diff options
Diffstat (limited to 'src/health/health.d/tcp_resets.conf')
| -rw-r--r-- | src/health/health.d/tcp_resets.conf | 66 |
1 files changed, 66 insertions, 0 deletions
diff --git a/src/health/health.d/tcp_resets.conf b/src/health/health.d/tcp_resets.conf new file mode 100644 index 000000000..63f798d78 --- /dev/null +++ b/src/health/health.d/tcp_resets.conf @@ -0,0 +1,66 @@ +# you can disable an alarm notification by setting the 'to' line to: silent + +# ----------------------------------------------------------------------------- +# tcp resets this host sends + + alarm: 1m_ip_tcp_resets_sent + on: ip.tcphandshake + class: Errors + type: System + component: Network +host labels: _os=linux + lookup: average -1m at -10s unaligned absolute of OutRsts + units: tcp resets/s + every: 10s + info: average number of sent TCP RESETS over the last minute + + alarm: 10s_ip_tcp_resets_sent + on: ip.tcphandshake + class: Errors + type: System + component: Network +host labels: _os=linux + lookup: average -10s unaligned absolute of OutRsts + units: tcp resets/s + every: 10s + warn: $netdata.uptime.uptime > (1 * 60) AND $this > ((($1m_ip_tcp_resets_sent < 5)?(5):($1m_ip_tcp_resets_sent)) * (($status >= $WARNING) ? (1) : (10))) + delay: up 20s down 60m multiplier 1.2 max 2h + options: no-clear-notification + summary: System TCP outbound resets + info: Average number of sent TCP RESETS over the last 10 seconds. \ + This can indicate a port scan, \ + or that a service running on this host has crashed. \ + Netdata will not send a clear notification for this alarm. + to: silent + +# ----------------------------------------------------------------------------- +# tcp resets this host receives + + alarm: 1m_ip_tcp_resets_received + on: ip.tcphandshake + class: Errors + type: System + component: Network +host labels: _os=linux freebsd + lookup: average -1m at -10s unaligned absolute of AttemptFails + units: tcp resets/s + every: 10s + info: average number of received TCP RESETS over the last minute + + alarm: 10s_ip_tcp_resets_received + on: ip.tcphandshake + class: Errors + type: System + component: Network +host labels: _os=linux freebsd + lookup: average -10s unaligned absolute of AttemptFails + units: tcp resets/s + every: 10s + warn: $netdata.uptime.uptime > (1 * 60) AND $this > ((($1m_ip_tcp_resets_received < 5)?(5):($1m_ip_tcp_resets_received)) * (($status >= $WARNING) ? (1) : (10))) + delay: up 20s down 60m multiplier 1.2 max 2h + options: no-clear-notification + summary: System TCP inbound resets + info: average number of received TCP RESETS over the last 10 seconds. \ + This can be an indication that a service this host needs has crashed. \ + Netdata will not send a clear notification for this alarm. + to: silent |