validating changes

Author: cjac

cloudbuild/run-presubmit-on-k8s.sh

@@ -28,7 +28,7 @@ spec:
     image: "${IMAGE}"
     resources:
       requests:
-        memory: "8G"
+        memory: "4G"
         cpu: "6000m"
     env:
     - name: COMMIT_SHA
@@ -66,11 +66,21 @@ kubectl wait --for=condition=Ready "pod/${POD_NAME}" --timeout=15m
 
 # To mitigate problems with early test failure, retry kubectl logs
 sleep 10s
-while ! kubectl describe "pod/${POD_NAME}" | grep -q Terminated; do
-  # Try to stream logs, but primary log capture is now in the trap
+while true; do
+  if ! kubectl describe "pod/${POD_NAME}" > /dev/null 2>&1; then
+    echo "Pod ${POD_NAME} not found, assuming it has been deleted."
+    break # Exit the loop if the pod doesn't exist
+  fi
+
+  if kubectl describe "pod/${POD_NAME}" | grep -q Terminated; then
+    echo "Pod ${POD_NAME} is Terminated."
+    break # Exit the loop if the pod is Terminated
+  fi
+
+  # Try to stream logs
   kubectl logs -f "${POD_NAME}" --since-time="${LOGS_SINCE_TIME}" --timestamps=true || true
   LOGS_SINCE_TIME=$(date --iso-8601=seconds)
-  sleep 2 # Short sleep to avoid busy waiting if logs -f exits
+  sleep 2
 done
 
 # Final check on the pod exit code

gpu/README.md

@@ -26,7 +26,7 @@ Refer to internal arrays in `install_gpu_driver.sh` for the full matrix.)*
 
 CUDA | Full Version | Driver    | cuDNN     | NCCL   | Tested Dataproc Image Versions
 -----| ------------ | --------- | --------- | -------| ---------------------------
-11.8 | 11.8.0       | 525.147.05| 9.5.1.17  | 2.21.5 | 2.0, 2.1 (Debian/Ubuntu/Rocky)
+11.8 | 11.8.0       | 525.147.05| 9.5.1.17  | 2.21.5 | 2.0, 2.1 (Debian/Ubuntu/Rocky); 2.2 (Ubuntu 22.04)
 12.0 | 12.0.1       | 525.147.05| 8.8.1.3   | 2.16.5 | 2.0, 2.1 (Debian/Ubuntu/Rocky); 2.2 (Rocky 9, Ubuntu 22.04)
 12.4 | 12.4.1       | 550.135   | 9.1.0.70  | 2.23.4 | 2.1 (Ubuntu 20.04, Rocky 8); Dataproc 2.2+
 12.6 | 12.6.3       | 550.142   | 9.6.0.74  | 2.23.4 | 2.1 (Ubuntu 20.04, Rocky 8); Dataproc 2.2+
@@ -324,4 +324,4 @@ handles metric creation and reporting.
     Debian-based systems, including handling of archived backports repositories
     to ensure dependencies can be met.
   * Tested primarily with Dataproc 2.0+ images. Support for older Dataproc
-    1.5 images is limited.
+    1.5 images is limited.