test: add Kafka consumer-group, add-partition tests (inline style) (r…

…isingwavelabs#16244)

Signed-off-by: xxchan <[email protected]>

Makefile.toml

@@ -15,6 +15,7 @@ extend = [
   { path = "src/storage/backup/integration_tests/Makefile.toml" },
   { path = "src/java_binding/make-java-binding.toml" },
   { path = "src/stream/tests/integration_tests/integration_test.toml" },
+  { path = "e2e_test/source_inline/commands.toml" },
 ]
 
 env_files = ["./risedev-components.user.env"]
@@ -1292,7 +1293,7 @@ echo "All processes has exited."
 [tasks.slt]
 env = { SLT_HOST = "${RISEDEV_RW_FRONTEND_LISTEN_ADDRESS}", SLT_PORT = "${RISEDEV_RW_FRONTEND_PORT}", SLT_DB = "dev" }
 category = "RiseDev - Test - SQLLogicTest"
-install_crate = { version = "0.20.0", crate_name = "sqllogictest-bin", binary = "sqllogictest", test_arg = [
+install_crate = { version = "0.20.1", crate_name = "sqllogictest-bin", binary = "sqllogictest", test_arg = [
   "--help",
 ], install_command = "binstall" }
 dependencies = ["check-risedev-env-file"]

ci/Dockerfile

@@ -18,6 +18,15 @@ RUN apt-get update -yy && \
     && rm -rf /var/lib/{apt,dpkg,cache,log}/
 ENV PYO3_PYTHON=python3.12
 
+# Install nvm and zx
+ENV NVM_DIR /root/.nvm
+ENV NODE_VERSION 20.11.1
+RUN curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash \
+  && . $NVM_DIR/nvm.sh \
+  && nvm install $NODE_VERSION
+ENV PATH $NVM_DIR/versions/node/v$NODE_VERSION/bin:$PATH
+RUN npm install -g zx
+
 SHELL ["/bin/bash", "-c"]
 
 RUN mkdir -p /risingwave
@@ -43,6 +52,16 @@ RUN pip3 install --break-system-packages pyarrow pytest
 
 # Install poetry
 RUN curl -sSL https://install.python-poetry.org | python3 -
+# Install rpk
+RUN if [ "$(uname -m)" = "amd64" ] || [ "$(uname -m)" = "x86_64" ]; then \
+        curl -LO https://github.com/redpanda-data/redpanda/releases/latest/download/rpk-linux-amd64.zip && \
+        unzip rpk-linux-amd64.zip -d ~/.local/bin/ && \
+        rm rpk-linux-amd64.zip; \
+    else \
+        curl -LO https://github.com/redpanda-data/redpanda/releases/latest/download/rpk-linux-arm64.zip && \
+        unzip rpk-linux-arm64.zip -d ~/.local/bin/ && \
+        rm rpk-linux-arm64.zip; \
+    fi
 ENV PATH /root/.local/bin:$PATH
 
 ENV CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
@@ -51,7 +70,7 @@ ENV CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
 RUN curl -L --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/cargo-bins/cargo-binstall/main/install-from-binstall-release.sh | bash
 RUN cargo binstall -y --no-symlinks cargo-llvm-cov cargo-nextest cargo-hakari cargo-sort cargo-cache cargo-audit \
     [email protected] \
-    sqllogictest-bin@0.19.1 \
+    sqllogictest-bin@0.20.1 \
     [email protected] \
     && cargo cache -a \
     && rm -rf "/root/.cargo/registry/index" \

ci/build-ci-image.sh

@@ -10,7 +10,7 @@ cat ../rust-toolchain
 # shellcheck disable=SC2155
 
 # REMEMBER TO ALSO UPDATE ci/docker-compose.yml
-export BUILD_ENV_VERSION=v20240413
+export BUILD_ENV_VERSION=v20240414_x
 
 export BUILD_TAG="public.ecr.aws/w1p7b4n3/rw-build-env:${BUILD_ENV_VERSION}"
 

ci/docker-compose.yml

@@ -71,7 +71,7 @@ services:
       retries: 5
 
   source-test-env:
-    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240413
+    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240414_x
     depends_on:
       - mysql
       - db
@@ -84,7 +84,7 @@ services:
       - ..:/risingwave
 
   sink-test-env:
-    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240413
+    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240414_x
     depends_on:
       - mysql
       - db
@@ -103,12 +103,12 @@ services:
 
 
   rw-build-env:
-    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240413
+    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240414_x
     volumes:
       - ..:/risingwave
 
   ci-flamegraph-env:
-    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240413
+    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240414_x
     # NOTE(kwannoel): This is used in order to permit
     # syscalls for `nperf` (perf_event_open),
     # so it can do CPU profiling.
@@ -119,7 +119,7 @@ services:
       - ..:/risingwave
 
   regress-test-env:
-    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240413
+    image: public.ecr.aws/w1p7b4n3/rw-build-env:v20240414_x
     depends_on:
       db:
         condition: service_healthy

ci/scripts/e2e-source-test.sh

@@ -152,7 +152,7 @@ risedev ci-kill
 
 echo "--- e2e, ci-kafka-plus-pubsub, kafka and pubsub source"
 RUST_LOG="info,risingwave_stream=info,risingwave_batch=info,risingwave_storage=info" \
-risedev ci-start ci-pubsub
+risedev ci-start ci-pubsub-kafka
 ./scripts/source/prepare_ci_kafka.sh
 cargo run --bin prepare_ci_pubsub
 risedev slt './e2e_test/source/basic/*.slt'
@@ -168,6 +168,9 @@ echo "--- e2e, kafka alter source again"
 ./scripts/source/prepare_data_after_alter.sh 3
 risedev slt './e2e_test/source/basic/alter/kafka_after_new_data_2.slt'
 
+echo "--- e2e, inline test"
+risedev slt './e2e_test/source_inline/**/*.slt'
+
 echo "--- Run CH-benCHmark"
 risedev slt './e2e_test/ch_benchmark/batch/ch_benchmark.slt'
 risedev slt './e2e_test/ch_benchmark/streaming/*.slt'

e2e_test/source/README.md

@@ -1,3 +1,7 @@
+> [!NOTE]
+>
+> Please write new tests according to the style in `e2e_test/source_inline`.
+
 Test in this directory needs some prior setup.
 
 See also `ci/scripts/e2e-source-test.sh`, and `scripts/source`

e2e_test/source_inline/README.md

@@ -0,0 +1,30 @@
+# "Inline" style source e2e tests
+
+Compared with prior source tests ( `e2e_test/source` ), tests in this directory are expected to be easy to run locally and easy to write.
+
+Refer to https://github.com/risingwavelabs/risingwave/issues/12451#issuecomment-2051861048 for more details.
+
+## Install Dependencies
+
+Some additional tools are needed to run the `system` commands in tests.
+
+- `rpk`: Redpanda (Kafka) CLI toolbox. https://docs.redpanda.com/current/get-started/rpk-install/
+- `zx`: A tool for writing better scripts. `npm install -g zx`
+
+## Run tests
+
+To run locally, use `risedev d` to start services (including external systems like Kafka and Postgres, or specify `user-managed` to use your own service).
+Then use `risedev slt` to run the tests, which will load the environment variables (ports, etc.)
+according to the services started by `risedev d` .
+
+```sh
+risedev slt 'e2e_test/source_inline/**/*.slt'
+```
+
+## Write tests
+
+To write tests, please ensure each file is self-contained and does not depend on running external scripts to setup the environment.
+
+Use `system` command to setup instead.
+For simple cases, you can directly write a bash command;
+For more complex cases, you can write a test script (with any language like bash, python, zx), and invoke it in the `system` command.

e2e_test/source_inline/commands.toml

@@ -0,0 +1,107 @@
+# This file contains commands used by the tests.
+
+[tasks.source-test-hook]
+private = true
+dependencies = ["check-risedev-env-file"]
+env_files = ["${PREFIX_CONFIG}/risedev-env"]
+
+# Note about the Kafka CLI tooling:
+# - Built-in Kafka console tools:
+#       Java based.
+#       Style example: kafka-topics.sh --bootstrap-server localhost:9092 --topic t --create
+#       Some limitations: cannot disable logging easily, cannot consume to end and then exit.
+# - kcat:
+#       C based (rdkafka)
+#       Some limitations: cannot do admin operations, only consume/produce.
+# - rpk:
+#       Golang based.
+#       Style example: RPK_BROKERS=localhost:9092 rpk topic create t
+[tasks.kafka-hook]
+private = true
+description = "Check if Kafka is started by RiseDev"
+dependencies = ["source-test-hook"]
+script = '''
+#!/usr/bin/env sh
+set -e
+
+if [ ! -d "${PREFIX_BIN}/kafka" ]; then
+    echo "Kafka is not installed in ${PREFIX_BIN}/kafka. Did you enable Kafka using $(tput setaf 4)\`./risedev configure\`$(tput sgr0)?"
+    exit 1
+fi
+
+if [ -z "${RISEDEV_KAFKA_BOOTSTRAP_SERVERS}" ]; then
+    echo "RISEDEV_KAFKA_BOOTSTRAP_SERVERS is not set in risedev-env file. Did you start Kafka using $(tput setaf 4)\`./risedev d\`$(tput sgr0)?"
+    exit 1
+fi
+'''
+
+[tasks.clean-kafka]
+category = "RiseDev - Test - Source Test - Kafka"
+description = "Delete all kafka topics."
+dependencies = ["kafka-hook"]
+command = "rpk"
+args = ["topic", "delete", "-r", "*"]
+
+[tasks.kafka-topics]
+category = "RiseDev - Test - Source Test - Kafka"
+dependencies = ["kafka-hook"]
+script = """
+#!/usr/bin/env sh
+set -e
+${PREFIX_BIN}/kafka/bin/kafka-topics.sh --bootstrap-server ${RISEDEV_KAFKA_BOOTSTRAP_SERVERS} "$@"
+"""
+
+[tasks.kafka-produce]
+category = "RiseDev - Test - Source Test - Kafka"
+dependencies = ["kafka-hook"]
+script = """
+#!/usr/bin/env sh
+set -e
+${PREFIX_BIN}/kafka/bin/kafka-console-producer.sh --bootstrap-server ${RISEDEV_KAFKA_BOOTSTRAP_SERVERS} "$@"
+"""
+
+[tasks.kafka-consume]
+category = "RiseDev - Test - Source Test - Kafka"
+dependencies = ["kafka-hook"]
+script = """
+#!/usr/bin/env sh
+set -e
+${PREFIX_BIN}/kafka/bin/kafka-console-consumer.sh --bootstrap-server ${RISEDEV_KAFKA_BOOTSTRAP_SERVERS} "$@"
+"""
+
+[tasks.kafka-consumer-groups]
+category = "RiseDev - Test - Source Test - Kafka"
+dependencies = ["kafka-hook"]
+script = """
+#!/usr/bin/env sh
+set -e
+${PREFIX_BIN}/kafka/bin/kafka-consumer-groups.sh --bootstrap-server ${RISEDEV_KAFKA_BOOTSTRAP_SERVERS} "$@"
+"""
+
+# rpk tools
+[tasks.rpk]
+category = "RiseDev - Test - Source Test - Kafka"
+dependencies = ["kafka-hook"]
+# check https://docs.redpanda.com/current/reference/rpk/rpk-x-options/ or rpk -X help/list for options
+script = """
+#!/usr/bin/env sh
+set -e
+
+if [ -z "$(which rpk)" ]; then
+    echo "rpk is not installed. Install it via https://docs.redpanda.com/current/get-started/rpk-install/"
+    exit 1
+fi
+
+rpk "$@"
+"""
+
+[tasks.redpanda-console]
+category = "RiseDev - Test - Source Test - Kafka"
+description = "Start Redpanda console (Kafka GUI) at localhost:8080."
+dependencies = ["kafka-hook"]
+script = '''
+#!/usr/bin/env sh
+set -e
+echo "$(tput setaf 2)Start Redpanda console at http://localhost:8080$(tput sgr0)"
+docker run --network host -e KAFKA_BROKERS=$RPK_BROKERS docker.redpanda.com/redpandadata/console:latest
+'''

e2e_test/source_inline/kafka/add_partition.slt

@@ -0,0 +1,74 @@
+# Note: control substitution on will force us to use "\\n" instead of "\n" in commands
+control substitution on
+
+system ok
+rpk topic create test_add_partition -p 3
+
+system ok
+cat <<EOF | rpk topic produce test_add_partition -f "%p %v\\n" -p 0
+0 {"x":"a"}
+1 {"x":"b"}
+2 {"x":"c"}
+EOF
+
+statement ok
+CREATE SOURCE s(x varchar)
+WITH(
+    ${RISEDEV_KAFKA_WITH_OPTIONS_COMMON},
+    topic = 'test_add_partition',
+    scan.startup.mode = 'earliest',
+) FORMAT PLAIN ENCODE JSON;
+
+statement ok
+CREATE MATERIALIZED VIEW mv AS SELECT * from s;
+
+query ?
+SELECT * FROM s order by x;
+----
+a
+b
+c
+
+sleep 2s
+
+query ?
+SELECT * FROM mv order by x;
+----
+a
+b
+c
+
+system ok
+rpk topic add-partitions test_add_partition --num 1
+
+system ok
+cat <<EOF | rpk topic produce test_add_partition -f "%p %v\\n" -p 0
+3 {"x":"d"}
+EOF
+
+
+query ?
+SELECT * FROM s order by x;
+----
+a
+b
+c
+d
+
+# It needs some time for the split change to be reflected in MV
+sleep 40s
+
+query ?
+SELECT * FROM mv order by x;
+----
+a
+b
+c
+d
+
+
+statement ok
+DROP SOURCE s CASCADE;
+
+system ok
+rpk topic delete test_add_partition