When running a modified dfind that printed out extra data (uid, gid, blocks, size) on a whole file system czlustre3 (680 million items), the processes ended far enough apart that slurm killed the remaining processes. One option is to just tell slurm to allow a larger difference in process end times, but I think this issue is already solved for dwalk, such that dwalk can do a whole file system and do a --text printout and the processes all end at approximately the same time.