Pg_Upgrade's copies or links user data and index files from the old to the new cluster, and of course this can be slow, especially the default copy mode. Previous releases of pg_upgrade did the copying/linking serially.
Building on my recent pg_upgrade --jobs mode addition, I have just applied a patch to allow each tablespace to be copied/linked in parallel. Here are the performance results with two tablespaces on different magnetic disks, in copy mode:
---- seconds ----
GB git patch
2 62.09 63.75
4 95.93 107.22
8 194.96 195.29
16 494.38 348.93
32 983.28 644.23
64 2227.73 1244.08
128 4735.83 2547.09