write directly to pv to test job

.github/scripts/du.py

@@ -4,8 +4,9 @@
 import subprocess
 import sys
 import json
+from datetime import date
 
-OUTPUT_FILE = "/output/du_report.json"
+OUTPUT_DIR = "/home/asmacdo/du_reports/"
 SIZE_THRESHOLD_GB = 1
 SIZE_THRESHOLD_BYTES = SIZE_THRESHOLD_GB * 1024 * 1024 * 1024
 
@@ -41,11 +42,12 @@ def prepare_report(directory):
     for user, data in report.items():
         data["disk_usage_human_readable"] = bytes_to_human_readable(data["disk_usage_bytes"])
 
-    os.makedirs(os.path.dirname(OUTPUT_FILE), exist_ok=True)
-    with open(OUTPUT_FILE, 'w') as f:
-        json.dump(report, f, indent=4)
-
-    print(f"Disk usage report generated at {os.path.abspath(OUTPUT_FILE)}")
+    # os.makedirs(os.path.dirname(OUTPUT_FILE), exist_ok=True)
+    # output_file =
+    # with open(OUTPUT_FILE, 'w') as f:
+    #     json.dump(report, f, indent=4)
+    #
+    # print(f"Disk usage report generated at {os.path.abspath(OUTPUT_FILE)}")
 
 
 if __name__ == "__main__":
@@ -55,7 +57,8 @@ def prepare_report(directory):
         path = sys.argv[1]
         directories = [d for d in os.listdir(path) if os.path.isdir(os.path.join(path, d))]
 
-        os.makedirs(os.path.dirname(OUTPUT_FILE), exist_ok=True)
-        with open(OUTPUT_FILE, 'w') as f:
+        os.makedirs(os.path.dirname(OUTPUT_DIR), exist_ok=True)
+        current_date = date.today().strftime('%Y-%m-%d')
+        with open(f"OUTPUT_DIR/{current_date}.json", "w") as f:
             f.write("\n".join(directories))
         # prepare_report(directory)

.github/workflows/report.yaml

@@ -83,13 +83,6 @@ jobs:
           kubectl wait --for=condition=complete job/disk-usage-report-job --timeout=360s -n jupyterhub
         continue-on-error: true
 
-      - name: Retrieve generated report file
-        run: |
-          POD_NAME=$(kubectl get pods -n jupyterhub --selector=job-name=disk-usage-report-job -o jsonpath='{.items[0].metadata.name}')
-          kubectl cp $POD_NAME:/output/du_report.json du_report.json -n jupyterhub
-          cat du_report.json
-        continue-on-error: true
-
       # continue-on-error for previous steps so we delete the job
       - name: Delete Disk Usage Report Job
         run: |