We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 16f771d commit cd5878aCopy full SHA for cd5878a
nemo_run/core/execution/dgxcloud.py
@@ -405,7 +405,11 @@ def fetch_logs(
405
job_subdir = self.job_dir[len(nemo_run_home) + 1 :] # +1 to remove the initial backslash
406
self.pvc_job_dir = os.path.join(self.pvc_nemo_run_dir, job_subdir)
407
408
- cmd.extend([f"{self.pvc_job_dir}/logs/output-{i}.log" for i in range(self.nodes)])
+ while files := len(glob.glob(f"{self.pvc_job_dir}/logs/output-*.log")) < self.nodes:
409
+ logger.info(f"Waiting for {self.nodes - len(files)} log files to be created...")
410
+ time.sleep(3)
411
+
412
+ cmd.extend(files)
413
414
logger.info(f"Attempting to stream logs with command: {cmd}")
415
0 commit comments