test(opcua): add fixed candidate saturation diagnosis with observer barriers

2026-11-10 14:51:19 -05:00
parent ab35ddd3c2
commit 54a4ff2149
8 changed files with 833 additions and 13 deletions
@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# Diagnostic only. The published xUnit apphost and observer are self-contained .NET 10.0.14.
+set -euo pipefail
+mkdir -p /task/tmp /task/data /task/results /task/control
+export TMPDIR=/task/tmp XDG_DATA_HOME=/task/data
+export OTOPCUA_SDK2_SOAK=1 OTOPCUA_SDK2_SOAK_MODE=saturation OTOPCUA_SDK2_SOAK_SECONDS=1800
+export OTOPCUA_SDK2_SOAK_OUTPUT=/task/resources.jsonl
+export OTOPCUA_SDK2_SATURATION_CONTROL=/task/control
+export OPCUA_CERTIFICATE_LEAK_TRACKING=1
+export DOTNET_CLI_TELEMETRY_OPTOUT=1 DOTNET_NOLOGO=1
+[[ $(uname -s) == Linux && $(uname -m) == aarch64 && -d /proc/self/fd ]]
+dotnet --info > /task/controller-runtime.txt
+vstest_pid= observer_pid=
+cleanup() {
+    for child in "$vstest_pid" "$observer_pid"; do
+        if [[ -n "$child" ]] && kill -0 "$child" 2>/dev/null; then kill "$child" 2>/dev/null || true; fi
+    done
+}
+trap cleanup EXIT
+dotnet vstest /app/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests.dll \
+  --TestCaseFilter:'FullyQualifiedName~Sdk2LifecycleSoakTests.Descriptor_probe_' \
+  --ResultsDirectory:/task/results '--Logger:trx;LogFileName=descriptor-controls.trx' > /task/descriptor-controls.log 2>&1
+/observer/observer /task/control "$OTOPCUA_SDK2_SATURATION_RUN_ID" > /task/observer.log 2>&1 &
+observer_pid=$!
+dotnet vstest /app/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests.dll \
+  --TestCaseFilter:'FullyQualifiedName=ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests.Sdk2LifecycleSoakTests.Repeated_lifecycles_return_resources_to_a_steady_baseline' \
+  --ResultsDirectory:/task/results '--Logger:trx;LogFileName=saturation.trx' > /task/test.log 2>&1 &
+vstest_pid=$!
+observed=0
+for attempt in $(seq 1 1200); do
+    if [[ -s /task/resources.jsonl ]]; then
+        target_pid=$(head -n 1 /task/resources.jsonl | sed -n 's/.*"processId":\([0-9]*\),.*/\1/p')
+        [[ -n "$target_pid" ]]
+        target_exe=$(readlink "/proc/$target_pid/exe")
+        [[ "$target_exe" == /app/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests ]]
+        printf 'targetPid=%s\nactualExecutable=%s\n' "$target_pid" "$target_exe" > /task/target-runtime.txt
+        awk '$6 ~ /\/(libcoreclr.so|libhostfxr.so|libhostpolicy.so|System.Private.CoreLib.dll)$/ {print $6}' "/proc/$target_pid/maps" | sort -u >> /task/target-runtime.txt
+        grep -Fx /app/libcoreclr.so /task/target-runtime.txt > /dev/null
+        [[ $(readlink "/proc/$observer_pid/exe") == /observer/observer ]]
+        awk '$6 ~ /\/libcoreclr.so$/ {print $6}' "/proc/$observer_pid/maps" | sort -u > /task/observer-runtime.txt
+        grep -Fx /observer/libcoreclr.so /task/observer-runtime.txt > /dev/null
+        observed=1
+        break
+    fi
+    kill -0 "$vstest_pid" 2>/dev/null || break
+    sleep 0.1
+done
+[[ "$observed" == 1 ]]
+set +e
+wait "$vstest_pid"
+test_status=$?
+printf '%s\n' "$test_status" > /task/test-exit-status.txt
+for attempt in $(seq 1 400); do
+    kill -0 "$observer_pid" 2>/dev/null || break
+    sleep 0.1
+done
+if kill -0 "$observer_pid" 2>/dev/null; then kill "$observer_pid"; fi
+wait "$observer_pid"
+observer_status=$?
+printf '%s\n' "$observer_status" > /task/observer-exit-status.txt
+# Preserve a cold-cap failure even when diagnostic readiness succeeds.
+if [[ "$test_status" != 0 ]]; then exit "$test_status"; fi
+exit "$observer_status"