colblk: experiment with potential performance improvements

[RaduBerinde]

This issue is meant to be a running list of ideas to improve performance in the columnar format.

• Don't separate suffix into wall time / logical time / untyped version. The hypothesis is that the current comparison code is too complex and a simple bytes.Compare might be faster [radu] Experimented with this and saw 10-30% regressions in CockroachDataBlockIterShort.
• Add a version-is-not-timestamp column to data blocks and have a fast path for blocks or regions that only have timestamps. This column would be empty for all sql table data.
• Separate prefix and suffix in index blocks and use compressed prefix encoding. The seeking should be faster and we'd be able to use a single-level index in more cases.
• Expose a PrevPrefix operation that uses the prefix changed bitmap to quickly jump to the previous key. The expectation is that this would reduce CPU during reverse scans. I believe MVCC GC currently scans in reverse and could benefit.
• In PrefixBytes.Search try to compare a single byte before calling bytes.Compare.
• Move block properties into BlockPropertyCollector-defined columns. This can allow more compact encoding of properties (eg, MVCC timestamps may benefit from uint delta encoding). Likely a minor benefit, but we would additionally avoid decoding O(n) varints where n is the number of BlockPropertyCollectors
• Stash block decoders in the table cache to avoid the initial parsing of the structure of a block on block cache hits

Jira issue: PEBBLE-273