Failed to clone disk: There is not enough space on the file system for the selected operation (13)

The Situation:
1.  We have two SuperMicro servers running ESXi 4.0, and do cross-backups each night between the servers using vkmfstools.  Earch server has Windows 2003 Server VM running  Windows Services for UNIX Version 3.5, each with a system virtual hard drive, and a data virtual hard drive, which is shared as an NFS volume.  All VMs are thin.  This has worked fine since 2008.

2.  We recently purchased two more powerful servers from SoftLayer to upgrade.  These are SuperMicro Dual XEON 5670 Servers with 12GB RAM, and 2TB RAID 10 array.  I did a fresh install of ESXi 5.1 on both machines.  I mounted the NFS datastores on the old servers on the new servers to copy the VMs across.  The Windows NFS volumes were not brought across.  I simply made new NFS virtual disks for the Windows 2003 Server VMs that are 500GB in size, or 2 1/2 times the size of the originals.  The VMs are in production and run as expected.

The Problem:

1.  When Server2 backs up fine to the NFS volume on Server1, the clones go fine.  However, when Server1 backs up to Server2, the largest VM (55GB thin and 80GB declared, fails at the 90% point on each attempt, even if you clear space, which it shouldn't need as the drive only has about 50 GB of data on a 500 GB NFS volume, and the ESXi VMWare Client shows the same amount of free space no matter which server I check it from..

     Destination disk format: VMFS thin-provisioned
     Cloning disk '/vmfs/volumes/datastore1/my_vm/my_vm.vmdk'...
     Clone: 90% done.Failed to clone disk: There is not enough space on the file system for the selected operation (13).

2.  The 90% is an interesting number because something else that is different with Server1 is when you begin the backup with vkmfstools, it starts counting at 10% instead of 0%.  This is the case while copying any VM, not just the larger one, and whether you copy locally, or to the NFS volume.

3.  I can successfully back up the large VM from the Server1 computer if I copy it locally to another directory on the its own hard drive, and it starts at 10% then also.

Thoughts:

I believe the provblem is related to the vmfstools starting the counting at 10%.  Even so, it doesn't fail all VMs it backs up, and it backs it up fine to a local directory.  I've never experienced anything like this before.  ESXi normally just works.  If you know what the problem is, I'd greatly appreciate your help.

Thanks!