Merge pull request #22 from kristianwind/site-test-volume-leak

Stop ci/site-test.sh leaking a MariaDB volume on every run

ci/site-test.sh

@@ -27,10 +27,49 @@ PHP_VERSION="${PHP_VERSION:-8.3}"
 
 id="wpci-$$"
 net="$id-net"
+# 🔴 -v, and it is the whole bug. `mariadb:lts` declares VOLUME
+# /var/lib/mysql, so every run creates an ANONYMOUS volume, and `docker rm -f`
+# does not remove anonymous volumes — only `docker rm -f -v` does. The named
+# $id-wp below is removed correctly, which is exactly what made this function
+# look complete: removing three of the four things you created is
+# indistinguishable from removing all four unless you count.
+#
+# Measured 2026-09-17 after a sibling plugin traced it: the Gitea runner's disk
+# was 100% full, 26 GB in 95 volumes with 1 in use, and a push there failed
+# with `unable to create temporary object directory` — three layers from the
+# cause. This machine had 127 dangling volumes and 15.2 GB reclaimable.
 cleanup() {
-  docker rm -f "$id-db" "$id-cli" >/dev/null 2>&1 || true
+  # Ask the containers which volumes they own BEFORE removing them. A global
+  # before/after count would be wrong here: several sessions share this box and
+  # run these container pairs concurrently, so a neighbour's volume would read
+  # as this run's leak.
+  local owned=""
+  owned=$(docker inspect -f \
+    '{{range .Mounts}}{{if eq .Type "volume"}}{{.Name}} {{end}}{{end}}' \
+    "$id-db" "$id-cli" 2>/dev/null || true)
+
+  docker rm -f -v "$id-db" "$id-cli" >/dev/null 2>&1 || true
   docker volume rm -f "$id-wp" >/dev/null 2>&1 || true
   docker network rm "$net" >/dev/null 2>&1 || true
+
+  # Count rather than trust the flag. This is advisory on a failed run — a test
+  # that died halfway has more urgent news — but on a successful run a leftover
+  # volume is a real regression and says so.
+  local leaked=""
+  for v in $owned; do
+    docker volume inspect "$v" >/dev/null 2>&1 && leaked="$leaked $v"
+  done
+  if [ -n "$leaked" ]; then
+    echo "::warning::This run left docker volume(s) behind:$leaked — 95 of these filled the Gitea runner's disk."
+    # `return` from an EXIT trap does NOT change the script's exit status;
+    # only `exit` does. Without this the warning would print and the build
+    # would still go green, which is the failure mode of every other check
+    # this kit has had to fix tonight.
+    if [ "${site_test_ok:-0}" = 1 ]; then
+      ci_fail "The site test leaked the volume(s) above. Left alone this fills the runner's disk, and the symptom is a push failing with 'unable to create temporary object directory'."
+      exit 1
+    fi
+  fi
 }
 trap cleanup EXIT
 
@@ -144,5 +183,9 @@ else
   echo "  nothing logged at all"
 fi
 
+# Set only here, so the leak check above is advisory on a run that failed for
+# some other reason and fatal on one that otherwise passed.
+site_test_ok=1
+
 ci_step "done"
 echo "WordPress $(wp core version)$( [ "$NEEDS_WOOCOMMERCE" = yes ] && echo " + WooCommerce $(wp plugin get woocommerce --field=version)" ) on PHP $PHP_VERSION: green"