Moved setting of configuration variables after the configuration file
has been read.
Updated the code parsing seeds to comply with configuration file format
- seeds: <ip1>,<ip2>,<ip3>
Signed-off-by: Shlomi Livne <shlomi@cloudius-systems.com>
Code calls failure_detector::is_alive on all cpus, so we start
failure_detector on all cpus. However, the internal data of failure_detector
is modified on cpu zero and it is not replicated to non-zero cpus.
This is fine since the user of failure_detector (the gossiper) accesses
it on cpu0 only.
_token_metadata is needed by replication strategy code on all cpus.
Changes to _token_metadata are done on cpu 0. Replicate it to all cpus.
We may copy only if _token_metadata actually changes. As a starter, we
always copy in gossip modification callbacks.
Currently if you run more than one instance on the same machine, they
all bind to the same local address and port (we enable an option that
makes this non error) and cql/thrift requests are distributed randomly
among them.
The API needs the database distribute object to get information from it.
This adds a database reference the API context so it would be
available in the API.
Signed-off-by: Amnon Heiman <amnon@cloudius-systems.com>
Integrate messaging_service and failure_detector and gossiper into urchin.
To start a 3 nodes cluster on a single host:
./seastar --listen-address 127.0.0.1 --seed-provider-parameters 127.0.0.1
./seastar --listen-address 127.0.0.2 --seed-provider-parameters 127.0.0.1
./seastar --listen-address 127.0.0.3 --seed-provider-parameters 127.0.0.1
This adds the API to urchin, all API related files will be placed under
the api directory.
The API server uses a context object to access global parameters,
typically the different servers themselves.
After this patch the api-doc will be available, though empty under:
http://localhost:10000/api-doc
Signed-off-by: Amnon Heiman <amnon@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>
When engine.exit() is used, e.g., on trapping SIGINT, the engine
exits before doing db.stop(), causing an assertion failure.
This patch adds an at_exit([&db] { return db.stop(); }). This means
that before the engine exits, it runs db.stop() and waits for the
future that it returns to be completed. This is exactly what we need.
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
s/database/distributed<database>/ everywhere.
Use simple distribution rules: writes are broadcast, reads are local.
This causes tremendous data duplication, but will change soon.
cql/, where the binary protocol code resides, is too similar to cql3/, where
the grammar lives. Rename it to transport/ to reduce confusion. While the
name isn't perfect, it matches origin.
If data directory does not exist, Urchin starts up without printing
anything and hangs. Make sure the error is shown to user by terminating
the application.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Signed-off-by: Tomasz Grabiec <tgrabiec@cloudius-systems.com>
This patch implement initial support for CQL binary protocol versions 1,
2, 3, and 4. The CQL server is able to handshake with cqlsh and
cassandra-stress from Cassandra 2.1 which uses the STARTUP and OPTIONS
messages. Queries or other functionality is not supported.
To try it out, start Urchin:
$ build/release/seastar --smp 1 --datadir data
CQL server listening on port 9042 ...
Thrift server listening on port 9160 ...
Then try to login with cqlsh:
$ ./bin/cqlsh 127.0.0.1
Urchin side will fail with:
CQL_VERSION => 3.2.0
warning: ignoring event registration
warning: ignoring query SELECT peer, data_center, rack, tokens, rpc_address, schema_version FROM system.peers
seastar: cql/server.cc:222: future<> cql_server::connection::process_query(uint16_t, temporary_buffer<char>&): Assertion `0' failed.
Aborted (core dumped)
TODO:
- Compression is not supported.
- Authentication is not supported.
- Supported options are defined to make cqlsh and cassandra-stress
happy. We really need to decide which CQL versions and compression
algorithms we want to support.
- std::string is used everywhere because sstring does not work with
std::map, std::multimap, and others.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Signed-off-by: Tomasz Grabiec <tgrabiec@cloudius-systems.com>
This patch includes a helper function that executes a function for each entry
in a directory. It is future based and can include in the future, future-based
code to asychronously read, for instance, an sstable.
At the moment, it only scan all keyspaces and make sure they appear in the
keyspaces hash.
Both the database and keyspace classes gain a populate<T> factory that returns a
populated database. At this point, the names found are just listed, but not really
stored anywhere.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
This is the directory from which we will read the sstables.
Code to actually parse them will come later.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
