From 0256d332cc0c7b1dcf96ecb9c1e3d147439d432e Mon Sep 17 00:00:00 2001 From: Vinya Kestur Date: Thu, 23 Jul 2026 17:55:10 +0000 Subject: [PATCH] test: fix L0_lifecycle test_shutdown_dynamic exit timeout Extend the exit-timeout window for the test_shutdown_dynamic server launch to SERVER_TIMEOUT (120s) and tolerate a non-zero wait exit so "set -e" does not abort the rest of L0_lifecycle when the exit timeout fires while draining in-flight dynamic-batch work. Root cause: the test issues 6 async inferences with execute_delay_ms=5000 and then SIGINTs the server while they are in flight. The default 30s Triton exit timeout is not enough for the drain on Luna, so the server logs "Exit timeout expired" and exits non-zero, and "wait $SERVER_PID" under "set -e" aborts the whole suite. The related lifecycle_test.py assertion-string and lint changes from earlier revisions of this branch are now redundant with #8888 on main, so this PR carries only the shutdown-timeout fix in test.sh. --- qa/L0_lifecycle/test.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/qa/L0_lifecycle/test.sh b/qa/L0_lifecycle/test.sh index 964986a519..0178c55624 100755 --- a/qa/L0_lifecycle/test.sh +++ b/qa/L0_lifecycle/test.sh @@ -1,5 +1,5 @@ #!/bin/bash -# Copyright 2018-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# Copyright 2018-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. # # Redistribution and use in source and binary forms, with or without # modification, are permitted provided that the following conditions @@ -1563,7 +1563,7 @@ cp -r ../custom_models/custom_zero_1_float32 models/. && \ echo "{ key: \"execute_delay_ms\"; value: { string_value: \"5000\" }}" >> config.pbtxt && \ echo "]" >> config.pbtxt) -SERVER_ARGS="--model-repository=`pwd`/models --log-verbose=1" +SERVER_ARGS="--model-repository=`pwd`/models --log-verbose=1 --exit-timeout-secs=${SERVER_TIMEOUT}" SERVER_LOG="./inference_server_$LOG_IDX.log" run_server if [ "$SERVER_PID" == "0" ]; then @@ -1585,7 +1585,7 @@ if [ `grep -c "Found 1 gRPC service connections and inference handlers" $SERVER_ fi kill $SERVER_PID || true -wait $SERVER_PID +wait $SERVER_PID || true rm -f $CLIENT_LOG