rhdh: gzip junit results in SHARED_DIR and align overlays resource limits (openshift#81313)

* rhdh: gzip junit results in SHARED_DIR to avoid Secret size limit

The junit-results.xml on the overlays main branch exceeds the Kubernetes
Secret 1 MiB size limit, causing the SHARED_DIR Secret update to fail
and leaving the send-data-router step with no junit file to report.

Fix by gzipping junit XML before writing to SHARED_DIR (XML compresses
~10-15x) and decompressing in the data-router steps to ARTIFACT_DIR
before processing and sending to Data Router.

Changes:
- overlays ocp-helm: gzip junit + 800 KB size check before SHARED_DIR
- overlays send-data-router: decompress .gz to ARTIFACT_DIR, fall back
  to plain XML for backward compat
- rhdh send-data-router: same decompression + fallback (preventive,
  activated by a follow-up PR in redhat-developer/rhdh)

Assisted-by: OpenCode

* rhdh overlays: align ocp-helm resource requests/limits with rhdh

Match the RHDH ocp-helm step resource specs:
- CPU: 1 request / 10 limit (was 2 / 4)
- Memory: 1Gi request / 5Gi limit (was 6Gi / 8Gi)

Assisted-by: OpenCode

* rhdh: harden data-router scripts error handling

- Remove set +o nounset (all env vars have defaults in ref YAML)
- Add explicit exit 0 to guarantee the step never fails the CI job
- Change ERROR to WARNING for missing junit (expected in overflow case)
- Fix unbound GIT_PR_NUMBER and TAG_NAME references in rhdh data-router
- Add comments explaining the set +o errexit contract

Assisted-by: OpenCode

Author: zdrapela

ci-operator/step-registry/redhat-developer/rhdh-plugin-export-overlays/ocp/helm/redhat-developer-rhdh-plugin-export-overlays-ocp-helm-commands.sh

@@ -206,9 +206,18 @@ collect_artifacts() {
         cp -a node_modules/.cache/e2e-test-results "${ARTIFACT_DIR}/" 2>&1 || echo "[WARNING] e2e-test-results not found"
     fi
     # Copy JUnit results to SHARED_DIR for data-router step
+    # Gzip to stay under Kubernetes Secret 1 MiB limit (raw XML can exceed it)
     if [[ -f "playwright-report/junit-results.xml" ]]; then
-        cp "playwright-report/junit-results.xml" "${SHARED_DIR}/"
-        echo "[INFO] Copied junit-results.xml to ${SHARED_DIR}/"
+        gzip -c "playwright-report/junit-results.xml" > "${SHARED_DIR}/junit-results.xml.gz"
+        local gz_size
+        gz_size=$(stat -c%s "${SHARED_DIR}/junit-results.xml.gz" 2>/dev/null || stat -f%z "${SHARED_DIR}/junit-results.xml.gz")
+        local max_size=$((800 * 1024))
+        if (( gz_size > max_size )); then
+            echo "[WARNING] junit-results.xml.gz is $(( gz_size / 1024 )) KB, exceeds $(( max_size / 1024 )) KB limit. Removing from SHARED_DIR to prevent Secret update failure."
+            rm -f "${SHARED_DIR}/junit-results.xml.gz"
+        else
+            echo "[INFO] Copied junit-results.xml.gz to ${SHARED_DIR}/ ($(( gz_size / 1024 )) KB)"
+        fi
     fi
 }
 

ci-operator/step-registry/redhat-developer/rhdh-plugin-export-overlays/ocp/helm/redhat-developer-rhdh-plugin-export-overlays-ocp-helm-ref.yaml

@@ -33,8 +33,8 @@ ref:
   timeout: 3h30m0s
   resources:
     limits:
-      memory: 8Gi
-      cpu: "4"
+      cpu: "10"
+      memory: 5Gi
     requests:
-      cpu: "2"
-      memory: 6Gi
+      cpu: "1"
+      memory: 1Gi

ci-operator/step-registry/redhat-developer/rhdh-plugin-export-overlays/send/data-router/redhat-developer-rhdh-plugin-export-overlays-send-data-router-commands.sh

@@ -1,7 +1,8 @@
 #!/bin/bash
 
+# This post step must never fail the overall CI job — it is a reporting step.
+# errexit is disabled so errors are handled internally (retries, warnings, graceful skips).
 set +o errexit
-set +o nounset
 
 # Skip data router reporting when job was triggered via Gangway API with overrides
 OVERRIDE_VARS=(
@@ -87,16 +88,27 @@ get_artifacts_url() {
 process_junit_file() {
   echo "Processing JUnit file for Data Router compatibility..."
 
-  local junit_file="${SHARED_DIR}/junit-results.xml"
-  if [[ ! -f "$junit_file" ]]; then
+  mkdir -p "${ARTIFACT_DIR}/data-router"
+
+  local junit_gz="${SHARED_DIR}/junit-results.xml.gz"
+  local junit_shared="${SHARED_DIR}/junit-results.xml"
+  local junit_file="${ARTIFACT_DIR}/data-router/junit-results.xml"
+
+  # Decompress gzipped junit to ARTIFACT_DIR (new format); fall back to plain XML (backward compat)
+  if [[ -f "$junit_gz" ]]; then
+    gunzip -c "$junit_gz" > "$junit_file"
+    echo "Decompressed junit-results.xml.gz -> ${junit_file}"
+  elif [[ -f "$junit_shared" ]]; then
+    cp "$junit_shared" "$junit_file"
+    echo "Copied junit-results.xml from SHARED_DIR to ARTIFACT_DIR"
+  else
     echo "WARNING: junit-results.xml not found in ${SHARED_DIR}, skipping processing"
     return
   fi
 
   echo "Processing: junit-results.xml"
 
   # Create backup in ARTIFACT_DIR
-  mkdir -p "${ARTIFACT_DIR}/data-router"
   cp "$junit_file" "${ARTIFACT_DIR}/data-router/junit-results.xml.original.xml"
 
   # Construct artifacts URL for attachment placeholder replacement
@@ -253,9 +265,10 @@ main() {
   local output=""
   local DATA_ROUTER_REQUEST_ID=""
 
-  if [[ ! -f "${SHARED_DIR}/junit-results.xml" ]]; then
-    echo "ERROR: No JUnit results file (junit-results.xml) found in ${SHARED_DIR}"
-    return
+  local junit_for_send="${ARTIFACT_DIR}/data-router/junit-results.xml"
+  if [[ ! -f "$junit_for_send" ]]; then
+    echo "WARNING: No JUnit results file found (processed by process_junit_file), skipping Data Router upload"
+    return 0
   fi
 
   for ((i = 1; i <= max_attempts; i++)); do
@@ -265,7 +278,7 @@ main() {
         --url "${DATA_ROUTER_URL}" \
         --username "${DATA_ROUTER_USERNAME}" \
         --password "${DATA_ROUTER_PASSWORD}" \
-        --results "${SHARED_DIR}/junit-results.xml" \
+        --results "$junit_for_send" \
         --verbose --wirelog 2>&1) && \
       DATA_ROUTER_REQUEST_ID=$(echo "$output" | grep "request:" | awk '{print $2}') &&
       [ -n "$DATA_ROUTER_REQUEST_ID" ]; then
@@ -320,3 +333,6 @@ main() {
 }
 
 main
+
+# Ensure this reporting step never fails the CI job regardless of what main() returned
+exit 0

ci-operator/step-registry/redhat-developer/rhdh/send/data-router/redhat-developer-rhdh-send-data-router-commands.sh

@@ -1,7 +1,8 @@
 #!/bin/bash
 
+# This post step must never fail the overall CI job — it is a reporting step.
+# errexit is disabled so errors are handled internally (retries, warnings, graceful skips).
 set +o errexit
-set +o nounset
 
 # Skip data router reporting when job was triggered via Gangway API with overrides
 OVERRIDE_VARS=(
@@ -96,7 +97,30 @@ get_artifacts_url() {
 process_junit_files() {
   echo "📝 Processing JUnit files for Data Router compatibility..."
 
-  for junit_file in "${SHARED_DIR}"/junit-results-*.xml; do
+  mkdir -p "${ARTIFACT_DIR}/data-router"
+
+  # Decompress gzipped junit files to ARTIFACT_DIR (new format); copy plain XML as fallback (backward compat)
+  for junit_gz in "${SHARED_DIR}"/junit-results-*.xml.gz; do
+    if [[ -f "$junit_gz" ]]; then
+      local filename
+      filename=$(basename "${junit_gz%.gz}")
+      gunzip -c "$junit_gz" > "${ARTIFACT_DIR}/data-router/${filename}"
+      echo "Decompressed $(basename "$junit_gz") -> ${ARTIFACT_DIR}/data-router/${filename}"
+    fi
+  done
+  for junit_shared in "${SHARED_DIR}"/junit-results-*.xml; do
+    if [[ -f "$junit_shared" ]]; then
+      local filename
+      filename=$(basename "$junit_shared")
+      # Only copy if not already decompressed from .gz
+      if [[ ! -f "${ARTIFACT_DIR}/data-router/${filename}" ]]; then
+        cp "$junit_shared" "${ARTIFACT_DIR}/data-router/${filename}"
+        echo "Copied ${filename} from SHARED_DIR to ARTIFACT_DIR"
+      fi
+    fi
+  done
+
+  for junit_file in "${ARTIFACT_DIR}"/data-router/junit-results-*.xml; do
     if [[ ! -f "$junit_file" ]]; then
       continue
     fi
@@ -204,9 +228,9 @@ save_data_router_metadata() {
     --arg name "$JOB_NAME" \
     --arg description "[View job run details](${JOB_URL})" \
     --arg job_type "$JOB_TYPE" \
-    --arg pr "$GIT_PR_NUMBER" \
+    --arg pr "${GIT_PR_NUMBER:-}" \
     --arg job_name "$JOB_NAME" \
-    --arg tag_name "$TAG_NAME" \
+    --arg tag_name "${TAG_NAME:-}" \
     --arg install_method "$install_method" \
     --arg cluster_type "$cluster_type" \
     --arg container_platform "$CONTAINER_PLATFORM" \
@@ -270,25 +294,25 @@ main() {
     for ((i = 1; i <= max_attempts; i++)); do
       echo "Attempt ${i} of ${max_attempts} to send test results through Data Router."
 
-      # Check if JUnit results files exist in SHARED_DIR
+      # Check if JUnit results files exist in ARTIFACT_DIR (decompressed by process_junit_files)
       local junit_files_found=false
-      for file in "${SHARED_DIR}"/junit-*.xml; do
+      for file in "${ARTIFACT_DIR}"/data-router/junit-*.xml; do
         if [[ -f "$file" ]]; then
           junit_files_found=true
           break
         fi
       done
 
       if [[ "$junit_files_found" == false ]]; then
-        echo "ERROR: No JUnit results files (junit-*.xml) found in ${SHARED_DIR}"
-        return
+        echo "WARNING: No JUnit results files (junit-*.xml) found in ${ARTIFACT_DIR}/data-router, skipping Data Router upload"
+        return 0
       fi
 
       if output=$(droute send --metadata "$(get_metadata_output_path)" \
           --url "${DATA_ROUTER_URL}" \
           --username "${DATA_ROUTER_USERNAME}" \
           --password "${DATA_ROUTER_PASSWORD}" \
-          --results "${SHARED_DIR}/junit-*.xml" \
+          --results "${ARTIFACT_DIR}/data-router/junit-*.xml" \
           --verbose --wirelog 2>&1) && \
         DATA_ROUTER_REQUEST_ID=$(echo "$output" | grep "request:" | awk '{print $2}') &&
         [ -n "$DATA_ROUTER_REQUEST_ID" ]; then
@@ -349,3 +373,6 @@ main() {
 }
 
 main
+
+# Ensure this reporting step never fails the CI job regardless of what main() returned
+exit 0