DEPOT logging: add Telemt fleet monitoring via Zabbix

Install and persist Grafana Zabbix plugin 6.5.0, provision the internal Zabbix datasource, and add a fleet dashboard modeled on client 02 Telemt panels. Add an active-agent Zabbix 7 template plus a 30-second sanitized collector for active IP count/list, connections, traffic, and uptime. Active checks avoid inbound polling of client-private Docker hosts. The exact Zabbix host names and required ZABBIX_API_TOKEN Portainer variable are documented. Compose validation passed on 10.0.0.6; the live plugin registered successfully under Grafana 13.1.0.
2026-07-31 11:55:55 +03:00
parent 961f0112de
commit 1fb6899b1f
12 changed files with 1207 additions and 40 deletions
@@ -0,0 +1,65 @@
+#!/usr/bin/bash
+set -euo pipefail
+
+container_name="ts-lan-telemt"
+output_dir="/var/lib/zabbix"
+json_target="${output_dir}/telemt-active-ips.json"
+text_target="${output_dir}/telemt-active-ips.txt"
+metrics_target="${output_dir}/telemt-metrics.prom"
+
+install -d -o root -g zabbix -m 0750 "${output_dir}"
+
+container_pid="$(docker inspect --format '{{.State.Pid}}' "${container_name}")"
+if [[ -z "${container_pid}" || "${container_pid}" == "0" ]]; then
+  exit 1
+fi
+
+host_ip="$(ip -4 route get 1.1.1.1 | awk '{for (i=1; i<=NF; i++) if ($i == "src") {print $(i+1); exit}}')"
+if [[ -z "${host_ip}" ]]; then
+  exit 1
+fi
+
+json_tmp="$(mktemp "${output_dir}/.telemt-active-ips.json.XXXXXX")"
+text_tmp="$(mktemp "${output_dir}/.telemt-active-ips.txt.XXXXXX")"
+metrics_tmp="$(mktemp "${output_dir}/.telemt-metrics.prom.XXXXXX")"
+trap 'rm -f "${json_tmp}" "${text_tmp}" "${metrics_tmp}"' EXIT
+
+# The API response also contains proxy links and secrets. Filter it in-memory
+# and persist only the username and current active IP address list.
+nsenter -t "${container_pid}" -n \
+  curl --fail --silent --show-error --max-time 5 \
+  http://127.0.0.1:9091/v1/users |
+  jq --compact-output '{
+    users: [
+      .data[]
+      | {
+          username,
+          active_unique_ips: (.active_unique_ips_list // [])
+        }
+    ]
+  }' > "${json_tmp}"
+
+{
+  active_count="$(jq '[.users[].active_unique_ips[]] | unique | length' "${json_tmp}")"
+  printf 'Active IP addresses: %s\n' "${active_count}"
+  jq --raw-output '
+    [
+      .users[] as $user
+      | $user.active_unique_ips[]
+      | "\($user.username) | \(.)"
+    ]
+    | if length == 0 then ["No active IP addresses"] else . end
+    | .[]
+  ' "${json_tmp}"
+} > "${text_tmp}"
+
+# Cache Prometheus output locally. Zabbix active checks read the cache, so the
+# central server does not need a route to each private Docker host.
+curl --fail --silent --show-error --max-time 5 \
+  "http://${host_ip}:9092/metrics" > "${metrics_tmp}"
+
+chown root:zabbix "${json_tmp}" "${text_tmp}" "${metrics_tmp}"
+chmod 0640 "${json_tmp}" "${text_tmp}" "${metrics_tmp}"
+mv -f "${json_tmp}" "${json_target}"
+mv -f "${text_tmp}" "${text_target}"
+mv -f "${metrics_tmp}" "${metrics_target}"