One node on the cluster has a TmpDisk value of 12.1 TB (= 12100000 MB) specified in slurm.conf which is properly displayed by scontrol. With sinfo, however, the last digit of the TmpDisk value is missing as shown in the following example: slater:~> scontrol show node cusp05 NodeName=cusp05 Arch=x86_64 CoresPerSocket=12 CPUAlloc=48 CPUTot=48 CPULoad=48.11 AvailableFeatures=(null) ActiveFeatures=(null) Gres=(null) NodeAddr=cusp05 NodeHostName=cusp05 Version=20.02.6 OS=Linux 5.3.18-lp152.66-default #1 SMP Tue Mar 2 13:18:19 UTC 2021 (73933a3) RealMemory=3072000 AllocMem=2806848 FreeMem=6769 Sockets=4 Boards=1 State=ALLOCATED ThreadsPerCore=1 TmpDisk=12100000 Weight=48 Owner=N/A MCS_label=N/A Partitions=normal BootTime=2021-03-12T16:03:54 SlurmdStartTime=2021-03-12T16:27:11 CfgTRES=cpu=48,mem=3000G,billing=48 AllocTRES=cpu=48,mem=2806848M CapWatts=n/a CurrentWatts=0 AveWatts=0 ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s slater:~> sinfo -n cusp05 -o %d TMP_DISK 1210000