From 54c2bd119f77fcd418455e85c954d5fd74d6e624 Mon Sep 17 00:00:00 2001
From: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
Date: Tue, 24 Oct 2023 11:49:42 +0200
Subject: [PATCH] Add ICMP probes

These probes check if we can reach several targets via ICMP, which is
not proxied, so they can be used to see if ICMP forwarding is working in
the login node.

In particular, we test if we can reach the Google (8.8.8.8) and
Cloudflare (1.1.1.1) DNS servers, the BSC gateway which responds to ping
only from the intranet and the login node (ssfhead).

Reviewed-By: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
---
 m/hut/blackbox.yml   |  3 +--
 m/hut/monitoring.nix | 32 +++++++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/m/hut/blackbox.yml b/m/hut/blackbox.yml
index 83de003d..e69acd31 100644
--- a/m/hut/blackbox.yml
+++ b/m/hut/blackbox.yml
@@ -121,12 +121,11 @@ modules:
         - expect: "PING :([^ ]+)"
           send: "PONG ${1}"
         - expect: "^:[^ ]+ 001"
-  icmp_example:
+  icmp:
     prober: icmp
     timeout: 5s
     icmp:
       preferred_ip_protocol: "ip4"
-      source_ip_address: "127.0.0.1"
   dns_udp_example:
     prober: dns
     timeout: 5s
diff --git a/m/hut/monitoring.nix b/m/hut/monitoring.nix
index 304590f6..61fa22cf 100644
--- a/m/hut/monitoring.nix
+++ b/m/hut/monitoring.nix
@@ -100,7 +100,7 @@
         }];
       }
       {
-        job_name = "blackbox";
+        job_name = "blackbox-http";
         metrics_path = "/probe";
         params = { module = [ "http_2xx" ]; };
         static_configs = [{
@@ -128,6 +128,36 @@
           }
         ];
       }
+      {
+        job_name = "blackbox-icmp";
+        metrics_path = "/probe";
+        params = { module = [ "icmp" ]; };
+        static_configs = [{
+          targets = [
+            "1.1.1.1"
+            "8.8.8.8"
+            "ssfhead"
+            "gw.bsc.es"
+          ];
+        }];
+        relabel_configs = [
+          {
+            # Takes the address and sets it in the "target=<xyz>" URL parameter
+            source_labels = [ "__address__" ];
+            target_label = "__param_target";
+          }
+          {
+            # Sets the "instance" label with the remote host we are querying
+            source_labels = [ "__param_target" ];
+            target_label = "instance";
+          }
+          {
+            # Shows the host target address instead of the blackbox address
+            target_label = "__address__";
+            replacement = "127.0.0.1:${toString config.services.prometheus.exporters.blackbox.port}";
+          }
+        ];
+      }
       {
         # Scrape the IPMI info of the hosts remotely via LAN
         job_name = "ipmi-lan";