fix: keep apps running when network diagnostics fail

2026-09-30 17:34:11 -04:00
parent 02b840f2d1
commit f91c1f33db
11 changed files with 96 additions and 105 deletions
@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# Simulate failures without namespaces, network access, or real repair commands.
+set -euo pipefail
+source "$(dirname "$0")/../../scripts/container-doctor.sh"
+id() { if [[ "$*" == '-u archipelago' ]]; then echo 1000; else echo "${TEST_UID:-0}"; fi; }
+pgrep() { if [[ "$HAS_NETWORK" == 1 ]]; then echo 123; else return 1; fi; }
+sleep() { :; }
+# Any mutation fails the test immediately, including within command substitution.
+tripwire() { echo 'FAIL: diagnostic attempted a mutation' >&2; exit 99; }
+podman() { tripwire; }
+podman_rootless() { tripwire; }
+sudo() { tripwire; }
+systemctl() { tripwire; }
+pkill() { tripwire; }
+kill() { tripwire; }
+rm() { tripwire; }
+mkdir() { tripwire; }
+timeout() {
+    if [[ "$2" == bash ]]; then return "$HOST_STATUS"; fi
+    [[ "$2" == nsenter ]] || exit 98
+    PROBES=$((PROBES + 1))
+    if [[ "$PROBES" == 1 ]]; then return "$FIRST_STATUS"; fi
+    return "$SECOND_STATUS"
+}
+check_case() {
+    local label=$1 expected=$2 expected_probes=$3
+    PROBES=0
+    local status=0
+    check_rootless_netns_egress > /dev/null || status=$?
+    [[ "$status" == "$expected" && "$PROBES" == "$expected_probes" ]] || {
+        echo "FAIL: $label status=$status probes=$PROBES"; exit 1;
+    }
+    echo "PASS: $label"
+}
+HAS_NETWORK=1 HOST_STATUS=0 FIRST_STATUS=0 SECOND_STATUS=0
+check_case healthy 1 1
+TEST_UID=1000 check_case rootless-caller 1 0
+HAS_NETWORK=0 check_case no-network 1 0
+HOST_STATUS=1 check_case host-offline 2 0
+FIRST_STATUS=1 check_case transient-recovery 1 2
+FIRST_STATUS=1 SECOND_STATUS=1 check_case repeated-egress-failure 2 2
+FIRST_STATUS=126 SECOND_STATUS=126 check_case namespace-access-failure 2 2
+# Failure must remain an unresolved warning on every scheduled invocation.
+FIRST_STATUS=1 SECOND_STATUS=1
+for attempt in 1 2 3 4 5; do
+    PROBES=0
+    run_fix netns-egress check_rootless_netns_egress > /dev/null
+done
+[[ "$CHECKS_WARNED" == 5 && "$FIXES_APPLIED" == 0 && "$CHECKS_PASSED" == 0 ]]
+FIRST_STATUS=0 PROBES=0
+run_fix netns-egress check_rootless_netns_egress > /dev/null
+[[ "$CHECKS_PASSED" == 1 && "$FIXES_APPLIED" == 0 ]]
+echo 'PASS: repeated failure warnings never trigger repair or report a successful check'