Merge pull request #10774 from amaltaro/fix-10653-152

JobAccountant workaround for StepChain jobs with duplicate files - wmagent branch
dmwm · Aug 25, 2021 · 2be9734 · 2be9734
2 parents c2fa70a + 712565b
commit 2be9734
Showing 1 changed file with 9 additions and 0 deletions.
diff --git a/src/python/WMComponent/JobAccountant/AccountantWorker.py b/src/python/WMComponent/JobAccountant/AccountantWorker.py
@@ -454,6 +454,8 @@ def handleJob(self, jobID, fwkJobReport):
                                                 conn=self.getDBConn(),
                                                 transaction=self.existingTransaction())
 
+        # FIXME: temporary workaround for: https://github.com/dmwm/WMCore/issues/9633
+        skipOutputFiles = False
         if jobSuccess:
             fileList = fwkJobReport.getAllFiles()
 
@@ -504,6 +506,7 @@ def handleJob(self, jobID, fwkJobReport):
                 if not fwjrFile.get("locations") and fwjrFile.get("lfn", "").endswith(".root"):
                     logging.warning("The following file doesn't have any location: %s", fwjrFile)
                     jobSuccess = False
+                    skipOutputFiles = True
                     break
         else:
             fileList = fwkJobReport.getAllFilesFromStep(step='logArch1')
@@ -548,6 +551,12 @@ def handleJob(self, jobID, fwkJobReport):
             else:
                 wmbsJob["outcome"] = "failure"
 
+            # FIXME: BAD HACK to avoid crashing the component
+            if skipOutputFiles:
+                logging.warning("Skipping output file registration for failed job: %d", jobID)
+                self.listOfJobsToFail.append(wmbsJob)
+                return jobSuccess
+
             for fwjrFile in fileList:
 
                 logging.debug("Job %d , register output %s", jobID, fwjrFile["lfn"])