If you run a manual compaction with nodetool each CF will be compacted to a
single SSTable.
Not that this is not normally recommended as it means that automatic compaction
will take a long time to get to the file.
Take a look at nodetool cfhistograms to get an idea of how spread out your dat
Cassandra has no way of knowing that all the data is in the most recent
sstable, and will have to check the others too, and this bring a lot of
difficulty to data compaction.
I have a question that if I want a high performance data compaction, how can I
implement that all the columns are all
