Interesting speed difference

[readie]

I have two very similar backup jobs, each with 16 VMs, general purpose servers, using the same Veeam server and proxies and target. However, the stats are quite different . .
job 1 - Processed 1.6TB, Read 57GB, Transferred 22.7GB (2.5x), Duration 2:40:57, Processing rate 16MB/s, Bottleneck Target (22%, 4%, 51%, 54%)
job 2 - Processed 975GB, Read 170GB, Transferred 20.8GB (8.2x), Duration 1:08:35, Processing rate 54MB/s, Bottleneck Source (48%, 5%, 47%, 35%)

OK so the jobs are somewhat different, but job 2 reads over 3 times as much data, compresses at 8.2x rather than 2.5x, and Processing rate is over 3x as fast. Is the processing that much faster because the compression is much better for some reason?
What further diagnosis can I do to see why one is so much faster, or is it just down to the type of data on the VMs?
Bob

[foggy]

is it just down to the type of data on the VMs?

To a large extent. Various processing rate for different VMs is expected, think amount of changed blocks, their compressibility, inline deduplication, etc. There're also a number of other factors.

Btw, make sure CBT is enabled for both jobs, so you're comparing apples to apples.