mirror of
https://github.com/featurebasedb/featurebase.git
synced 2026-10-13 14:28:02 +00:00
* Introduce ServiceManager and Refactor DAX Integration tests The ServiceManager provides an interface with which to manage featurebase (dax) services (mds, queryer, computer). It replaces the confusing interface implementations in /dax/server/server.go (which optionally used pointers to in-process objects to satisfy an interface) with (for now) http implementations. The thought is that even if we're running all services in-process, we should communicate between services over http in order to mirror what we would do in a production environment where the services are running on different nodes. This batch of commits does quit a lot, most of which is captured here: - Added `path` support to `dax.Address`. Address is now a string of the form [scheme]://[host]:[port]/[path]. - Added `Holder.directiveApplied` to determine (in tests) if the computer has completed applying the latest directive. This is somewhat temporary until we improve the mds-to-computer logic. - Removed the "service prefix" code which was prepending client URL paths with the prefix. Instead, the serviceType (mds, queryer, computer[n] is now part of `dax.Address`). - Removed, from the dax config, the top level `StorageMethod` and `StorageDSN` and now just have `MDS.Config.DataDir`. - Added `Computer.Config.N` to specify the number of computers to run in-process. - Moved the `pilosa.MDS` interface to `computer.Registrar`. This is an example of getting the interfaces defined in the right packages. - Added `SnapshotTable()` method to the mds client (to align with its API). - Changed `Balancer.AddJob()` to `Balancer.AddJobs()` to support, for example, adding 256 partitions in a single call. Refactored some of the naive Balancer to account for this. - Added a `Seed` to the top-level config. It's not really useful because of package `crypto/rand`. - Added an in-memory implementation of the DisCo interface and disabled etcd in a computer service. - Create sepearte data-dirs for each in-process computer. - Disabled grpc in dax. - Modified the sql3 test definition format to support multiple insert steps and separate query results (to align with those steps). * Changes necessary to get multiple computer instance running in-process For now the config looks like this: ``` [computer] run = true n = 4 ``` but we can probably just change that to be something like: ``` [computer] run = 4 ``` *Issues found running multiple "computers" in-process* - grpc was trying to bind on the same port - changed GRPCListener from `*net.TCPListener` to `net.Listener` - created a nopListener and set to that for now (i.e. disabled grpc) - etcd was starting more than once - changed dax to use in-memory implementations of the disco interfaces (i.e. stop using etcd) - IDAllocator (which uses boltdb) was trying to open the `idalloc.db` file more than once - realized we have to set separate data-dirs for each holder. that fixed it. * Port dax integration tests to ManagedCommand * Modify Balancer-related methods like AddJob to AddJobs There were (and still are) a lot of places where we were adding on job at a time, even when we had a long list of jobs to add. This resulted in every job add (for example adding 1 of 256 shards) taking ~40ms, or over 10s to create a keyed table. One reason was because each job add was making multiple boltdb transactions. * Port over more dax integration test stuff * Add DirectiveApplied to signify that snapshot/writes have loaded. We use this in tests to avoid using sleeps. This should be considered temporary; we're going to need a more robust solution for determining when a computer node is ready to serve complete data. * Finish porting dax integration tests * Improve godocs * Remove docker-based DAX integration tests. * go mod tidy * Move test/managed.go to avoid package conflicts * Modify IDK integration tests to work with ServiceManager changes This is really just computer -> computer0 And the MDS DataDir config change. * cleanup found during review * echo $CI_COMMIT_REF_SLUG in CI * remove docker image arg, use build instead
153 lines
5 KiB
YAML
153 lines
5 KiB
YAML
version: '3'
|
|
|
|
services:
|
|
postgres:
|
|
image: postgres
|
|
environment:
|
|
POSTGRES_DB: postgres
|
|
POSTGRES_USER: postgres
|
|
POSTGRES_PASSWORD: password
|
|
zookeeper:
|
|
image: confluentinc/cp-zookeeper:${CONFLUENT_VERSION:-5.5.3}
|
|
environment:
|
|
ZOOKEEPER_CLIENT_PORT: 2181
|
|
KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/jaas_kafka_broker.conf"
|
|
volumes:
|
|
- ./docker-sasl/ssl_keys:/etc/kafka/secrets
|
|
|
|
kafka:
|
|
image: confluentinc/cp-kafka:${CONFLUENT_VERSION:-5.5.3}
|
|
environment:
|
|
KAFKA_ADVERTISED_LISTENERS: LISTENER_DOCKER_INTERNAL://kafka:19092,LISTENER_DOCKER_EXTERNAL://kafka:9092,LISTENER_DOCKER_EXTERNAL_SSL://kafka:9094
|
|
KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: LISTENER_DOCKER_INTERNAL:PLAINTEXT,LISTENER_DOCKER_EXTERNAL:PLAINTEXT,LISTENER_DOCKER_EXTERNAL_SSL:SASL_SSL
|
|
KAFKA_INTER_BROKER_LISTENER_NAME: LISTENER_DOCKER_INTERNAL
|
|
KAFKA_ZOOKEEPER_CONNECT: "zookeeper:2181"
|
|
KAFKA_BROKER_ID: 1
|
|
KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
|
|
KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
|
|
KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/jaas_kafka_broker.conf"
|
|
|
|
KAFKA_SASL_ENABLED_MECHANISMS: PLAIN
|
|
KAFKA_SSL_KEYSTORE_FILENAME: broker_kafkaBroker_server.keystore.jks
|
|
KAFKA_SSL_KEYSTORE_CREDENTIALS: credentials
|
|
KAFKA_SSL_KEY_CREDENTIALS: credentials
|
|
|
|
KAFKA_SASL_MECHANISM_INTER_BROKER_PROTOCOL: PLAIN
|
|
volumes:
|
|
- ./docker-sasl/ssl_keys:/etc/kafka/secrets
|
|
|
|
depends_on:
|
|
- zookeeper
|
|
|
|
# UI can be nice for debugging stuff and messing with Kafka. Not used by tests.
|
|
kafka-ui:
|
|
container_name: kafka-ui
|
|
image: provectuslabs/kafka-ui:latest
|
|
ports:
|
|
- 8080:8080
|
|
depends_on:
|
|
- zookeeper
|
|
- kafka
|
|
- schema-registry
|
|
environment:
|
|
KAFKA_CLUSTERS_0_NAME: local
|
|
KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS: kafka:9092
|
|
KAFKA_CLUSTERS_0_ZOOKEEPER: zookeeper:2181
|
|
KAFKA_CLUSTERS_0_JMXPORT: 9997
|
|
KAFKA_CLUSTERS_0_SCHEMAREGISTRY: http://schema-registry:8081
|
|
|
|
schema-registry:
|
|
image: confluentinc/cp-schema-registry:${CONFLUENT_VERSION:-5.5.3}
|
|
environment:
|
|
SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: PLAINTEXT://kafka:19092
|
|
SCHEMA_REGISTRY_HOST_NAME: schema-registry
|
|
SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
|
|
depends_on:
|
|
- zookeeper
|
|
- kafka
|
|
|
|
pilosa:
|
|
#image: registry.gitlab.com/molecula/featurebase/featurebase:linux-amd64-${BRANCH_NAME} # (jaffee) I think we should build directly from this tree rather than pulling the image... makes the local dev flow easier
|
|
build: ..
|
|
environment:
|
|
PILOSA_DATA_DIR: /data
|
|
PILOSA_BIND: 0.0.0.0:10101
|
|
PILOSA_BIND_GRPC: 0.0.0.0:20101
|
|
PILOSA_ADVERTISE: pilosa:10101
|
|
PILOSA_LOOKUP_DB_DSN: "postgresql://postgres:password@postgres:5432/postgres?sslmode=disable"
|
|
depends_on:
|
|
- postgres
|
|
volumes:
|
|
- ./testenv/certs:/certs
|
|
|
|
pilosa-tls:
|
|
#image: registry.gitlab.com/molecula/featurebase/featurebase:linux-amd64-${BRANCH_NAME}
|
|
build: ..
|
|
environment:
|
|
PILOSA_DATA_DIR: /data
|
|
PILOSA_BIND: https://0.0.0.0:10111
|
|
PILOSA_BIND_GRPC: 0.0.0.0:20111
|
|
PILOSA_ADVERTISE: https://pilosa-tls:10111
|
|
PILOSA_TLS_CA_CERTIFICATE: /certs/ca.crt
|
|
PILOSA_TLS_CERTIFICATE: /certs/pilosa-tls.crt
|
|
PILOSA_TLS_KEY: /certs/pilosa-tls.key
|
|
PILOSA_TLS_ENABLE_CLIENT_VERIFICATION: 1
|
|
volumes:
|
|
- ./testenv/certs:/certs
|
|
|
|
pilosa-auth:
|
|
#image: registry.gitlab.com/molecula/featurebase/featurebase:linux-amd64-${BRANCH_NAME}
|
|
build: ..
|
|
environment:
|
|
PILOSA_DATA_DIR: /data
|
|
PILOSA_BIND: 0.0.0.0:10105
|
|
PILOSA_BIND_GRPC: 0.0.0.0:20105
|
|
PILOSA_ADVERTISE: pilosa-auth:10105
|
|
PILOSA_CONFIG: /testdata/featurebase.conf
|
|
volumes:
|
|
- ./testdata:/testdata
|
|
depends_on:
|
|
- fakeidp
|
|
|
|
fakeidp:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile-fakeIDP
|
|
|
|
idk-test:
|
|
build:
|
|
context: ../.
|
|
dockerfile: ./idk/Dockerfile-test
|
|
environment:
|
|
IDK_DEFAULT_SHARD_TRANSACTIONAL: ${IDK_DEFAULT_SHARD_TRANSACTIONAL}
|
|
volumes:
|
|
- ./testenv/certs:/certs
|
|
- ./docker-sasl/ssl_keys:/ssl_keys
|
|
- ./testdata:/testdata
|
|
depends_on:
|
|
#- kafka
|
|
#- postgres
|
|
- fakeidp
|
|
wait:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile-wait
|
|
volumes:
|
|
- ./testenv/certs:/certs
|
|
|
|
dax:
|
|
build:
|
|
context: ..
|
|
dockerfile: Dockerfile-dax
|
|
environment:
|
|
FEATUREBASE_BIND: 0.0.0.0:8080
|
|
FEATUREBASE_VERBOSE: "true"
|
|
FEATUREBASE_QUERYER_RUN: "true"
|
|
FEATUREBASE_MDS_RUN: "true"
|
|
FEATUREBASE_MDS_CONFIG_DATA_DIR: /dax-data/mds
|
|
FEATUREBASE_WRITELOGGER_RUN: "true"
|
|
FEATUREBASE_WRITELOGGER_CONFIG_DATA_DIR: /dax-data/wl
|
|
FEATUREBASE_SNAPSHOTTER_RUN: "true"
|
|
FEATUREBASE_SNAPSHOTTER_CONFIG_DATA_DIR: /dax-data/snaps
|
|
FEATUREBASE_COMPUTER_RUN: "true"
|
|
FEATUREBASE_COMPUTER_CONFIG_DATA_DIR: /dax-data/computer
|