B4L/cnx-network-clan
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add gateway diagnostics: iperf3, CLI toolkit, periodic WAN speed test

Browse Source 
iperf3 serves throughput tests from every VLAN and the mesh; an hourly
librespeed run feeds speedtest_* metrics through node_exporter's textfile
collector, and vmalert flags download rates below half the link's own
7-day median so ISP degradation surfaces without per-site thresholds.
This commit is contained in:
Berwn
2026-07-31 10:44:52 +07:00
parent b11ff75ca6
commit d8d4a686eb
5 changed files with 142 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/monitoring/alerts.nix
+25
View File
@@ -59,6 +59,31 @@ in
}
];
}
{
# WAN quality on the site gateways, fed by the hourly speedtest timer
# (modules/router/speedtest.nix) via the node_exporter textfile
# collector. Degradation is judged against the link's own 7-day median,
# so no per-site/per-ISP-plan threshold needs maintaining.
name = "wan";
rules = [
{
alert = "WANSpeedDegraded";
expr = "speedtest_download_mbps < 0.5 * quantile_over_time(0.5, speedtest_download_mbps[7d])";
for = "3h";
labels.severity = "warning";
annotations.summary = "WAN download on {{ $labels.instance }} is below half its 7-day median";
annotations.description = "Sustained for 3h (several test runs) — likely ISP degradation, line fault, or saturation. Compare speedtest_upload_mbps/speedtest_ping_ms and run `librespeed-cli` manually on the gateway.";
}
{
alert = "WANSpeedTestFailing";
expr = "speedtest_success == 0";
for = "3h";
labels.severity = "warning";
annotations.summary = "Speed tests on {{ $labels.instance }} have been failing for 3h";
annotations.description = "librespeed-cli cannot complete a test while other traffic may still flow; check `journalctl -u speedtest` on the gateway.";
}
];
}
{
name = "backup";
rules = [