC
Same destination address and probe method. A matching TTL does not establish the same forwarding path.
TTL
Before RTT
During RTT
Responding address
1
0.138 msAS8002 · Stealth
0.163 msAS8002 · Stealth
Same responder
2
0.201 msAS8002 · Stealth
0.208 msAS8002 · Stealth
Same responder
3
4.196 ms
11.460 msAS13335 · Cloudflare
Same responder
4
No reply
No reply
Not established
5
2.394 msAS13335 · Cloudflare
1.506 msAS13335 · Cloudflare
Same responder
6
1.350 msAS13335 · Cloudflare
1.354 msAS13335 · Cloudflare
Same responder
RTTs include the return path. Different responders, missing replies and independent probe flows limit what a change can localize. MTR snapshots remain separate in the replay.
Event timeline.
Latency anomaly. Times shown are UTC.
Event opened
UTC
Last event observation
UTC
02 / Assessment
Assessment.
Investigation stateInvestigating
Path assessment
Elevated latency observed.
Endpoint round-trip time was elevated during part of the event. The available path observations do not identify where the increase occurred.
What we observed
A sustained increase in measured round trip time was observed.
Recording counts describe collected measurements, not application availability or packet loss. Exact packet paths and the return path remain unverified.
Measurements at a glance.
Baseline RTT1.564 msUsual round trip before the event
Last recorded event RTT1.605 msLast successful event recording
Event p95 RTT6.583 ms95th percentile of successful recordings
Change from baseline+0.041 msLast event RTT compared with the baseline
Successful / expected recordings80 / 80Recorded endpoint samples during the event
RTT is round trip time; p95 describes the upper range of successful recordings. Endpoint measurements differ from individual trace replies and are not an uptime percentage.
Record sources and timestamps
Analysis updated
Unavailable
Public snapshot published
UTC
Public observation window
– UTC
Event and source timestamps are UTC. The latency chart uses its selected timezone. Page refresh times are separate from measurement timestamps.
03 / Method and limits
Method and limits.
How to interpret the sampled path and its limits
Corroborating the path.
Comparisons use matching destinations before and during the event. ICMP traces use echo probes. TCP/443 traces send SYN probes to port 443 only; they do not complete a TCP handshake or perform a TLS or HTTP exchange.
The Stealth gNMI interface verifies the active route-table choice and maps its primary next hop to the Stealth logical interface, configured attachment and, where applicable, the known LAG member set at each snapshot. Stable Stealth replies, together with mapped interface evidence showing no corresponding errors or sustained capacity pressure, reduce the likelihood of a Stealth forwarding issue. An 80% load warning warrants investigation; it does not prove congestion. Lower interval averages can conceal bursts or queue pressure. Optical readings assess the physical link, not congestion.
What remains unseen.
Probe reply handling can differ from packet forwarding. A slow intermediate reply that disappears at later hops does not locate a forwarding problem. A destination that does not respond to a trace is not thereby shown to be unavailable.
Stealth does not use ECMP in this monitored scope. The route snapshot does not identify which physical LAG member carried a particular independent probe, attest line-card forwarding at that packet instant, prove the exact application packet flow or observe the return path. RTT includes the return path, which may differ. No remote reverse traceroute is available. Tunnels and silent routers may hide parts of the path. Address registration alone does not establish the forwarding operator or responsibility.