apt_updates: the role owns the apt metrics (Debian collector off, explicit zero rows, multi-suite security detection)

apt_updates/tasks/main.yml

@@ -11,6 +11,7 @@
     src: apt-updates-metrics.j2
     dest: /usr/local/sbin/apt-updates-metrics
     mode: "0755"
+  register: apt_updates_script
 
 - name: Create the apt timers' drop-in directories
   ansible.builtin.file:
@@ -39,3 +40,41 @@
   when: apt_updates_dropins.changed
   # Check mode does not write the drop-ins.
   ignore_errors: "{{ ansible_check_mode }}"
+
+# Debian's prometheus-node-exporter-apt collector writes apt.prom with the same metric families as this role under
+# other HELP texts; node_exporter drops the rows of both files then. This role owns the apt metrics, so the
+# collector stays off and its file, also a stale leftover of a removed collector, goes away.
+- name: Look for the Debian apt metrics collector
+  ansible.builtin.stat:
+    path: /lib/systemd/system/prometheus-node-exporter-apt.timer
+  register: apt_updates_debian_collector
+
+- name: Stop and disable the Debian apt metrics collector timer
+  ansible.builtin.systemd:
+    name: prometheus-node-exporter-apt.timer
+    enabled: false
+    state: stopped
+  when: apt_updates_debian_collector.stat.exists
+
+- name: Stop the Debian apt metrics collector service
+  ansible.builtin.systemd:
+    name: prometheus-node-exporter-apt.service
+    state: stopped
+  when: apt_updates_debian_collector.stat.exists
+
+- name: Remove the Debian apt metrics collector output
+  ansible.builtin.file:
+    path: "{{ apt_updates_textfile_dir }}/apt.prom"
+    state: absent
+
+# The timers' drop-ins write the metrics after the next apt run; this gives a new host and a changed script
+# current metrics at once.
+- name: Look for the apt metrics file
+  ansible.builtin.stat:
+    path: "{{ apt_updates_textfile_dir }}/apt_updates.prom"
+  register: apt_updates_prom
+
+- name: Write the apt metrics
+  ansible.builtin.command: /usr/local/sbin/apt-updates-metrics
+  when: apt_updates_script.changed or not apt_updates_prom.stat.exists
+  changed_when: true

apt_updates/templates/apt-updates-metrics.j2

@@ -9,11 +9,14 @@ out=$textfile_dir/apt_updates.prom
 tmp=$(mktemp "$textfile_dir/.apt_updates.XXXXXX")
 trap 'rm -f "$tmp"' EXIT
 
-arch=$(dpkg --print-architecture)
+# Architectures a pending package can have: the native and foreign ones, plus "all" for architecture-independent
+# packages. Each gets a row per kind even at 0, so a resolved backlog reads as 0 and not as a vanished series.
+archs="$(dpkg --print-architecture) $(dpkg --print-foreign-architectures | tr '\n' ' ') all"
 
-# The simulated upgrade lists "Inst <package> [<installed>] (<candidate> <origin> [<arch>])" per package.
+# The simulated upgrade lists "Inst <package> [<installed>] (<candidate> <origins> [<arch>])" per package. A version in
-# An origin containing "security" counts as security, everything else as regular.
+# several suites lists them all, comma separated. A package counts as security when any origin contains "security",
-pending=$(apt-get -s upgrade | awk -v host="$host" -v arch="$arch" '
+# everything else as regular.
+pending=$(apt-get -s upgrade | awk -v host="$host" -v archs="$archs" '
   /^Inst / {
     line = $0
     sub(/^[^(]*\(/, "", line)
@@ -21,13 +24,16 @@ pending=$(apt-get -s upgrade | awk -v host="$host" -v arch="$arch" '
     n = split(line, f, " ")
     pkg_arch = f[n]
     gsub(/\[|\]/, "", pkg_arch)
-    origin = (n >= 3) ? f[2] : ""
+    sub(/^[^ ]+ /, "", line)
-    kind = (tolower(origin) ~ /security/) ? "security" : "regular"
+    kind = (tolower(line) ~ /security/) ? "security" : "regular"
     count[kind, pkg_arch]++
   }
   END {
-    if (!(("security", arch) in count)) count["security", arch] = 0
+    split(archs, a, " ")
-    if (!(("regular", arch) in count)) count["regular", arch] = 0
+    for (i in a) {
+      if (!(("security", a[i]) in count)) count["security", a[i]] = 0
+      if (!(("regular", a[i]) in count)) count["regular", a[i]] = 0
+    }
     for (key in count) {
       split(key, k, SUBSEP)
       printf "apt_upgrades_pending{host=\"%s\",origin=\"%s\",arch=\"%s\"} %d\n", host, k[1], k[2], count[key]
@@ -41,11 +47,15 @@ if [[ -e /run/reboot-required ]]; then
   reboot=1
 fi
 
-# Debian writes update-stamp, Ubuntu update-success-stamp; both are touched by a successful update.
+# Debian writes update-stamp, Ubuntu update-success-stamp; both are touched by a successful update. Both are missing
+# until apt.systemd.daily has run an update, then the package cache stands in.
 stamp=/var/lib/apt/periodic/update-success-stamp
 if [[ ! -e $stamp ]]; then
   stamp=/var/lib/apt/periodic/update-stamp
 fi
+if [[ ! -e $stamp ]]; then
+  stamp=/var/cache/apt/pkgcache.bin
+fi
 cache=$(stat -c %Y "$stamp")
 
 {