We want the format of query results to be eventually defined in the
IDL and be independent of the format we use in memory to represent
collections. This change is a step in this direction.
The change decouples format of collection cells in query results from
our in-memory representation. We currently use collection_mutation_view,
after the change we will use CQL binary protocol format. We use that because
it requires less transformations on the coordinator side.
One complication is that some list operations need to retrieve keys
used in list cells, not only values. To satisfy this need, new query
option was added called "collections_as_maps" which will cause lists
and sets to be reinterpreted as maps matching their underlying
representation. This allows the coordinator to generate mutations
referencing existing items in lists.
List operations and prefetching were not handling static columns
correctly. One issue was that prefetching was attaching static column
data to row data using ids which might overlap with clustered columns.
Another problem was that list operations were always constructing
clustering key even if they worked on a static column. For static
columns the key would be always empty and lookup would fail.
The effect was that list operations which depend on curent state had
no effect. Similar problem could be observed on C* 2.1.9, but not on 2.2.3.
Fixes#903.
This gives about 30% increase in tps in:
build/release/tests/perf/perf_simple_query -c1 --query-single-key
This patch switches query result format from a structured one to a
serialized one. The problems with structured format are:
- high level of indirection (vector of vectors of vectors of blobs), which
is not CPU cache friendly
- high allocation rate due to fine-grained object structure
On replica side, the query results are probably going to be serialized
in the transport layer anyway, so this change only subtracts
work. There is no processing of the query results on replica other
than concatenation in case of range queries. If query results are
collected in serialized form from different cores, we can concatenate
them without copying by simply appending the fragments into the
packet. This optimization is not implemented yet.
On coordinator side, the query results would have to be parsed from
the transport layer buffers anyway, so this also doesn't add work, but
again saves allocations and copying. The CQL server doesn't need
complex data structures to process the results, it just goes over it
linearly consuming it. This patch provides views, iterators and
visitors for consuming query results in serialized form. Currently the
iterators assume that the buffer is contiguous but we could easily
relax this in future so that we can avoid linearization of data
received from seastar sockets.
The coordinator side could be optimized even further for CQL queries
which do not need processing (eg. select * from cf where ...) we
could make the replica send the query results in the format which is
expected by the CQL binary protocol client. So in the typical case the
coordinator would just pass the data using zero-copy to the client,
prepending a header.
We do need structure for prefetched rows (needed by list
manipulations), and this change adds query result post-processing
which converts serialized query result into a structured one, tailored
particularly for prefetched rows needs.
This change also introduces partition_slice options. In some queries
(maybe even in typical ones), we don't need to send partition or
clustering keys back to the client, because they are already specified
in the query request, and not queried for. The query results hold now
keys as optional elements. Also, meta-data like cell timestamp and
ttl is now also optional. It is only needed if the query has
writetime() or ttl() functions in it, which it typically won't have.
