From 0bd27dea0aa5f2623d1e3a1aed60a29379f8487a Mon Sep 17 00:00:00 2001
From: Zhang Lei <xiaolei.zl@alibaba-inc.com>
Date: Thu, 5 Sep 2024 14:06:23 +0800
Subject: [PATCH] feat(interactive): Support customizing service configuration
 via `gsctl` (#4205)

The customized engine configuration can be specified during the
deployment of the interactive instance.
- [x] Add CI test verify it works
---
 .github/workflows/flex-interactive.yml  |  5 +-
 docs/flex/interactive/configuration.md  | 84 ++++++++-----------------
 python/graphscope/gsctl/commands/dev.py | 31 ++++++++-
 3 files changed, 60 insertions(+), 60 deletions(-)

diff --git a/.github/workflows/flex-interactive.yml b/.github/workflows/flex-interactive.yml
index 37ca3a52fd53..24e291eab1a7 100644
--- a/.github/workflows/flex-interactive.yml
+++ b/.github/workflows/flex-interactive.yml
@@ -54,10 +54,13 @@ jobs:
         # install gsctl
         python3 -m pip install ${GITHUB_WORKSPACE}/python/dist/*.whl
         # launch service: 8080 for coordinator http port; 7687 for cypher port;
-        docker run -p 8080:8080 -p 7688:7687 graphscope/interactive:latest --enable-coordinator &
+        gsctl instance deploy --type interactive --image-registry graphscope --image-tag latest --interactive-config ${GITHUB_WORKSPACE}/flex/tests/hqps/interactive_config_test.yaml
         sleep 20
         # test
         python3 -m pip install --no-cache-dir pytest pytest-xdist
         python3 -m pytest -d --tx popen//python=python3 \
                           -s -v \
                           $(dirname $(python3 -c "import graphscope.gsctl as gsctl; print(gsctl.__file__)"))/tests/test_interactive.py
+
+        # destroy instance
+        gsctl instance destroy --type interactive -y
diff --git a/docs/flex/interactive/configuration.md b/docs/flex/interactive/configuration.md
index a75ca8396840..79729dca1e80 100644
--- a/docs/flex/interactive/configuration.md
+++ b/docs/flex/interactive/configuration.md
@@ -15,12 +15,13 @@ Below is a list of all configurable items:
 | admin-port       | 7777    | The port of the interactive admin service       | v0.3          |
 | storedproc-port   | 10000    | The port of the interactive stored procedure service      | v0.3          |
 | cypher-port       | 7687    | The port of the cypher service       | v0.3          |
+| config             | None    | The customized configuration file for engine interactive service | v0.4   |
 <!-- | gremlin-port       | None    | The port of the gremlin service       | v0.3          | -->
 
 
 <!-- *Note: The default value for `gremlin-port` is `None`, meaning the Gremlin service will not be initiated by default. -->
 
-### Default Ports
+### Ports
 
 By default, Interactive will launch the following services on these ports:
 
@@ -43,74 +44,46 @@ The Gremlin service is disabled by default. To enable it, add the `--gremlin-por
 gsctl instance deploy --type interactive --coordinator-port 8081 --admin-port 7778 --cypher-port 7688 --storedproc-port 10001 --gremlin-port 8183
 ``` -->
 
+### Service Configuration
 
-<!-- Those content are commented but not deleted, since we will support those configurations later.
-> TODO: Currently `gsctl` doesn't support the following command!
+By default, `Interactive` will initialize the service with its default settings.
+However, GraphScope Interactive is designed to be flexible and adaptable to your specific needs. This means you can tailor the service's behavior using custom configurations.
 
-Starting your GraphScope Interactive service can be straightforward, as demonstrated in our [getting_started](./getting_started.md) guide. By default, executing the command:
 
-```bash
-gsctl use GRAPH <name>
-```
-
-will initialize the service with its default settings. However, GraphScope is designed to be flexible and adaptable to your specific needs. This means you can tailor the service's behavior using custom configurations.
-
-## Customizing Your Service Configuration
-To customize the service's settings, you can provide a YAML configuration file. This file allows you to specify various parameters, from directory paths to log levels, ensuring the service aligns with your requirements. To use a custom configuration, simply pass the YAML file to the command as follows:
+#### Customizing Your Service Configuration
+To customize the service's settings, you can provide a YAML configuration file `interactive_config.yaml`. This file allows you to specify various parameters, from directory paths to log levels, ensuring the service aligns with your requirements. To use a custom configuration, simply pass the YAML file to the command as follows:
 
 ```bash
-gsctl use GRAPH <name> -c ./interactive_config.yaml
+gsctl instance deploy --type interactive --config ./interactive_config.yaml
 ```
 
-Note: Please be aware that you're not required to configure every option. Simply adjust the settings that are relevant to your needs. Any options left unconfigured will automatically adopt their default values, as detailed in the sections that follow.
-
-
-If you already have an Interactive service running and wish to apply a new set of configurations, a simple restart with the custom configuration is required. This ensures that the service updates its settings and operates according to your newly specified preferences.
-
-To restart the service with your custom configuration, use the following command:
-```bash
-gsctl service restart -c ./conf/interactive_config.yaml
+```{note}
+Please be aware that you're not required to configure every option. Simply adjust the settings that are relevant to your needs. Any options left unconfigured will automatically adopt their default values, as detailed in the following sections.
 ```
-Remember, any changes made in the configuration file will only take effect after the service has been restarted with the updated file.
 
 
 
-## Sample Configuration
+##### Sample Configuration
 Here's a glimpse of what a typical YAML configuration file might look like:
 
 ```yaml
-log_level: INFO # default INFO
-verbose_level: 2 # verbose all logs above level 2(including)
+log_level: INFO # default INFO, available(INFO,WARNING,ERROR,FATAL)
+verbose_level: 0 # default 0, should be a int in range [0,10]. 10 will verbose all logs
 compute_engine:
-  thread_num_per_worker: 1  # the number of shared workers, default 1
+  thread_num_per_worker: 1  # the number of threads for each worker, default 1
 compiler:
   planner:
-  is_on: true
-  opt: RBO
-  rules:
-    - FilterMatchRule
-    - FilterIntoJoinRule
-    - NotExistToAntiJoinRule
+    is_on: true
+    opt: RBO
+    rules:
+      - FilterMatchRule
+      - FilterIntoJoinRule
+      - NotExistToAntiJoinRule
   query_timeout: 20000  # query timeout in milliseconds, default 20000
-  endpoint:
-    default_listen_address: localhost
-    bolt_connector: # cypher query endpoint 
-      disabled: false # disable cypher endpoint or not.
-      port: 7687
-    gremlin_connector: # gremlin query endpoint 
-      disabled: false # disable gremlin endpoint or not.
-      port: 8182
-http_service:
-  default_listen_address: localhost
-  admin_port: 7777
-  query_port: 10000
 ```
 
 
-## Available Configurations
-For configurations associated with the root directory, we do not accept relative paths to ensure consistency.
-
-### Service configurations
+##### Available Configurations
 
 In this following table, we use the `.` notation to represent the hierarchy within the `YAML` structure.
 
@@ -119,20 +92,17 @@ In this following table, we use the `.` notation to represent the hierarchy with
 | --------           | --------  | -------- |-----------  |
 | log_level     |  INFO   | The level of database log, INFO/WARNING/ERROR/FATAL | 0.0.1 |
 | verbose_level     |  0   | The verbose level of database log, should be a int | 0.0.3 |
-|default_graph  | modern | The name of default graph on which to start the graph service. | 0.0.1 |
 | compute_engine.thread_num_per_worker | 1 | The number of threads will be used to process the queries. Increase the number can benefit the query throughput | 0.0.1 |
 | compiler.planner.is_on | true | Determines if query optimization is enabled for compiling Cypher queries  | 0.0.1 |
 | compiler.planner.opt | RBO | Specifies the optimizer to be used for query optimization. Currently, only the Rule-Based Optimizer (RBO) is supported | 0.0.1 |
 | compiler.planner.rules.FilterMatchRule | N/A | An optimization rule that pushes filter (`Where`) conditions into the `Match` clause | 0.0.1 |
 | compiler.planner.rules.FilterIntoJoinRule | N/A | A native Calcite optimization rule that pushes filter conditions to the Join participants before performing the join | 0.0.1 |
 | compiler.planner.rules.NotMatchToAntiJoinRule | N/A | An optimization rule that transforms a "not exist" pattern into an anti-join operation  | 0.0.1 |
-| compiler.endpoint.default_listen_address | localhost | The address for compiler endpoint to bind | 0.0.3 |
-| compiler.endpoint.bolt_connector.disabled | false | Whether to disable the cypher endpoint| 0.0.3 |
-| compiler.endpoint.bolt_connector.port | 7687 | The port for compiler's cypher endpoint.| 0.0.3 |
-| compiler.endpoint.gremlin_connector.disabled | true | Whether to disable the gremlin endpoint| 0.0.3 |
-| compiler.endpoint.gremlin_connector.port | 8182 | The port for compiler's cypher endpoint.| 0.0.3 |
-| http_service.default_listen_address | localhost | The address for http service to bind | 0.0.2 |
-| http_service.admin_port | 7777 | The port for admin service to listen on | 0.0.2 |
-| http_service.query_port | 10000 | The port for query service to listen on, for stored procedure queries, user can directory submit queries to query_port without compiler involved | 0.0.2 | -->
+| compiler.query_timeout  | 3000000   ｜ The maximum time for compiler to wait engine's reply, in `ms`  | 0.0.3 | 
+
+#### TODOs
 
+We currently only allow service configuration during instance deployment. In the near future, we will support:
 
+- Graph-level configurations
+- Modifying service configurations
\ No newline at end of file
diff --git a/python/graphscope/gsctl/commands/dev.py b/python/graphscope/gsctl/commands/dev.py
index 8744b46f1df3..4b1ec9ad91d0 100644
--- a/python/graphscope/gsctl/commands/dev.py
+++ b/python/graphscope/gsctl/commands/dev.py
@@ -42,6 +42,7 @@
 # Interactive docker container config
 INTERACTIVE_DOCKER_CONTAINER_NAME = "gs-interactive-instance"
 INTERACTIVE_DOCKER_CONTAINER_LABEL = "flex=interactive"
+INTERACTIVE_DOCKER_DEFAULT_CONFIG_PATH = "/opt/flex/share/interactive_config.yaml"
 
 scripts_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "..", "scripts")
 install_deps_script = os.path.join(scripts_dir, "install_deps.sh")
@@ -182,6 +183,12 @@ def interactive(app, graphscope_repo):
     show_default=True,
     required=False,
 )
+@click.option(
+    "--interactive-config",
+    help="Interactive config file path [docker only]",
+    required=False,
+    default=None,
+)
 @click.option(
     "--gremlin-port",
     help="Mapping port of gremlin query, -1 means disable mapping [docker only]",
@@ -220,6 +227,7 @@ def deploy(
     storedproc_port,
     cypher_port,
     gremlin_port,
+    interactive_config,
 ):  # noqa: F811
     """Deploy a GraphScope Flex instance"""
     cmd = []
@@ -244,6 +252,17 @@ def deploy(
         if gremlin_port != -1:
             cmd.extend(["-p", f"{gremlin_port}:8182"])
         image = f"{image_registry}/{type}:{image_tag}"
+        if interactive_config is not None:
+            if not os.path.isfile(interactive_config):
+                click.secho(
+                    f"Interactive config file {interactive_config} does not exist.",
+                    fg="red",
+                )
+                return
+            interactive_config = os.path.abspath(interactive_config)
+            cmd.extend(
+                ["-v", f"{interactive_config}:{INTERACTIVE_DOCKER_DEFAULT_CONFIG_PATH}"]
+            )
         cmd.extend([image, "--enable-coordinator"])
     returncode = run_shell_cmd(cmd, os.getcwd())
     if returncode == 0:
@@ -293,9 +312,17 @@ def deploy(
     show_default=True,
     required=False,
 )
-def destroy(type, container_name):
+@click.option(
+    "-y",
+    "--yes",
+    is_flag=True,
+    default=False,
+    help="Do not ask for confirmation",
+    required=False,
+)
+def destroy(type, container_name, yes):
     """Destroy Flex Interactive instance"""
-    if click.confirm(f"Do you want to destroy {container_name} instance?"):
+    if yes or click.confirm(f"Do you want to destroy {container_name} instance?"):
         cmd = []
         if type == "interactive":
             cmd = [