In both preparing for a data migration between filers as well as assessing a new backup program we've been comparing different backup tools. We're trying to rectify why different backup tools report wide variations in the amount of data they copy.

Here's the setup. One F720 filer with two FC9 shelves attached. One volume (vol0) of approx. 180GB with 23 qtrees. Nfs-only, no CIFS.

The volume report from FilerView reports there is 47GB of the 180GB total available.

From the Unix admin host a df reports vol0 is 180GB and 140GB is used. The df also reports .snapshot is 33.3GB with 10GB used.

Question 1: Why the difference in used and available space between the FilerView report and df?

We employed three different backup tools to backup the entire volue; ndmpcopy (run from a Unix host, not the built-in Ontap verion), Omniback and Commvault Galaxy. Ndmpcopy was set as a filer to filer copy whereas Omniback and Galaxy backed up to tape. The Omniback and Galaxy backup policy was defined to backup the nightly.0 snapshot of the filer.

After each approach was run ndmpcopy reported it copied approximately 125GB of data, Omniback reported copying approximately 130GB of data and Galaxy reported copying 115GB of data.

Question 2: Why do different backup methodologies report such a wide disparity in the amount of data copied?

Has anyone encountered this before and can provide a rational explanation.

Thanks.

Spencer Kantor Telcordia Technologies