There's a CQL version constant in query processor. Use it when
advertising CQL version to clients.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
This patch adds initial support for PREPARE and EXECUTE requests which
are used by the CQL binary protocol for prepared statements. The use of
prepared statement gives a nice 2.5x single core performance boost for
Urchin:
$ ./build/release/seastar --data data --smp 1
$ ./tools/bin/cassandra-stress write -mode cql3 simplenative -rate threads=32
Results:
op rate : 31728
partition rate : 31728
row rate : 31728
latency mean : 1.0
latency median : 0.9
latency 95th percentile : 1.8
latency 99th percentile : 1.8
latency 99.9th percentile : 5.6
latency max : 181.7
Total operation time : 00:00:30
END
$ ./tools/bin/cassandra-stress write -mode cql3 simplenative prepared -rate threads=32
Results:
op rate : 75033
partition rate : 75033
row rate : 75033
latency mean : 0.4
latency median : 0.4
latency 95th percentile : 0.7
latency 99th percentile : 0.8
latency 99.9th percentile : 3.4
latency max : 205.0
Total operation time : 00:00:30
END
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Data type objects are thread-local so the lookup map also needs to be
thread-local. Fixes SMP issues when prepared statements are enabled
which exercise the type encoders.
Spotted by Tomek.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
The in-wire protocol wants raw bytes, not hex representation. Broken by
commit a2519926a6 ("db: add some iostream
output operators").
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Preparation for range queries, from Tomasz:
"This series adds static typic for different key variants.
It also changes clustered row map to boost implementation which allows to use
heterogenous keys, so that we can lookup a row by a full prefix without
reserializing it.
Similar change is made to row prefix tombstones."
If receiver type is not a collection type, we need to return early; not
the other way around.
Fixes SIGSEGV with cassandra-stress when prepared statements are
enabled.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
There's a cyclic dependency between cql3 and transport namespaces when
we introduce prepared statements. The latter pulls
parsed_statement::prepared from the former. Break the cycle by using
a forward delcaration in cql_statement.hh.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Query processor needs to store prepared statements as part of a client
session for PREPARE and EXECUTE requests. Switch from unique_ptr to
shared_ptr in preparation for that.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
std::map<> does not support lookup using different comparator than the
one used to compare keys. For range prefix queries and for row prefix
tombstone queries we will need to perform lookups using different
comparators.
Holding keys and their prefixes as "bytes" is error prone. It's easy
to mix them up (or use wrong types). This change adds wrappers for
keys with accessors which are meant to make misuses as difficult as
possible.
Prefix and full keys are now distinguished. Places which assumed that
the representation is the same (it currently is) were changed not to
do so. This will allow us to introduce more compact storage for non-prefix
keys.
From Avi:
The protocol_version variable is problematic for two reasons:
- as an integer, it can get confused with a nearby unrelated integer argument
- it represents a layering violation, where the transport protocol leaks into
the database layer
Fix by abstracting it with a new serialization_format class. The transport
layer converts protocol_version to serialization_format.
This is an abstraction layer boundary between transport and the rest of the
code. Instead of the protocol version permeating through the code, encapsulate
it in a serialization_format variable.
This is intended to replace all uses of protocol_version outside transport.
