This was my thoughts as well; was just trying to get back to my initial question.
Interesting. I know when we enabled the cache on vb we saw significant improvement on the load of our db node. So the fact that the cache is not used on XF caused me concern. While load is not as high as vb pre-cache, we are seeing a higher average load than before our switch. I'd love to see some benchmarks supporting disabling the cache.
Code:
mysql> show variables like '%query_cache%';
+------------------------------+-----------+
| Variable_name | Value |
+------------------------------+-----------+
| have_query_cache | YES |
| query_cache_limit | 1048576 |
| query_cache_min_res_unit | 4096 |
| query_cache_size | 536870912 |
| query_cache_type | ON |
| query_cache_wlock_invalidate | OFF |
+------------------------------+-----------+