[perf bench] set timeout to debug hanging (vllm-project#8516)

gnpinkert · Sep 16, 2024 · 5478c4b · 5478c4b
1 parent 47f5e03
commit 5478c4b
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/.buildkite/nightly-benchmarks/benchmark-pipeline.yaml b/.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
@@ -8,8 +8,7 @@ steps:
           containers:
           - image: badouralix/curl-jq
             command:
-            - sh
-            - .buildkite/nightly-benchmarks/scripts/wait-for-image.sh
+            - sh .buildkite/nightly-benchmarks/scripts/wait-for-image.sh
   - wait
   - label: "A100"
     agents:

diff --git a/.buildkite/nightly-benchmarks/scripts/wait-for-image.sh b/.buildkite/nightly-benchmarks/scripts/wait-for-image.sh
@@ -2,9 +2,11 @@
 TOKEN=$(curl -s -L "https://public.ecr.aws/token?service=public.ecr.aws&scope=repository:q9t5s3a7/vllm-ci-test-repo:pull" | jq -r .token)
 URL="https://public.ecr.aws/v2/q9t5s3a7/vllm-ci-test-repo/manifests/$BUILDKITE_COMMIT"
 
+TIMEOUT_SECONDS=10
+
 retries=0
 while [ $retries -lt 1000 ]; do
-    if [ $(curl -s -L -H "Authorization: Bearer $TOKEN" -o /dev/null -w "%{http_code}" $URL) -eq 200 ]; then
+    if [ $(curl -s --max-time $TIMEOUT_SECONDS -L -H "Authorization: Bearer $TOKEN" -o /dev/null -w "%{http_code}" $URL) -eq 200 ]; then
         exit 0
     fi