This is an automated email from the ASF dual-hosted git repository.
xxyu pushed a commit to branch doc5.0
in repository https://gitbox.apache.org/repos/asf/kylin.git
commit 5221ec3de31e39c43183af24d5809f704295114b
Author: Mukvin <boyboys...@163.com>
AuthorDate: Tue Aug 16 18:10:20 2022 +0800
KYLIN-5221 add operations doc
---
website/docs/configuration/configuration.md | 2 +-
website/docs/configuration/hadoop_queue_config.md | 2 +-
website/docs/configuration/query_cache.md | 2 +-
website/docs/configuration/spark_rpc_encryption.md | 5 +-
.../data-access-control/acl_table.md | 75 +++++
.../access-control/data-access-control/intro.md | 41 +++
.../data-access-control/project_acl.md | 54 ++++
.../operations/access-control/group_management.md | 52 ++++
.../operations/access-control/images/acl_5_en.png | Bin 0 -> 337881 bytes
.../access-control/images/table_acl_1_en.png | Bin 0 -> 70055 bytes
.../access-control/images/table_acl_2_en.png | Bin 0 -> 33907 bytes
.../access-control/images/table_acl_3_en.png | Bin 0 -> 81429 bytes
website/docs/operations/access-control/intro.md | 24 ++
.../operations/access-control/user_management.md | 93 +++++++
.../operations/access-control/users/user_w1.png | Bin 0 -> 30698 bytes
.../operations/access-control/users/user_w2.png | Bin 0 -> 11792 bytes
.../operations/access-control/users/user_w3.png | Bin 0 -> 7887 bytes
.../operations/access-control/users/user_w4.png | Bin 0 -> 9204 bytes
.../operations/access-control/users/user_w5.png | Bin 0 -> 11144 bytes
.../operations/access-control/users/user_w6.png | Bin 0 -> 16649 bytes
.../operations/access-control/users/user_w7.png | Bin 0 -> 16242 bytes
.../operations/access-control/users/user_w8.png | Bin 0 -> 27691 bytes
website/docs/operations/logs/audit_log.md | 208 ++++++++++++++
.../operations/logs/images/after_update_model.png | Bin 0 -> 332033 bytes
.../operations/logs/images/after_update_pwd.png | Bin 0 -> 284440 bytes
.../operations/logs/images/before_update_model.png | Bin 0 -> 339841 bytes
.../operations/logs/images/before_update_pwd.png | Bin 0 -> 292514 bytes
.../docs/operations/logs/images/metadata_table.png | Bin 0 -> 565143 bytes
website/docs/operations/logs/intro.md | 21 ++
website/docs/operations/logs/system_log.md | 249 +++++++++++++++++
website/docs/operations/overview.md | 22 ++
.../images/project_settings_acceleration.png | Bin 213058 -> 0 bytes
.../images/project_settings_acceleration_tips.png | Bin 150813 -> 0 bytes
.../images/project_settings_storage_low_usage.png | Bin 240252 -> 0 bytes
.../images/recommendation_preferences_en.png | Bin 153741 -> 0 bytes
.../images/service_state.en.png | Bin 58508 -> 0 bytes
.../images/storage_quota.en.png | Bin 34171 -> 0 bytes
.../alerting.md | 0
.../project-operation/images/add_project.png | Bin 0 -> 66925 bytes
.../project-operation/images/project_list.png | Bin 0 -> 262909 bytes
.../images/project_settings.png | Bin
.../images/project_settings_basic_general.png | Bin
.../images/project_settings_cc_expose.png | Bin
.../images/project_settings_custom_config.png | Bin
.../project_settings_default_database_en.png | Bin
.../images/project_settings_job_notification.png | Bin
.../project_settings_job_notification_page.png | Bin
.../images/project_settings_model_rewrite.png | Bin
.../images/project_settings_pushdown.png | Bin
.../images/project_settings_segment_en.png | Bin
.../images/project_settings_storage.png | Bin
.../images/project_settings_yarn_queue.png | Bin
.../images/toolbar.en.png | Bin
.../intro.md | 0
.../project-operation/project_management.md | 62 +++++
.../project_settings.md | 0
.../{ => system-operation}/cli_tool/diagnosis.md | 0
.../cli_tool/environment_dependency_check.md | 48 ++++
.../system-operation/cli_tool/images/accept_en.png | Bin 0 -> 76977 bytes
.../system-operation/cli_tool/images/button_en.png | Bin 0 -> 195535 bytes
.../cli_tool/images/rollback_en.png | Bin 0 -> 80422 bytes
.../{ => system-operation}/cli_tool/intro.md | 0
.../cli_tool/metadata_tool/intro.md | 18 ++
.../metadata_tool/metadata_backup_restore.md | 88 ++++++
.../system-operation/cli_tool/rollback.md | 123 +++++++++
.../diagnosis/build_flame_graph.md | 78 ++++++
.../system-operation/diagnosis/diagnosis.md | 86 ++++++
.../diagnosis/images/diagnosis_web_en.png | Bin 0 -> 179703 bytes
.../diagnosis/images/job_diagnosis_web_en.png | Bin 0 -> 141217 bytes
.../diagnosis/images/query_diagnosis_web.png | Bin 0 -> 127898 bytes
.../operations/system-operation/diagnosis/intro.md | 17 ++
.../diagnosis/query_flame_graph.md | 58 ++++
.../docs/operations/system-operation/guardian.md | 62 +++++
...den_modify_metadata_during_maintenance_mode.png | Bin 0 -> 189044 bytes
..._metadata_promoting_during_maintenance_mode.png | Bin 0 -> 188242 bytes
.../system-operation/images/maintenance_mode.png | Bin 0 -> 246534 bytes
.../system_recover_from_maintenance_mode.png | Bin 0 -> 178347 bytes
website/docs/operations/system-operation/intro.md | 17 ++
.../operations/system-operation/junk_file_clean.md | 90 ++++++
.../operations/system-operation/limit_query.md | 72 +++++
.../system-operation/maintenance_mode.md | 76 +++++
.../system-operation/update-session-table.md | 46 ++++
website/sidebars.js | 306 +++++++++++++++++----
83 files changed, 2044 insertions(+), 53 deletions(-)
diff --git a/website/docs/configuration/configuration.md
b/website/docs/configuration/configuration.md
index 979e92303f..3046f38233 100644
--- a/website/docs/configuration/configuration.md
+++ b/website/docs/configuration/configuration.md
@@ -82,7 +82,7 @@ The file **kylin.properties** occupies some of the most
important configurations
| kylin.engine.spark-conf.spark.driver.host | Configure the
IP of the node where the Kylin is located |
| kylin.engine.sanity-check-enabled | Configure
Kylin whether to open Sanity Check during indexes building. The default value
is `true` |
| kylin.job.finished-notifier-url | When the
building job is completed, the job status information will be sent to the url
via HTTP request |
-| kylin.diag.obf.level | The
desensitization level of the diagnostic package. `RAW` means no
desensitization, `OBF` means desensitization. Configuring `OBF` will
desensitize sensitive information such as usernames and passwords in the
`kylin.properties` file (please refer to the [Diagnosis Kit
Tool](../operations/cli_tool/diagnosis.md) chapter), The default value is
`OBF`. |
+| kylin.diag.obf.level | The
desensitization level of the diagnostic package. `RAW` means no
desensitization, `OBF` means desensitization. Configuring `OBF` will
desensitize sensitive information such as usernames and passwords in the
`kylin.properties` file (please refer to the [Diagnosis Kit
Tool](../operations/system-operation/cli_tool/diagnosis.md) chapter), The
default value is `OBF`. |
| kylin.diag.task-timeout | The subtask
timeout time for the diagnostic package, whose default value is 3 minutes |
| kylin.diag.task-timeout-black-list | Diagnostic
package subtask timeout blacklist (the values are separated by commas). The
subtasks in the blacklist will be skipped by the timeout settings and will run
until it finished. The default value is `METADATA`, `LOG` <br />The optional
value is as below: <br />METADATA, AUDIT_LOG, CLIENT, JSTACK, CONF,
HADOOP_CONF, BIN, HADOOP_ENV, CATALOG_INFO, SYSTEM_METRICS, MONITOR_METRICS,
SPARK_LOGS, SPARDER_HISTORY, KG_LOGS, L [...]
| kylin.query.queryhistory.max-size | The total
number of records in the query history of all projects, the default is 10000000
|
diff --git a/website/docs/configuration/hadoop_queue_config.md
b/website/docs/configuration/hadoop_queue_config.md
index b252ec2350..f85925250b 100644
--- a/website/docs/configuration/hadoop_queue_config.md
+++ b/website/docs/configuration/hadoop_queue_config.md
@@ -50,4 +50,4 @@ Similarly, you may set up YARN queue for other Kylin
instances to achieve comput
###<span id="project">Project-level YARN Queue Setting</span>
-The system admin user can set the YARN Application Queue of the project in
**Setting -> Advanced Settings -> YARN Application Queue**, please refer to the
[Project Settings](../operations/project-maintenance/project_settings.md) for
more information.
+The system admin user can set the YARN Application Queue of the project in
**Setting -> Advanced Settings -> YARN Application Queue**, please refer to the
[Project Settings](../operations/project-operation/project_settings.md) for
more information.
diff --git a/website/docs/configuration/query_cache.md
b/website/docs/configuration/query_cache.md
index 27e09396f1..f767537f57 100644
--- a/website/docs/configuration/query_cache.md
+++ b/website/docs/configuration/query_cache.md
@@ -19,7 +19,7 @@ By default, Kylin enables query cache in each process to
improve query performan
> **Note**: In order to ensure data consistency, query cache is not available
> in pushdown.
-###Use Default Cache
+### Use Default Cache
Kylin enables query cache by default at each node/process level. The
configuration details are described below. You can change them in
`$KYLIN_HOME/conf/kylin.properties` under Kylin installation directory.
diff --git a/website/docs/configuration/spark_rpc_encryption.md
b/website/docs/configuration/spark_rpc_encryption.md
index 0e696b829e..e6e3b9bb17 100644
--- a/website/docs/configuration/spark_rpc_encryption.md
+++ b/website/docs/configuration/spark_rpc_encryption.md
@@ -21,8 +21,11 @@ For more details about Spark RPC communication encryption,
please see [Spark Sec
This function is disabled by default. If you need to enable it, please refer
to the following method for configuration.
### Spark RPC Communication Encryption Configuration
-1、1. Please refer to [Spark
Security](http://spark.apache.org/docs/1.6.2/job-scheduling.html#dynamic-resource-allocation)
to ensure that RPC communication encryption is enabled in the Spark cluster.
+
+1、Please refer to [Spark
Security](http://spark.apache.org/docs/1.6.2/job-scheduling.html#dynamic-resource-allocation)
to ensure that RPC communication encryption is enabled in the Spark cluster.
+
2、Add the following configurations in `$KYLIN_HOME/conf/kylin.properties`, to
To enable Kylin nodes and Spark cluster communication encryption
+
```
### spark rpc encryption for build jobs
kylin.storage.columnar.spark-conf.spark.authenticate=true
diff --git
a/website/docs/operations/access-control/data-access-control/acl_table.md
b/website/docs/operations/access-control/data-access-control/acl_table.md
new file mode 100644
index 0000000000..5978d8aabc
--- /dev/null
+++ b/website/docs/operations/access-control/data-access-control/acl_table.md
@@ -0,0 +1,75 @@
+---
+title: Table Access Control
+language: en
+sidebar_label: Table Access Control
+pagination_label: Table Access Control
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - table access control
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+### <span id="table">Table ACL</span>
+
+**Introduction**
+
+Table ACLs determines whether a user/user group can access a certain table
loaded into Kyligence Enterprise. When a user/group is restricted to a table,
the user/user group cannot query the table.
+
+- System administrator can grant table-level data access to a user/user group.
All users/user groups that have access rights to the current project can read
or query all tables in the current project by default.
+- When the access rights of the user/user group are deleted, or the user/user
group is removed from the system, the corresponding table-level permissions are
also deleted.
+- When the table is deleted from the project, the Table ACL for all users/user
groups are also deleted.
+- When the table is reloaded in the project, the Table ACL for all users/user
groups are retained.
+
+**Example**
+
+Now we will use specific examples to show the product behavior after setting
table ACLs.
+
+If a user do not have the access to table `SSB.SUPPLIER`, he cannot see the
corresponding table under the project or in the connected BI tool.
+
+
+
+
+
+If you query the table, the result will show an error.
+
+
+
+### <span id="set">Grant Table ACL</span>
+
+1. In the **Admin** -> Project page, the system administrator can grant
user/user group project-level access rights. For details, please refer to
[Project ACL](project_acl.en.md).
+
+2. Select the project you want to authorize，then click **Authorization** under
the right **Action** bar and go to the authorization page.
+
+3. Click the left arrow button and expand the user/user group that requires
authorization, and the interface displays the tables / columns / rows that the
user/user group has access to.
+
+ 
+
+4. Click the **Edit** button and check the tables and columns that need to be
granted access. There is no row-level access restriction by default, which
means that users can access all the rows in the column.
+
+ 
+
+5. Click the **+ Add** button on the right of the **Row Access List**, select
the column in the pop-up window and enter the rows that can be accessed.
Support for **IN** or **LIKE** rules to set row level permissions, increase or
decrease row-level access via the **+/-** button on the right, and click
**Submit**.
+
+ 
+
+6. For granted row-level access, click the **...** button on the right to
modify the settings, or click **Delete** on the right.
+
+ 
+
+7. Confirm that the currently settings for Table ACLs are correct and click
**Submit**.
+
+
+
+### <span id="notice">Notices</span>
+
+- The authorization operation is a whitelist display for the user/user group,
that is, only the tables / rows / columns permissions added for the user/user
group are accessible.
+- By default, a user/user group will be automatically granted all access
permissions on all tables in this project after added into this project. You
can modify the configuration item
`kylin.acl.project-internal-default-permission-granted=true` in the
configuration file. After setting it to `false`, when the user/user group is
added to the project, there is no table granted by default. System
administrators can manually select tables and set access permissions.
+- The access to the user/user group takes the largest set of results that can
be accessed (union).
+ - If user `user1` has access to table `table1`, user `user1` is in user
group `group1`, and user group `group1` has access to table `table2`. At this
time user `user1` can also access the tables `table1` and `table2`.
+ - If user group `group1` has access to tables `table1` and `table2`, user
group `group2` has access to tables `table2` and `table3`, user `user1` belongs
to user group `group1` and `group2`. At this time `user1` has access to the
tables `table1`, `table2` and `table3`.
+- Only system administrator users can perform **add/delete/change **
operations at the Table / Column / Row ACL.
diff --git
a/website/docs/operations/access-control/data-access-control/intro.md
b/website/docs/operations/access-control/data-access-control/intro.md
new file mode 100644
index 0000000000..b84e0958ab
--- /dev/null
+++ b/website/docs/operations/access-control/data-access-control/intro.md
@@ -0,0 +1,41 @@
+---
+title: Data Access Control
+language: en
+sidebar_label: Data Access Control
+pagination_label: Data Access Control
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - data access control
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+
+Kylin provides a rich set of access control features for big enterprise. Start
from Kylin 5, every action from user must satisfy both **Operation Permission**
and **Data Access Permission**, before the action can perform.
+
+- Operation Permission: Defined at project level, specifies what operations a
user can perform within a project. User can have one of the four permissions,
from weak to powerful:
+ - *QUERY*: Allows to run query in a project.
+ - *OPERATION*: Allows to operate models, like building, refreshing, and
managing Segments. Implies the QUERY permission.
+ - *MANAGEMENT*: Allows to manage models and cubes, like create and edit.
Implies the OPERATION permission.
+ - *ADMIN*: Project level administrator permission, allows to manage source
tables, and all other operations in a project.
+
+ See [Project ACL](project_acl.md) for more details.
+
+- Data Access Permission: Defined on data, specifies which tables, columns,
and rows a user can access. See [Table](acl_table.md) for more details.
+
+### Examples of Permission Check
+
+To perform an action, user must have both operation permission and data access
permission. Below are a few examples.
+
+- To manage source tables, user needs the ADMIN permission, and only the
tables user can access can be seen and acted. (Column and row ACLs does not
impact the source table management.)
+- To edit a model, user must have the MANAGEMENT permission and have access to
all the tables and columns in the model.
+- Running queries is mostly about data access control, since all users in a
project have at least QUERY permission. First user must have access to all the
tables and columns in the query, or the system will prompt permission error and
refuse to execute. Second the system will only return rows that are accessible
to a user. If different row ACLs are set for users, they may see different
results from a same query.
+
+### Other Notes
+
+- The system administrator is not restricted by the data access controls by
default, he/she has access to all data.
+- The system does not provide operation permissions at model level yet.
diff --git
a/website/docs/operations/access-control/data-access-control/project_acl.md
b/website/docs/operations/access-control/data-access-control/project_acl.md
new file mode 100755
index 0000000000..2b38cac6e7
--- /dev/null
+++ b/website/docs/operations/access-control/data-access-control/project_acl.md
@@ -0,0 +1,54 @@
+---
+title: Project Access Control
+language: en
+sidebar_label: Project Access Control
+pagination_label: Project Access Control
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - project access control
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+Project ACLs determines whether a user/user group can access a certain project
in Kylin. Kylin has four built-in project level permissions, *Admin*,
*Management*, *Operation* and *Query*. *Admin* includes the other three
permissions, *Management* includes *Operation* and *Query* permissions,
*Operation* includes *Query* permissions.
+
+- *QUERY*: Permission to query tables/models in the project. If pushdown is
enabled, user/group can query tables loaded to the project when there's no
ready model to answer the query.
+- *OPERATION*: Permission to build a model in the project, including rebuild a
segment, resume or discard jobs.
+- *MANAGEMENT*: Permission to edit/delete models in the project.
+- *ADMIN*: Permission to manage data sources, models in the project.
+
+After the system administrator logs in to Kylin, click the **Admin** button in
the global toolbar to enter the system management page, and click the
**Project** field to enter the Project Management page.
+
+After the system administrator assigns project access permission to a group,
users in the group will inherit the access permission on data source, models
and segments accordingly.
+
+
+### Grant Project ACL
+
+1. Select the project and click the **Authorization** icon under the
**Actions** column on the right to enter the authorization page.
+2. Expand a project on the project list.
+3. Click **+ User / Group** to grant access for a user / user group.
+4. Select the grant type : by **User** or by **User Group**. Then select the
user / user group and access permission to be granted, and click **Submit**.
+
+
+
+
+### Modify Project ACL
+
+1. Select the project and click the **Authorization** icon under the
**Actions** column on the right to enter the authorization page.
+2. Select the user / user group in the list and click the **Edit** icon under
the **Actions** column on the right.
+3. Modify user / user group's access permission and click **Submit**.
+
+### Revoke Project ACL
+
+1. Select the project and click the **Authorization** icon under the
**Actions** column on the right to enter the authorization page.
+2. Select the user / user group in the list and click the **Delete** icon
under the **Actions** column on the right.
+
+> **Caution**: When user/user group's project access permission has been
revoked, all access permission on this project including table-level, row-level
and column-level will be revoked subsequently.
+
+### Data authority control
+
+After setting the system level configuration parameter
**kylin.security.allow-project-admin-grant-acl=false**, the project
administrator in each project has no right to assign table / row / column
access rights to users or user groups, but can still view the table / row /
column access rights of users or user groups.
diff --git a/website/docs/operations/access-control/group_management.md
b/website/docs/operations/access-control/group_management.md
new file mode 100644
index 0000000000..1045c03d45
--- /dev/null
+++ b/website/docs/operations/access-control/group_management.md
@@ -0,0 +1,52 @@
+---
+title: User Group Management
+language: en
+sidebar_label: User Group Management
+pagination_label: User Group Management
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - user group management
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+This chapter provides an overview of what a user group is and how a user group
can be managed.
+
+### <span id="group">About User Group</span>
+
+A user group is a collection of users, and users in a user group share the
same ACL. By default, Kylin initializes four user groups, namely ALL_USERS,
ROLE_ADMIN, ROLE_ANALYST, and ROLE_MODELER, and ALL_USERS group is a default
user group, all users are included in the ALL_USERS user group. ALL_USERS and
ROLE_ADMIN user group cannot be modified or deleted. System administrators can
add or remove users in user groups except ALL_USERS, or add a user to multiple
groups except ALL_USERS. Use [...]
+
+
+### <span id="authority">About User Group Permissions</span>
+
+The system administrator can grant the project-level access permissions to a
user group. When a user group has been granted the project-level permissions,
users in this group will inherit the corresponding permissions from the group.
+
+When a user belongs to multiple groups, the user will inherit the
project-level permissions from the groups he/she belongs to.
+
+### <span id="management">Manage user groups</span>
+
+After the system administrator logs in to Kylin, click the **Admin** button in
the top toolbar to enter the system management page, and click the **Group**
field to enter the User Group Management page.
+
+### <span id="add">Create a user group</span>
+
+On the User Group Management page, click **+ User Group** button to create a
new group. In the pop-up window, the system administrator can fill in the group
name and click **OK** to save a new user group.
+
+### <span id="drop">Delete a user group</span>
+
+On the User Group Management page, select a user to be deleted, click the
**Drop** button under the **Actions** bar on the right. In the pop-up window,
the system administrator can confirm to delete a user group, once a user group
is deleted, users in this user group will not be deleted and permission grant
to this user group will be removed.
+
+### <span id="assign">Assign users to a user group</span>
+
+1. On the User Group Management page, select the user group to be assigned
users to.
+2. Click **Assign Users** under the **Actions** bar on the right.
+3. In the pop-up window, check the users who need to be assigned to the group,
click the right arrow **>**, the user will be assigned to the **Assigned
Users**.
+4. Click **OK** and the user will be assigned to this group.
+
+### <span id="update_group">Modify user's user group</span>
+
+Please refer to [User Management](user_management.md)
+
diff --git a/website/docs/operations/access-control/images/acl_5_en.png
b/website/docs/operations/access-control/images/acl_5_en.png
new file mode 100644
index 0000000000..ae06dff693
Binary files /dev/null and
b/website/docs/operations/access-control/images/acl_5_en.png differ
diff --git a/website/docs/operations/access-control/images/table_acl_1_en.png
b/website/docs/operations/access-control/images/table_acl_1_en.png
new file mode 100644
index 0000000000..b2baa58ea3
Binary files /dev/null and
b/website/docs/operations/access-control/images/table_acl_1_en.png differ
diff --git a/website/docs/operations/access-control/images/table_acl_2_en.png
b/website/docs/operations/access-control/images/table_acl_2_en.png
new file mode 100644
index 0000000000..abd00a9022
Binary files /dev/null and
b/website/docs/operations/access-control/images/table_acl_2_en.png differ
diff --git a/website/docs/operations/access-control/images/table_acl_3_en.png
b/website/docs/operations/access-control/images/table_acl_3_en.png
new file mode 100644
index 0000000000..0e7e47e31d
Binary files /dev/null and
b/website/docs/operations/access-control/images/table_acl_3_en.png differ
diff --git a/website/docs/operations/access-control/intro.md
b/website/docs/operations/access-control/intro.md
new file mode 100644
index 0000000000..fcc139d327
--- /dev/null
+++ b/website/docs/operations/access-control/intro.md
@@ -0,0 +1,24 @@
+---
+title: Access Control
+language: en
+sidebar_label: Access Control
+pagination_label: Access Control
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - access control
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+
+This chapter will describe how to grant roles to users/groups in Kyligence to
control their access rights, and how to perform fine-grained data access
control, it will cover:
+
+* [User Management](user_management.en.md)
+* [User Group Management](group_management.md)
+
+* [Data Access Control](access_control.md)
+ * [Project Access Control](project_acl.md)
diff --git a/website/docs/operations/access-control/user_management.md
b/website/docs/operations/access-control/user_management.md
new file mode 100644
index 0000000000..0b7a4fdfd6
--- /dev/null
+++ b/website/docs/operations/access-control/user_management.md
@@ -0,0 +1,93 @@
+---
+title: User Management
+language: en
+sidebar_label: User Management
+pagination_label: User Management
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - user management
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+
+This chapter introduces what a user is and how a user can be managed.
+
+### <span id="user">About Users</span>
+
+To use Kylin, a user must log in to the system using a user name and
corresponding password. Every user is unique in a Kylin instance, which is to
say, it is not necessary to create the same user for every project in a single
instance.
+By default, Kylin initializes one user, namely `ADMIN`. The user `ADMIN` is a
built-in system administrator, and the system administrator has all the
permissions of the entire system.
+
+
+### <span id="management">Manage Users</span>
+
+After the system administrator logs in to Kylin, click the **Admin** button in
the top toolbar to enter the system management page, and click the **User**
field to enter the User Management page.
+
+**Note**:
+
+1. Except for the system administrator, simply creating a user does not give
the user access to any project.
+2. Except for the system administrator, other users need to be given access at
the project level.
+
+
+### <span id="add">Add a User</span>
+
+On the User Management page, the system administrator can click the **+User**
button to add new users. In the pop-up window, please fill in the user name,
password, confirm new password, select whether the user role is a system
administrator or a normal user, and click **OK**.
+
+> **tips:** username is case insensitive, so duplicate names with existing
user names are not allowed.
+
+### <span id="edit">Edit a User Role</span>
+
+On the User Management page, select a user to be edited, click the **...**
(More Actions) button under the **Actions** bar on the right. Then click **Edit
Role**.
+
+In the pop-up window, the system administrator can modify user role to
administrator or user.
+
+### <span id="drop">Delete a User</span>
+
+On the User Management page, select a user to be deleted, click the **...**
(More Actions) button under the **Actions** bar on the right. Then click
**Delete**. The system administrator can confirm to delete a user in the
prompted window. User can not be restored after deleting, and user's access
permission on all projects will be removed.
+
+### <span id="disable">Enable/Disable a User</span>
+
+On the User Management page, select a user, and click the **...** (More
Actions) button under the **Actions** bar on the right. Then click **Enable /
Disable**. The system administrator can enable or disable a user, and disabled
users cannot login to the system.
+
+### <span id="adminpwd">Reset Password for ADMIN</span>
+
+On the User Management page, select a user, click **Reset Password** under
the **Actions** bar on the right.
+
+In the pop-up window, the system administrator can change the password and
need to enter the new password twice.
+
+The initial ADMIN account password needs to be modified after the first login.
To reset the password, you can execute the following command. After successful
execution, the ADMIN account will regenerate a random password and display it
on the console. When you log in, you need to change the password:
+
+```sh
+$KYLIN_HOME/bin/admin-tool.sh admin-password-reset
+```
+
+When the parameter `kylin.metadata.random-admin-password.enabled=false`, it
will not regenerate a random password but the fixed password `KYLIN`. If the
parameter `kylin.metadata.random-admin-password.enabled` is set from `false` to
`true` , it will regenerate a random password and display it on the console
after all the Kylin nodes restarted.
+
+**Caution** When run this command, Kylin will enter maintenance mode. If the
command is interrupted by force, you may need to exit maintain mode manually.
Refer to [maintenance_mode](../system-operation/maintenance_mode.en.md).
+
+
+### <span id="pwd">Reset password for Non-admin</span>
+
+Click **<username\>**-->**Setup** on the top right corner of the navigation
bar. In the pop-up window, user need to provide the old password and repeat the
new password twice to reset password.
+
+
+### <span id="group">Assign a User to a Group</span>
+
+To assign a user to a group, please do the followings:
+1. On the User Management page, select a user to be grouped.
+2. Click **Assign to Group** under the **Actions** bar on the right.
+3. Select a group to assign the user to under **Candidates**, and then click
the right arrow **>**. The group will enter into **Selected**.
+4. Click **OK** and the user will be in the selected group.
+
+
+### <span id="update_group">Modify User Group</span>
+
+To modify user group, please do the following steps:
+1. On the User Management page, select a user to modify the group membership.
+2. Click **Assign to Group** under the **Actions** bar on the right.
+3. Select the group to be modified under **Selected**, and then click the left
arrow **<**. The group will enter into **Candidates**.
+4. Click **OK** and the user group membership will be modified.
diff --git a/website/docs/operations/access-control/users/user_w1.png
b/website/docs/operations/access-control/users/user_w1.png
new file mode 100755
index 0000000000..82c4ef5d29
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w1.png differ
diff --git a/website/docs/operations/access-control/users/user_w2.png
b/website/docs/operations/access-control/users/user_w2.png
new file mode 100755
index 0000000000..d4fd0d31cd
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w2.png differ
diff --git a/website/docs/operations/access-control/users/user_w3.png
b/website/docs/operations/access-control/users/user_w3.png
new file mode 100755
index 0000000000..442612fbdc
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w3.png differ
diff --git a/website/docs/operations/access-control/users/user_w4.png
b/website/docs/operations/access-control/users/user_w4.png
new file mode 100755
index 0000000000..52c313cfc2
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w4.png differ
diff --git a/website/docs/operations/access-control/users/user_w5.png
b/website/docs/operations/access-control/users/user_w5.png
new file mode 100755
index 0000000000..c7722851e7
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w5.png differ
diff --git a/website/docs/operations/access-control/users/user_w6.png
b/website/docs/operations/access-control/users/user_w6.png
new file mode 100755
index 0000000000..a436ebbbc3
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w6.png differ
diff --git a/website/docs/operations/access-control/users/user_w7.png
b/website/docs/operations/access-control/users/user_w7.png
new file mode 100755
index 0000000000..e88c9701db
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w7.png differ
diff --git a/website/docs/operations/access-control/users/user_w8.png
b/website/docs/operations/access-control/users/user_w8.png
new file mode 100755
index 0000000000..46b7233371
Binary files /dev/null and
b/website/docs/operations/access-control/users/user_w8.png differ
diff --git a/website/docs/operations/logs/audit_log.md
b/website/docs/operations/logs/audit_log.md
new file mode 100644
index 0000000000..3cd52a124f
--- /dev/null
+++ b/website/docs/operations/logs/audit_log.md
@@ -0,0 +1,208 @@
+---
+title: Audit Log
+language: en
+sidebar_label: Audit Log
+pagination_label: Audit Log
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - audit log
+draft: false
+last_update:
+ date: 08/16/2022
+---
+
+### Basic Concept
+
+In the database, Audit Log is mainly used to monitor and record the operating
behavior of data, which is simply understood as a log.
+
+Kylin instances are stateless services. All state information is stored in
metadata. All operations that change data will create or modify metadata.
Changes to metadata are included in a database transaction. At the same time,
every time Modifications to metadata are recorded in the audit log, which is
equivalent to a snapshot of each version of the metadata. Audit Log mechanism
can not only monitor metadata through the Audit Log, but also help disaster
recovery.
+
+
+
+> Caution：The Audit Log can only be considered as a log of metadata, used to
monitor and troubleshoot problems, and can be used to repair some metadata. If
you want to ensure the stability of the system, you need to ensure that the
metadata is correct and back up the metadata in a timely manner.
+
+
+
+When Kylin is started for the first time, according to the metadata table name
you filled in for the configuration item `kylin.metadata.url` in the
configuration file` kylin.properties`, create a file named `{identifier}
_audit_log` in the metadata database. The audit table has a suffix `_audit_log`
compared to the metadata table.
+
+
+
+e.g：
+
+`kylin.metadata.url=ke_metadata@jdbc,driverClassName=org.postgresql.Driver,url=jdbc:postgresql://sandbox:5432/kylin,username=postgres,password=`
+
+The metadata is named `kylin`, the metadata table is named` ke_metadata`, and
the Audit Log table is named `ke_metadata_audit_log`.
+
+
+
+In Kylin, PostgreSQL is used as the metastore by default, and PostgreSQL is
used as an example later.
+
+
+
+**Audit Log table field descriptions**
+
+| name | type（postgresql） | type(mysql) | description
|
+| :----------- | ------------------ | ------------ |
:----------------------------------------------------------- |
+| id | bigserial | bigint | Auto incremental id
|
+| meta_key | varchar(255) | varchar(255) | The key of metadata,
corresponding to the META_TABLE_KEY field in the metadata table |
+| meta_content | bytea | longblob | The content of the
current metadata, when the operation is deletion, the value is NULL |
+| meta_ts | bigint | bigint | Update timestamp, when
the operation is deletion, the value is NULL |
+| meta_mvcc | bigint | bigint | The version of the
current metadata, when the operation is deletion, the value is NULL |
+| unit_id | varchar(255) | varchar(255) | Transaction id
|
+| operator | varchar(255) | varchar(255) | The username of operator
|
+| instance | varchar | varchar | The instance of operator
|
+
+
+
+### Version Information
+
+The `meta_table_key` field in the metadata table is associated with the
`meta_key` in the audit log table.
+
+- Metadata version: In the metadata table, the `meta_table_mvcc` field records
the latest version number of each item of metadata;
+
+- Audit log version: In the audit log table, the `meta_mvcc` field records the
version number. You can filter and view all historical versions of a certain
metadata according to the` meta_key` field;
+
+
+
+### Functions
+
+The following functions can be implemented through audit logs:
+
+- View the change history of all / a certain metadata and the corresponding
operation user
+- View the change of metadata in a transaction
+- View the audit log over a period of time
+- Facilitates metadata disaster recovery
+
+
+
+### Sample
+
+**Tool**
+
+PostgreSQL client tool：DBeaver
+
+
+
+**Table description**
+
+
+
+
+
+As shown in the table, the meta_key field is a metadata item and meta_content
is a metadata value. The meta_key value starts with `/ _global` to indicate
global metadata,` / project_name` starts to indicate metadata for a project,
and `/ UUID` is a globally unique identifier, which serves as an identifier for
a piece of metadata.
+
+e.g：
+
+- `_global/user/ADMIN` Represents metadata information of ADMIN users, the
specific information is in the meta_content field;
+- `_global/project/kylin.json` Represents metadata information for a project
named kylin;
+- `/${project_name}/model_desc/${model_id}` Model description information
representing a project;
+
+
+
+**Basic Operations**
+
+1. View the history of an item of metadata
+
+ ```
+ select * from ke_metadata_audit_log where meta_key =
'/_global/project/default.json';
+ ```
+
+2. View the history of a model
+
+ ```
+ select * from ke_metadata_audit_log where meta_key =
'/project/model_desc/49529000-c161-4013-bb80-9a78f4f0248d.json'
+ ```
+
+3. View the change of metadata in a transaction
+
+ ```
+ select * from ke_metadata_audit_log where unit_id =
'6090bfb5-2401-4176-8475-fe6fd82bc439';
+ ```
+
+4. View audit logs for metadata over a period of time
+
+ ```
+ select * from ke_metadata_audit_log where meta_ts > 1325376000000 and
meta_ts < 1328054400000 ;
+ ```
+
+5. Associate the metadata table to view the history changes of a user
+
+ ```
+ select a.meta_mvcc, a.meta_content, b.meta_table_mvcc, b.meta_table_content
from ke_metadata_audit_log a left join ke_metadata b on a.meta_key =
b.meta_table_key where a.meta_key = '/_global/user/ADMIN'
+ ```
+
+
+
+**Examples of actual scenarios**
+
+- Monitor if user password is changed
+
+ The ADMIN user is very important. It is not allowed to modify the password
by anyone other than the system administrator. You can monitor the content of
meta_content whose meta_key is `/_global/user/ADMIN`. One of the fields is
password. If this value changes, explained the password modified.
+
+
+
+ The meta_mvcc field version number increases before and after the password
is changed, the password value in the meta_content field changes, and the value
of default_password also changes from true to false:
+
+ 
+
+ 
+
+
+
+- Monitor if the model has been modified
+
+ Assume that the project name is kylin, and the table connection relationship
of model name test_model is not allowed to be modified. You can view the JSON
format of a model on the Kylin model page, where uuid represents the model id,
then the corresponding meta_key is `/kylin/model_desc/${model_id} `, monitor
whether the corresponding meta_mvcc field value increases, if there is a
change, the model is modified.
+
+
+
+ The second record is to change the format of the time partition column of
the model, and the unit_id field value of the two records is different,
indicating that the two changes were made in different transactions, and the
user who checked the operator field was ADMIN:
+
+ 
+
+ 
+
+
+
+### Configuration instructions
+
+
+In the Kylin configuration file `kylin.properties`, there are the following
configuration items about the audit log, which can be modified as needed.
**Please make sure the disk space of the audit log node is always sufficient.**
+
+
+- `kylin.metadata.audit-log.max-size=500000` The audit log stores the latest
500,000 rows by default. By default, the redundant operation log is cleared
every morning. You can modify this configuration item to adjust it.
+
+
+
+### Export Audit Log
+
+The Audit Log is stored in the database. You can use the tools provided by
Kylin to export the data within the specified time range to the local for
backup, or export it as an attachment to the Kylin ticket when encountering
problems, which is convenient for technology support personnel to locate the
problem.
+
+There are two ways to execute commands on the KE node:
+
+1. Use the diagnostic package command: `$ {KYLIN_HOME}/bin/diag.sh`
+
+ - -The Audit Log of the last 3 days will be obtained by default and stored
in the `audit_log/${starttime}_${endtime}.jsonl` file in the diagnostic package
directory;
+
+
+
+2. Using the AuditLogTool tool: `${KYLIN_HOME}/bin/kylin.sh
io.kyligence.kap.tool.AuditLogTool -startTime ${starttime} -endTime ${endtime}
-dir ${target_dir}`
+
+ - `${starttime}` and `${endtime}` Retrieves the specified range of Audit
Log. The format is timestamp in milliseconds: e.g `1579868382749`;
+ - `${target_dir}` specifies the directory where your Audit Log files are
stored. The generated Audit Log is stored in the
`${target_dir}/${starttime}_${endtime}` file;
+
+
+
+### Import Audit Log
+
+If you have the Audit Log file exported locally and want to view and analyze
it through the database, you can use the following methods to import.
+
+On a machine that already has a Kylin environment, use the AuditLogTool tool:
`${KYLIN_HOME}/kylin.sh io.kyligence.kap.tool.AuditLogTool -restore -table
${target_table_name} -dir ${auditlog_dir}`
+
+- The `$ {target_table_name}` parameter specifies the name of the Audit Log
table to be generated. Be careful not to duplicate the name of the Audit Log
table already in the Kylin environment.
+- The `$ {auditlog_dir}` parameter specifies the directory where the Audit Log
file is located;
+
+After the execution of the command is completed, the Audit Log table is
generated under the metastore specified by the configuration item
`kylin.metadata.url` in the` $ {KYLIN_HOME}/conf/kylin.properties` file.
+
diff --git a/website/docs/operations/logs/images/after_update_model.png
b/website/docs/operations/logs/images/after_update_model.png
new file mode 100644
index 0000000000..c0da4545a8
Binary files /dev/null and
b/website/docs/operations/logs/images/after_update_model.png differ
diff --git a/website/docs/operations/logs/images/after_update_pwd.png
b/website/docs/operations/logs/images/after_update_pwd.png
new file mode 100644
index 0000000000..4bcfc0c801
Binary files /dev/null and
b/website/docs/operations/logs/images/after_update_pwd.png differ
diff --git a/website/docs/operations/logs/images/before_update_model.png
b/website/docs/operations/logs/images/before_update_model.png
new file mode 100644
index 0000000000..e60309d83a
Binary files /dev/null and
b/website/docs/operations/logs/images/before_update_model.png differ
diff --git a/website/docs/operations/logs/images/before_update_pwd.png
b/website/docs/operations/logs/images/before_update_pwd.png
new file mode 100644
index 0000000000..88fea477c6
Binary files /dev/null and
b/website/docs/operations/logs/images/before_update_pwd.png differ
diff --git a/website/docs/operations/logs/images/metadata_table.png
b/website/docs/operations/logs/images/metadata_table.png
new file mode 100644
index 0000000000..85baef4deb
Binary files /dev/null and
b/website/docs/operations/logs/images/metadata_table.png differ
diff --git a/website/docs/operations/logs/intro.md
b/website/docs/operations/logs/intro.md
new file mode 100644
index 0000000000..9c2f2ebec6
--- /dev/null
+++ b/website/docs/operations/logs/intro.md
@@ -0,0 +1,21 @@
+---
+title: Logs
+language: en
+sidebar_label: Logs
+pagination_label: Logs
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - logs
+draft: false
+last_update:
+ date: 08/16/2022
+---
+
+This chapter mainly introduces different log types:
+
+* [System Log](logging.md)
+* [Audit Log](audit_log.md)
+
diff --git a/website/docs/operations/logs/system_log.md
b/website/docs/operations/logs/system_log.md
new file mode 100755
index 0000000000..d80321a73d
--- /dev/null
+++ b/website/docs/operations/logs/system_log.md
@@ -0,0 +1,249 @@
+---
+title: System Log
+language: en
+sidebar_label: System Log
+pagination_label: System Log
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - system log
+draft: false
+last_update:
+ date: 08/16/2022
+---
+
+
+## System Log
+
+After being successfully started, Kylin will create a directory named `logs/`
by default, all logs generated during Kylin runtime will be stored in this
directory.
+
+### Log files
+Log files generated by Kylin is as followings.
+
+#### `kylin.log`
+This file is Kylin's main log file, whose default logging level is DEBUG.
+
+#### `kylin.out`
+The standard output of Kylin process will be redirected to this file,
including the output of Tomcat and Hive.
+
+#### `kylin.gc`
+This file is the GC(Garbage Collection) log of Kylin Java process. And it
appends pid as filename suffix to avoid being overwritten.
+
+#### `access.log`
+This file stores the Tomcat access log. It records all HTTP request response
information.For example, User-Agent, access URL, etc.
+
+#### `jstack.timed.log`
+
+This file records Java stack traces of Java threads of Kylin, which is used to
record some threads running status. To avoid the storage overused, only 20 log
files can be kept. The new file will replace the oldest one, when exceeding the
maximum number.
+
+> Note:Because the execution of jstack depends on the .java_pid file written
by jvm in the /tmp directory, if the file is deleted (for example, a scheduled
clean up script), it will cause the jstack to not run properly, so that the
jstack.timed .log will not be generated
+
+#### `check-env.out`
+The standard output of executing `check-env.sh` script will be redirected to
this file.
+
+#### `check-env.error`
+The error message of executing `check-env.sh` script will be redirected to
this file.
+
+#### `shell.stderr`
+The result of running command lines will be stored in this file.
+
+#### `shell.stdout`
+The standard output of running command lines will be redirected to this file.
+
+#### `kylin.security.log`
+
+The log of system start, stop, upgrade, login and logout will be redirected to
this file.
+
+> Notes: When using LDAP service to implement user authentication, two logs
will be recorded for each login failure. Because when using the LDAP service,
if the login fails, another method will be used for authentication.
+
+#### `kylin.schedule.log`
+This file records logs related to task scheduling, whose default logging level
is DEBUG.
+
+#### `kylin.query.log`
+This file records query related logs, whose default logging level is DEBUG.
+
+#### `kylin.smart.log`
+This file records recommendation-related logs, whose default logging level is
DEBUG.
+
+#### `dump.hprof`
+When Out of Memory (OOM) occurs in Kylin, it will dump the entire heap, which
is convenient for checking the cause.
+> Note: When you have a large memory setting and Out of Memory OOM occurs, the
file dump.hprof will occupy a large storage space, which may cause your disk
space to be insufficient and the node to be abnormal. You can manually clean up
the historical file.
+
+### Logging Analysis
+Take query as an example, submitting a query on Web UI, and we'll see the
following information in `kylin.query.log`
+
+
+```
+==========================[QUERY]===============================
+Query Id: 8586e718-67b4-c840-61b4-a8898415a154
+SQL: select lo_revenue as from p_lineorder;
+User: ADMIN
+Success: true
+Duration: 1.243
+Project: ssb100_10
+Realization Names: [AUTO_MODEL_P_LINEORDER_1]
+Index Layout Ids: [30001]
+Snapshot Names: []
+Is Partial Match Model: [false]
+Scan rows: [35000]
+Total Scan rows: 35000
+Scan bytes: [246530]
+Total Scan Bytes: 246530
+Result Row Count: 280
+Shuffle partitions: 1
+Hit Exception Cache: false
+Storage Cache Used: false
+Storage Cache Type: null
+Is Query Push-Down: false
+Is Prepare: false
+Is Timeout: false
+Time Line Schema: massage,end calcite parse
sql,end_convert_to_relnode,end_calcite_optimize,end_plan,collect_olap_context_info,end
select
realization,end_rewrite,to_spark_plan,seg_pruning,fetch_file_status,shard_pruning,executed_plan,collect_result
+Time Line: 6,1,4,11,0,0,1,1,14,6,0,0,1,1198
+Message: null
+Is forced to Push-Down: false
+User Agent: null
+Scan Segment Count: 1
+Scan File Count: 1
+==========================[QUERY]===============================
+```
+The main fields in the above clip are described as follows:
+
+* `Query Id`： Query id
+* `SQL`： Query statement
+* `User`： The user name to execute the query
+* `Success`： Status flag of query result, true execution succeeded, false
execution failed
+* `Duration`： Query time (unit: seconds)
+* `Project`： The name of the project used in the query
+* `Realization Names`： The name of the model hit by the query
+* `Index Layout Ids`： ID of the layout hit by the query
+* `Snapshot Names`： Query the hit snapshot
+* `Is Partial Match Model`： Partial match model, such as a left B, you can
check table a alone
+* `Scan rows`： Query the number of data rows scanned
+* `Total Scan rows`： Total rows of data scanned by query
+* `Scan bytes`： Query the number of data bytes scanned
+* `Total Scan Bytes` ： Query the total number of bytes of scanned data
+* `Result Row Count`： The number of data rows returned by the query
+* `Shuffle partitions`： A spark query parameter that affects how many
partitions / tasks are generated after a shuffle. It is calculated by
kylin.query.engine.sparkl-sql-shuffle-parittions or dynamic calculation. The
calculation formula is min (the estimated value of data size and the total
number of cores of spark cluster)
+* `Hit Exception Cache`： Whether to hit the cache of failed queries
+* `Storage Cache Used`： Whether to hit the cache successfully queried
+* `Storage Cache Type`： The cache type of the hit query
+* `Is Query Push-Down`： Is it a push down query
+* `Is Prepare`： Whether it is a probe query (this item will be true for the
query sent by BI)
+* `Is Timeout`： Whether to timeout
+* `Time Line Schema`： Steps in query module
+* `Time Line`： Time spent in each step of the query module (MS)
+* `Message`：Query the prompt information on the page. The query is successful.
This item is null
+* `Is forced to Push-Down`： Whether to force down
+* `User Agent`： The environment information used to submit the query
+* `Scan Segment Count`： Number of scanned segments
+* `Scan File Count`： Number of scanned files
+
+### Logging Configuration
+
+Kylin uses log4j2 to configure logs. Users can edit the
`kylin-server-log4j.xml` file in the `$KYLIN_HOME/server/conf/` directory to
modify the log level, path, etc.
+After modification, you need to restart Kylin for the configuration to take
effect.
+
+The configuration of all logs starting with kylin and ending with log is in
`kylin-server-log4j.xml`, the configuration code is as follows.
+
+```xml
+ <Routing name="routing">
+ <Routes pattern="$${ctx:logCategory}">
+ <Route>
+ <RollingFile name="rolling-${ctx:logCategory}"
+
fileName="${env:KYLIN_HOME}/logs/kylin.${ctx:logCategory}.log"
+
filePattern="${env:KYLIN_HOME}/logs/kylin.${ctx:logCategory}.log.%i">
+ <Policies>
+ <SizeBasedTriggeringPolicy size="268435456"/>
+ </Policies>
+ <DefaultRolloverStrategy max="10"/>
+ <PatternLayout pattern="%d{ISO8601} %-5p
%X{request.project}[%t] %c{2} : %mask{%m}%n"/>
+ </RollingFile>
+ </Route>
+
+ <Route ref="server" key="$${ctx:logCategory}"/>
+ </Routes>
+ </Routing>
+
+```
+
+In the default configuration, log rolling is triggered when the log file
reaches 256MB, keeping the last 10 log files.
+
+If you need to configure one of the log files (such as kylin.query.log)
separately, you need to add a new Route under the Routes configuration in the
above configuration code, and configure the key as the corresponding log file
name (query, schedule).
+It should be noted that the new route needs to be configured before the
existing route, otherwise it will not take effect.
+
+The following is an example, modify the rolling strategy of kylin.query.log to
trigger at 0:00 every day, back up the last 5 logs.
+
+```xml
+<Route key="query">
+ <RollingFile name="rolling-${ctx:logCategory}"
fileName="${env:KYLIN_HOME}/logs/kylin.${ctx:logCategory}.log"
filePattern="${env:KYLIN_HOME}/logs/kylin.${ctx:logCategory}.log.%i">
+ <Policies>
+ <CronTriggeringPolicy schedule="0 0 0 * * ?"/>
+ </Policies>
+ <DefaultRolloverStrategy max="5" />
+ <PatternLayout pattern="%d{ISO8601} %-5p %X{request.project}[%t] %c{2}
: %mask{%m}%n" />
+ </RollingFile>
+</Route>
+```
+
+If you need to configure kylin.log, you can modify the RollingRandomAccessFile
configuration, for example, change the number of reserved files to 5
+
+```xml
+<RollingRandomAccessFile name="server"
fileName="${env:KYLIN_HOME}/logs/kylin.log" append="true"
+ filePattern="${env:KYLIN_HOME}/logs/kylin.log.%i"
immediateFlush="false" >
+ <Policies>
+ <SizeBasedTriggeringPolicy size="268435456"/>
+ </Policies>
+ <DefaultRolloverStrategy max="5"/>
+ <PatternLayout pattern="%d{ISO8601} %-5p %X{request.project}[%t] %c{2} :
%mask{%m}%n"/>
+</RollingRandomAccessFile>
+```
+
+### Error Code In Log
+
+The format of log error code is KE-AABBBCCC, AA refers to the error reporting
module, BBB refers to the more detailed business error reporting and CCC refers
to the error number.
+
+| AA | Description
|
+| ----------------------------------------------------------- |
------------------------------------------------------------ |
+| 00 | common |
+| 10 | server |
+| 20 | query |
+| 30 | build |
+| 40 | system |
+| 50 | tool |
+
+
+
+| BBB | Description
|
+| ----------------------------------------------------------- |
------------------------------------------------------------ |
+| 000 | general |
+| 001 | project |
+| 002 | model |
+| 003 | user |
+| 004 | user group |
+| 005 | password |
+| 006 | column |
+| 007 | table |
+| 008 | database |
+| 009 | measure |
+| 010 | dimension |
+| 011 | cc |
+| 012 | index |
+| 013 | job |
+| 014 | sql expression |
+| 015 | license |
+| 016 | email |
+| 017 | file |
+| 018 | kerberos |
+| 019 | catalog |
+| 020 | recommendation |
+| 021 | server |
+| 022 | segment |
+| 023 | diag |
+| 024 | auth |
+| 025 | shell |
+| 026 | metadata |
+| 027 | frequency query |
+| 028 | json |
+
diff --git a/website/docs/operations/overview.md
b/website/docs/operations/overview.md
new file mode 100755
index 0000000000..d3c9b22883
--- /dev/null
+++ b/website/docs/operations/overview.md
@@ -0,0 +1,22 @@
+---
+title: Overview
+language: en
+sidebar_label: Overview
+pagination_label: Overview
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - operation overview
+draft: false
+last_update:
+ date: 08/16/2022
+---
+
+As Kylin system administrator, typical daily operations include:
+
+- To ensure Kylin service running smoothly, system administrator should
monitor system logs on a regular basis.
+- To ensure building jobs run successfully, system administrator needs to
monitor jobs execution status via email notification or system web UI.
+- To ensure there are enough cluster resources for Kylin, system administrator
should check the YARN queue and storage utilization frequently.
+- To prevent any data loss or system failure, system administrator should make
plans for system backup and disaster recovery.
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_acceleration.png
b/website/docs/operations/project-maintenance/images/project_settings_acceleration.png
deleted file mode 100644
index e88b5e7167..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/project_settings_acceleration.png
and /dev/null differ
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_acceleration_tips.png
b/website/docs/operations/project-maintenance/images/project_settings_acceleration_tips.png
deleted file mode 100644
index e5d611f514..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/project_settings_acceleration_tips.png
and /dev/null differ
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_storage_low_usage.png
b/website/docs/operations/project-maintenance/images/project_settings_storage_low_usage.png
deleted file mode 100644
index e11df66530..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/project_settings_storage_low_usage.png
and /dev/null differ
diff --git
a/website/docs/operations/project-maintenance/images/recommendation_preferences_en.png
b/website/docs/operations/project-maintenance/images/recommendation_preferences_en.png
deleted file mode 100644
index 6538741e6c..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/recommendation_preferences_en.png
and /dev/null differ
diff --git
a/website/docs/operations/project-maintenance/images/service_state.en.png
b/website/docs/operations/project-maintenance/images/service_state.en.png
deleted file mode 100644
index 69dd4e44b1..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/service_state.en.png and
/dev/null differ
diff --git
a/website/docs/operations/project-maintenance/images/storage_quota.en.png
b/website/docs/operations/project-maintenance/images/storage_quota.en.png
deleted file mode 100644
index 40953f6ebc..0000000000
Binary files
a/website/docs/operations/project-maintenance/images/storage_quota.en.png and
/dev/null differ
diff --git a/website/docs/operations/project-maintenance/alerting.md
b/website/docs/operations/project-operation/alerting.md
similarity index 100%
rename from website/docs/operations/project-maintenance/alerting.md
rename to website/docs/operations/project-operation/alerting.md
diff --git a/website/docs/operations/project-operation/images/add_project.png
b/website/docs/operations/project-operation/images/add_project.png
new file mode 100644
index 0000000000..474e307aac
Binary files /dev/null and
b/website/docs/operations/project-operation/images/add_project.png differ
diff --git a/website/docs/operations/project-operation/images/project_list.png
b/website/docs/operations/project-operation/images/project_list.png
new file mode 100644
index 0000000000..f9763fe6b1
Binary files /dev/null and
b/website/docs/operations/project-operation/images/project_list.png differ
diff --git
a/website/docs/operations/project-maintenance/images/project_settings.png
b/website/docs/operations/project-operation/images/project_settings.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings.png
rename to website/docs/operations/project-operation/images/project_settings.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_basic_general.png
b/website/docs/operations/project-operation/images/project_settings_basic_general.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_basic_general.png
rename to
website/docs/operations/project-operation/images/project_settings_basic_general.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_cc_expose.png
b/website/docs/operations/project-operation/images/project_settings_cc_expose.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_cc_expose.png
rename to
website/docs/operations/project-operation/images/project_settings_cc_expose.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_custom_config.png
b/website/docs/operations/project-operation/images/project_settings_custom_config.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_custom_config.png
rename to
website/docs/operations/project-operation/images/project_settings_custom_config.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_default_database_en.png
b/website/docs/operations/project-operation/images/project_settings_default_database_en.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_default_database_en.png
rename to
website/docs/operations/project-operation/images/project_settings_default_database_en.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_job_notification.png
b/website/docs/operations/project-operation/images/project_settings_job_notification.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_job_notification.png
rename to
website/docs/operations/project-operation/images/project_settings_job_notification.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_job_notification_page.png
b/website/docs/operations/project-operation/images/project_settings_job_notification_page.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_job_notification_page.png
rename to
website/docs/operations/project-operation/images/project_settings_job_notification_page.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_model_rewrite.png
b/website/docs/operations/project-operation/images/project_settings_model_rewrite.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_model_rewrite.png
rename to
website/docs/operations/project-operation/images/project_settings_model_rewrite.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_pushdown.png
b/website/docs/operations/project-operation/images/project_settings_pushdown.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_pushdown.png
rename to
website/docs/operations/project-operation/images/project_settings_pushdown.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_segment_en.png
b/website/docs/operations/project-operation/images/project_settings_segment_en.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_segment_en.png
rename to
website/docs/operations/project-operation/images/project_settings_segment_en.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_storage.png
b/website/docs/operations/project-operation/images/project_settings_storage.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_storage.png
rename to
website/docs/operations/project-operation/images/project_settings_storage.png
diff --git
a/website/docs/operations/project-maintenance/images/project_settings_yarn_queue.png
b/website/docs/operations/project-operation/images/project_settings_yarn_queue.png
similarity index 100%
rename from
website/docs/operations/project-maintenance/images/project_settings_yarn_queue.png
rename to
website/docs/operations/project-operation/images/project_settings_yarn_queue.png
diff --git a/website/docs/operations/project-maintenance/images/toolbar.en.png
b/website/docs/operations/project-operation/images/toolbar.en.png
similarity index 100%
rename from website/docs/operations/project-maintenance/images/toolbar.en.png
rename to website/docs/operations/project-operation/images/toolbar.en.png
diff --git a/website/docs/operations/project-maintenance/intro.md
b/website/docs/operations/project-operation/intro.md
similarity index 100%
rename from website/docs/operations/project-maintenance/intro.md
rename to website/docs/operations/project-operation/intro.md
diff --git a/website/docs/operations/project-operation/project_management.md
b/website/docs/operations/project-operation/project_management.md
new file mode 100644
index 0000000000..ba84002070
--- /dev/null
+++ b/website/docs/operations/project-operation/project_management.md
@@ -0,0 +1,62 @@
+---
+title: Project Management
+language: en
+sidebar_label: Project Management
+pagination_label: Project Management
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - project management
+draft: true
+last_update:
+ date: Aug 16, 2022
+---
+
+This chapter introduces what a project is and how to manage projects.
+
+### <span id="about">About Projects</span>
+
+Project is the primary management unit of Kylin. In a project, you can design
multiple models and perform query analysis.
+
+System settings are isolated at the project level, so you can set different
operational preferences for different projects.
+
+### <span id="management">Manage Projects</span>
+
+After the system administrator logs in to Kylin, click the **Admin** button in
the top toolbar to enter the system management page, and click the **Porject**
field to enter the Project Management page.
+
+**Note**: if no project exist, you will not be allowed to access the **Admin**
page. Please add a project firstly and then enter the **Admin** page.
+
+On the project management page, the system administrator can view the project
information in the project list, and can also add projects, delete projects,
backup projects, or grant user access permissions.
+
+
+
+### <span id="add">Add a Project</span>
+
+The system administrator has two ways to add a new project:
+
+- On the **Admin -> Project Management** page, click the **+ Project** button
above the project list.
+- On the product normal page, click the **+**（Add Project) button at the top
toolbar.
+
+Fill in the project name and description in the pop-up window. The project
name is mandatory; the project description is optional. A good project
description will help with the maintenance of the project in the future.
+
+
+
+> **tips:** project name is case insensitive, so duplicate names with existing
project names are not allowed.
+
+### <span id="delete">Delete a Project</span>
+
+On the Project Management page, select a project to be deleted, click the
**...**(More Actions) button under the **Actions** bar on the right, then click
**Delete**.
+
+The system administrator can confirm to delete a project in the prompted
window. After the project is deleted, it will not be restored and the related
data will be cleared.
+
+If there are jobs in **RUNNING, PENDING, or PAUSED** status in the project, it
is needed to terminate the jobs before deleting the project.
+
+### <span id="change_owner">Change Project Owner</span>
+
+On the Project Management page, select a project to change owner, click the
**...**(More Actions) button under the **Actions** bar on the right, then click
**Change Owner**. Only the system administrator has permission to change the
project owner.
+
+### <span id="grant">Grant Porject-level Access Rights to User</span>
+
+On the Project Management page, select a project to authorizer, click the
**Authorization** button under the **Actions** bar on the right and set
permissions for the project. You can find out more at the [Project
ACL](../access-control/project_acl.md) section.
diff --git a/website/docs/operations/project-maintenance/project_settings.md
b/website/docs/operations/project-operation/project_settings.md
similarity index 100%
rename from website/docs/operations/project-maintenance/project_settings.md
rename to website/docs/operations/project-operation/project_settings.md
diff --git a/website/docs/operations/cli_tool/diagnosis.md
b/website/docs/operations/system-operation/cli_tool/diagnosis.md
similarity index 100%
rename from website/docs/operations/cli_tool/diagnosis.md
rename to website/docs/operations/system-operation/cli_tool/diagnosis.md
diff --git
a/website/docs/operations/system-operation/cli_tool/environment_dependency_check.md
b/website/docs/operations/system-operation/cli_tool/environment_dependency_check.md
new file mode 100644
index 0000000000..c6bf7a05a9
--- /dev/null
+++
b/website/docs/operations/system-operation/cli_tool/environment_dependency_check.md
@@ -0,0 +1,48 @@
+---
+title: Environment Dependency Check
+language: en
+sidebar_label: Environment Dependency Check
+pagination_label: Environment Dependency Check
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - environment dependency check
+draft: false
+last_update:
+ date: 08/16/2022
+---
+
+Before you start Kylin, we provide an environment dependency checking tool to
help you spot the potential problems in advance. This tool will be
automatically executed by startup script when you run Kylin at the first time.
+
+### How To Use
+
+As said above, if you start Kylin at the first time, the startup script will
automatically run this tool. If it check failed, this tool will be executed
again when you start this product. Once successfully passed this check, the
tool will not be executed automatically.
+
+If you need to check the environment dependency manually, just run the below
command:
+
+```sh
+$KYLIN_HOME/bin/check-env.sh
+```
+
+### What To Check
+
+The following table describes what will be checked in the tool.
+
+| Check Item | Description
|
+| ---------------------- |
------------------------------------------------------------ |
+| Kerberos | To check whether user enable Kerberos in the
settings. If not, the check will be skipped. Otherwise, it will execute the
following operations: <br /> 1. check if Kerberos command exists <br /> 2.
initialize Kerberos|
+| OS version and command | Kylin only supports Linux operating systems.
Besides operating system, this tool will also check if `hadoop` and `yarn`
commands exist. If these two commands are not available, please make sure
Hadoop cluster whether is available. |
+| Hadoop configuration files | Kylin copies Hadoop configuration
files to Kylin installation directory `$KYLIN_HOME/hadoop_conf`. For instance,
`core-site.xml`, `hdfs-site.xml`, `yarn-site.xml`, `hive-site.xml`, etc. This
tool will check if `$KYLIN_HOME/hadoop_conf` exists and contains necessary
configuration files. |
+| HDFS working directory | 1. Check if HDFS working directory
exists <br /> 2. If yes, check whether current user has write privilege |
+| Java version | Currently, we only support Java versions above
1.8 |
+| Server port | Check if the port is in use |
+| Spark | 1. Check if the configured resource size exceeds the cluster's
actual resource size, such as, executor cores and executor instances. <br /> 2.
Check if Spark is available <br /> 3. Check if the configured yarn queues for
submitting query jobs and build jobs are legal 4. Check if the configured
driver host address is legal|
+| Spark log directory | Users can configure a HDFS directory to store Spark
logs, so it checks if the directory exists and current user has read and write
privileges. |
+| Metastore | Check if the metastore is accessible and current user can
perform necessary operations on metadata. |
+| InfluxDB | 1. Check if InfluxDB is accessible <br /> 2.
Check if current user has read and write privileges |
+| ZooKeeper | Check if the service discovery is available. |
+| Clickhouse| Checking Clickhouse cluster health. |
+| KylinConfig | Checking kylin config, must starts with kylin / spring /
server. |
+| Query history | Check whether the current user has permissions of reading
and writing on the `query_history` and `query_history_realization` tables in
the RDBMS database|
diff --git
a/website/docs/operations/system-operation/cli_tool/images/accept_en.png
b/website/docs/operations/system-operation/cli_tool/images/accept_en.png
new file mode 100644
index 0000000000..f79cbb094e
Binary files /dev/null and
b/website/docs/operations/system-operation/cli_tool/images/accept_en.png differ
diff --git
a/website/docs/operations/system-operation/cli_tool/images/button_en.png
b/website/docs/operations/system-operation/cli_tool/images/button_en.png
new file mode 100644
index 0000000000..cfdcb1966d
Binary files /dev/null and
b/website/docs/operations/system-operation/cli_tool/images/button_en.png differ
diff --git
a/website/docs/operations/system-operation/cli_tool/images/rollback_en.png
b/website/docs/operations/system-operation/cli_tool/images/rollback_en.png
new file mode 100644
index 0000000000..c3f5742818
Binary files /dev/null and
b/website/docs/operations/system-operation/cli_tool/images/rollback_en.png
differ
diff --git a/website/docs/operations/cli_tool/intro.md
b/website/docs/operations/system-operation/cli_tool/intro.md
similarity index 100%
rename from website/docs/operations/cli_tool/intro.md
rename to website/docs/operations/system-operation/cli_tool/intro.md
diff --git
a/website/docs/operations/system-operation/cli_tool/metadata_tool/intro.md
b/website/docs/operations/system-operation/cli_tool/metadata_tool/intro.md
new file mode 100644
index 0000000000..683caa8623
--- /dev/null
+++ b/website/docs/operations/system-operation/cli_tool/metadata_tool/intro.md
@@ -0,0 +1,18 @@
+---
+title: Metadata Tool
+language: en
+sidebar_label: Metadata Tool
+pagination_label: Metadata Tool
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - metadata tool
+draft: true
+last_update:
+ date: 08/16/2022
+---
+
+This chapter introduces the metadata tool.
+
diff --git
a/website/docs/operations/system-operation/cli_tool/metadata_tool/metadata_backup_restore.md
b/website/docs/operations/system-operation/cli_tool/metadata_tool/metadata_backup_restore.md
new file mode 100644
index 0000000000..2669da34e5
--- /dev/null
+++
b/website/docs/operations/system-operation/cli_tool/metadata_tool/metadata_backup_restore.md
@@ -0,0 +1,88 @@
+---
+title: System Metadata Backup and Restore
+language: en
+sidebar_label: System Metadata Backup and Restore
+pagination_label: System Metadata Backup and Restore
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - system metadata backup and restore
+draft: true
+last_update:
+ date: 08/16/2022
+---
+
+Kylin instances are stateless services, and all state information is stored in
metadata. Therefore, backing up and restoring metadata is a crucial part of
operation and maintenance.
+
+Metadata is divided into system level and project level.
+
+### Metadata Backup {#metadata_backup}
+
+In general, it is a good practice to back up metadata before each failure
recovery or system upgrade. This can guarantee the possibility of rollback
after the operation fails, and still maintain the stability of the system in
the worst case.
+
+In addition, metadata backup is also a tool for fault finding. When the system
fails, the frontend frequently reports errors. By downloading and viewing
metadata, it is often helpful to determine whether there is a problem with the
metadata or not.
+
+Metadata can be backed up via the command line, as follows:
+
+- Metadata backup via **command line**
+
+ Kylin provides a command line tool for backing up metadata, using the
following methods:
+
+ - Backup **system level** metadata
+
+ ```sh
+ $KYLIN_HOME/bin/metastore.sh backup METADATA_BACKUP_PATH
+ ```
+ Parameter Description:
+
+ - `METADATA_BACKUP_PATH` - optional, represents the metadata storage path
of the backup, the default value is `${KYLIN_HOME}/meta_backups/`
+
+ - Backup **project level** metadata
+
+ ```sh
+ $KYLIN_HOME/bin/metastore.sh backup-project PROJECT_NAME
METADATA_BACKUP_PATH
+ ```
+
+ Parameter Description:
+
+ - `PROJECT_NAME` - required, the name of the project to be backed up,
such as learn_kylin
+ - `METADATA_BACKUP_PATH` - optional, represents the metadata storage path
of the backup, the default value is `${KYLIN_HOME}/meta_backups/`
+
+
+### Metadata Restore {#metadata_restore}
+
+Metadata recovery is required in Kylin with the **command line**.
+
+- Restore **system level** metadata
+
+ ```sh
+ $KYLIN_HOME/bin/metastore.sh restore METADATA_BACKUP_PATH [--after-truncate]
+ ```
+ Example:
+ ```sh
+ ./bin/metastore.sh restore meta_backups/2019-12-19-14-18-01_backup/
+ ```
+
+ Parameter Description:
+ - `METADATA_BACKUP_PATH` - required, represents the metadata path that are
going to be recovered, the default value is `${KYLIN_HOME}/meta_backups/
+ - `--after-truncate` - optional, if this parameter is added, the system
metadata will be completely restored, otherwise only the deleted and modified
metadata will be restored, and the new metadata will still be retained.
+
+- Restore **project level** metadata
+
+ ```sh
+ $KYLIN_HOME/bin/metastore.sh restore-project PROJECT_NAME
METADATA_BACKUP_PATH [--after-truncate]
+ ```
+ Example:
+ ```sh
+ ./bin/metastore.sh restore-project projectA
meta_backups/2019-12-19-14-18-01_backup/
+ ```
+
+ Parameter Description:
+
+ - `PROJECT_NAME` - required, represents the project name
+ - `METADATA_BACKUP_PATH` - required, represents the metadata path that are
going to be recovered, the default value is `${KYLIN_HOME}/meta_backups/
+ - `--after-truncate` - optional, if this parameter is added, the project
metadata will be completely restored, otherwise only the deleted and modified
metadata will be restored, and the new metadata will still be retained.
+
+**Caution** When run this command, Kylin will enter maintenance mode. If the
command is interrupted by force, you may need to exit maintain mode manually.
Refer [maintenance_mode](../../maintenance_mode.en.md).
diff --git a/website/docs/operations/system-operation/cli_tool/rollback.md
b/website/docs/operations/system-operation/cli_tool/rollback.md
new file mode 100644
index 0000000000..a27193153c
--- /dev/null
+++ b/website/docs/operations/system-operation/cli_tool/rollback.md
@@ -0,0 +1,123 @@
+---
+title: Rollback Tool
+language: en
+sidebar_label: Rollback Tool
+pagination_label: Rollback Tool
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - rollback tool
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+When a user error causes metadata or data loss, or when Kylin is unavailable
due to an unknown issue, you can roll back to a specified moment with the
rollback tool to ensure production stability.
+
+> Note: The rollback tool is used in some emergency cases, please use this
before read the materials carefully.
+
+### Introduction {#tools_Introduction}
+
+**How to Use**
+
+- Stop all Kylin services.
+
+- Use tools to roll back
+
+ ```bash
+ $KYLIN_HOME/bin/rollback.sh --project project_example --time '2020-09-01
15:20:19'
+ ```
+
+- Observe logs to identify differences of metadata such as project, model,
user, Segment, task, etc.
+
+- Complete the interaction and confirmation to ensure that you are aware of
the impact of the rollback.
+
+- After completed the rollback, start Kylin service.
+
+##### Parameters：
+
+- `-p，--project <arg> `: Project name [optional], `<arg>` is the project name.
+- `-t, --time <arg>`: Historical time point to roll back [required]. `<arg>`
is the specific time to roll back to, the format is ` yyyy-MM-dd HH: mm: ss`.
The available value is the time point from the earliest backup version time to
date.
+- `--skip-check-data`: Skip checking whether the resource file is available
[optional].
+
+### Use Case {#user_case}
+
+Below is a common scenario of using the rollback tool in the operational
process, describing how the tool can be used to roll back and downgrade issues
in the event of product agnostic issues.
+
+- In AI augmented mode, the `rollback_example` project has recommendation with
recommendation mode turned on. If the user accepts the recommendations under
the model at 16:06:05 on September 1, 2020, then the original model of this
project and the metadata related to the index will be updated.
+ 
+- At this point, it can be seen that the index recommended by the system has
been generated, but at this point there is an unknown problem, which results in
the index not being built properly and affects the health of the entire
cluster, and the product is also in an inoperable state.
+- To guarantee production availability, the rollback tool can be used to roll
back the metadata and data for this item to 15:20 on September 1.
+
+```sh
+$KYLIN_HOME/bin/rollback.sh --project rollback_example --time '2020-09-01
15:20:19'
+```
+
+- It can be seen that the item has returned to the state before the accident,
the index recommended by the system has disappeared, and the cluster has
returned to a stable state..
+
+
+
+- After the rollback is complete, a downgrade is also required for issues that
occur. In this example, you can click **Setting**, temporarily turn off the
smart recommendation feature under the **Basic Settings** tab first and
communicate with the Kylin technical support team in a timely manner.
+ 
+- After the product problem is fixed, you can turn on the recommendation mode
again.
+
+### Difference from Metadata Backup and Rollback Tool{#difference}
+
+Kylin now offers metadata backup and restore tools that go some way to
protecting metadata from loss. However, the tool has some limitations.
+
+- There is no way to rewind to the specified moment, you can only rewind to
the version that has been backed up in the past.
+- The metadata backup tool is straightforward, and it is possible that
metadata may not be available after being backed up. For example, some files
are cleaned up as garbage because the metadata does not exist, and the
corresponding backup metadata is not available.
+
+### Configurations{#related_configurations}
+
+
+The premise of using the rollback tool is that the resource data (cube data,
dictionary data, snapshot data, etc.) must be guaranteed not to be deleted
within the rollback time range. The retention period of the resource data
involves two configurations
+
+* `kylin.storage.time-machine-enabled` After this configuration is enabled,
the resources in the retention period will not be deleted in the KE service.
After being enabled, the snapshot data retention time will be the same as the
time configured in `kylin.storage.resource-survival-time-threshold`, the
default value is False.
+* `kylin.storage.resource-survival-time-threshold` Resource data retention
time, the default value is `7d`, unit description:` d` (day), `h` (hour),` m`
(minute).
+
+### Caution and Common Errors {#caution_and_common_errors}
+
+The following are some errors and points of attention that may be encountered
during the use of the tool
+
+**Points to take attention**
+
+- Using the rollback tool will roll back the state of the task execution to
the state of the historical moment, and will restart the execution after the KE
service is started.
+- After the rollback tool configuration is turned on, more garbage files may
be saved and more storage space may be token up. Using the garbage cleaning
tool during the retention period cannot clean up the expired resource data
during the retention period.
+- During the execution of the tool, if it is run multiple times, each run will
keep a backup of the current metadata in the `{working-dir}/_ current_backup`
directory, the file names are distinguished by time.
+- The time specified by the user cannot be greater than the current time.
+- All service nodes must be shut down before using the tool, otherwise it will
cause data inconsistency.
+- If the user manually deletes the dictionary data of the project and then
regenerates the dictionary data again, using the rollback tool will cause the
dictionary data and the index data to be inconsistent.
+- After opening the `kylin.storage.time-machine-enabled` configuration after
upgrading, users need to wait for a configured retention period before they can
be rolled back.
+- The user rolls back to the historical moment, and the snapshot data used is
also the snapshot data of the historical moment instead of using the latest
snapshot data.
+- If the rollback time specified by the user is less than the minimum time of
the metadata backup, the rollback cannot be performed.
+
+**Possible error results**
+
+- Using the rollback tool reverts the state of the task execution back to the
historical moment, and the execution is triggered again when the KE is started.
+- Turning on the time machine causes more junk files to be saved, taking up
more storage space, and using the junk cleanup tool during the retention period
does not clean up resource data that has expired during the retention period.
+- During tool execution, if there are multiple runs, each run keeps a backup
of the current metadata in the `{working-dir}/_current_backup` directory,
distinguishing the file name by time.
+- The time specified by the user cannot be greater than the current time.
+- All service nodes must be turned off before using the tool, otherwise data
inconsistencies will result.
+- If a user manually deletes the dictionary data for an item and then
regenerates the dictionary data, using the rollback tool can cause
inconsistencies between the dictionary data and CUBE data.
+- A user who has just upgraded a `kylin.storage.time-machine-enabled`
configuration needs to wait until a configuration's retention period has passed
before being guaranteed to roll back any time within the retention period.
+- The user rolls back to the historical moment and the snapshot data used is
also the snapshot data for the historical moment, not the latest snapshot data
used.
+- If the user-specified rollback time is less than the minimum time for
metadata backup, it cannot be rolled back.
+- `dectect port available failed` -> Failure to detect user ports requires
shutting down the service nodes of the cluster.
+- `check storage data available failed` -> Failed to detect resource file,
user can use `--skip-check-data` parameter to force rollback。
+- `restore current metadata failed, please restore the metadata database
manually` -> The metadata rollback fails, and overwriting with the current
backup also fails. Manual intervention is required to solve the problem. This
situation must be handled carefully to avoid loss of metadata.
+- The rollback scope of the rollback tool does not include historical
recommendations and projects manually deleted by the user
+
+### Appendix {#appendix}
+
+The following is a detailed process for the tool to perform rollback.
+
+- Backup metadata
+- Check if the cluster is stopped
+- Find the snapshot file of metadata from the backup directory, and then
replay the `auditlog` log to the time specified by the user
+- Compare the metadata differences and remind the user
+- Wait for confirmation
+- Check if the resource referenced to by metadata is available
+- Roll back the metadata. If the rollback fails, it will be overwritten with a
backup of the current metadata
diff --git
a/website/docs/operations/system-operation/diagnosis/build_flame_graph.md
b/website/docs/operations/system-operation/diagnosis/build_flame_graph.md
new file mode 100644
index 0000000000..bfea568978
--- /dev/null
+++ b/website/docs/operations/system-operation/diagnosis/build_flame_graph.md
@@ -0,0 +1,78 @@
+---
+title: Build Flame Graph
+language: en
+sidebar_label: Build Flame Graph
+pagination_label: Build Flame Graph
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - build flame graph
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+Kylin has built-in async-profiler. When flame graphs are needed to diagnose
build tasks performance, users can generate query flame graphs for Spark Driver
and Executor by calling the API interface.
+
+Since the flame graph is generated at the system level, it will affect all
projects. Only the Admin user has the authority to use this function.
+
+### Configs
+| Config | Comment
|
+|---------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|
+| kylin.engine.async-profiler-enabled | enable the profiling feature
(default to FALSE). After enables, you can trigger the generation and download
of the flame graph by calling the API |
+| kylin.engine.async-profiler-result-timeout | the timeout for the result
collection (default to 60s)
|
+| kylin.engine.async-profiler-profile-timeout | the timeout for the profiling
(default to 5min)
|
+
+
+### Start Profiling
+invoke the below HTTP API to start generating flame graph
+
+- HTTP Header
+ - `Accept: application/vnd.apache.kylin-v4-public+json`
+ - `Accept-Language: en`
+ - `Accept-Language: zh`
+ - `Content-Type: application/json;charset=utf-8`
+
+**There are two ways to generate**
+
+- GET
`http://host:port/kylin/api/jobs/profile/start_project?project={projectName}&step_id={jobStepId}¶ms={params}`
+ - URL Parameters
+ - `project`, Required, String, specifies the projectName where the current
build task is located, no default value
+ - `step_id`, Required, String, specifies the jobStepId of the current
build task, which can be found in the YARN interface, copying the rest of its
Name except `job_step_`.
+ - `params`, Optional, String, specify async-profiler parameter, default is
`start,event=cpu` (profile cpu usage)
+
+- GET
`http://host:port/kylin/api/jobs/profile/start_appid?app_id={yarnAppId}¶ms={params}`
+ - URL Parameters
+ - `app_id`, Required, String, specifies the Application ID of the current
build task submitted to YARN
+ - `params`, Optional, String, specify async-profiler parameter, default is
`start,event=cpu` (profile cpu usage)
+
+### Stop Profiling
+invoke the below HTTP API to stop generating flame graph and download flame
graph
+
+- HTTP Header
+ - `Accept: application/vnd.apache.kylin-v4-public+json`
+ - `Accept-Language: en`
+ - `Accept-Language: zh`
+ - `Content-Type: application/json;charset=utf-8`
+
+**There are two ways to get it**
+
+- GET
`http://host:port/kylin/api/jobs/profile/dump_project?project={projectName}&step_id={jobStepId}¶ms={params}`
+ - URL Parameters
+ - `project`, Required, String, specifies the projectName where the current
build task is located, no default value
+ - `step_id`, Required, String, specifies the jobStepId of the current
build task, which can be found in the YARN interface, copying the rest of its
Name except `job_step_`.
+ - `params`, Optional, String, specify the async-profiler parameter,
default is `flamegraph` (collects the results as a flame graph)
+
+- GET
`http://host:port/kylin/api/jobs/profile/dump_appid?app_id={yarnAppId}¶ms={params}`
+ - URL Parameters
+ - `app_id`, Required，String，specify the Application ID of the current
build task submitted to YARN
+ - `params`, Optional, String, specify the async-profiler parameter, the
default is `flamegraph` (collects the results as a flame graph)
+
+### Limitations
+1. Current async-profiler version comes with Kylin is Linux x64 (glibc):
async-profiler-2.5-linux-x64.tar.gz, Other platforms are not supported.
+2. The profiling may have some impact on the performance of Kylin, avoid doing
a long time profiling in production.
+3. The parameters involved in building the flame chart are system level
parameters, please do not set them at other levels as they may cause abnormal
behavior.
+4. The `params` support configuration parameters can be found at
https://github.com/jvm-profiling-tools/async-profiler
+5. On some machines, the required native libraries may fail to load when the
`/tmp` disk has the noexec attribute, causing Spark initialization to fail and
affecting normal build tasks, so this feature is disabled by default.
diff --git a/website/docs/operations/system-operation/diagnosis/diagnosis.md
b/website/docs/operations/system-operation/diagnosis/diagnosis.md
new file mode 100644
index 0000000000..7f16a0475c
--- /dev/null
+++ b/website/docs/operations/system-operation/diagnosis/diagnosis.md
@@ -0,0 +1,86 @@
+---
+title: System, Job and Query Diagnosis
+language: en
+sidebar_label: System, Job and Query Diagnosis
+pagination_label: System, Job and Query Diagnosis
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - diagnosis
+ - system diagnosis
+ - job diagnosis
+ - query diagnosis
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+
+## System, Job and Query Diagnosis
+
+Kylin users may face with many problems during usage, such as job failure,
SQL query failure, SQL query overtime, etc. In order to help solve these
problems efficiently, Kylin provides a *Diagnosis* function on Web UI to pack
related information into a zip package to help operation staff and Kyligence
Support team to analyze the root cause.
+
+Diagnosis function includes System, Job and Query Diagnosis. In addition to
the method of generating diagnostic package on web UI described in this
chapter, you can also generate the diagnostic package through the bash script.
For details, please refer to [Diagnosis Tool](cli_tool/diagnosis.en.md).
+
+
+### Generate System Diagnostic Package in Web UI
+
+System diagnostic package includes all diagnostic information of a Kylin
instance, and users can generate system diagnostic package on Web UI following
the following steps:
+
+
+
+1. Enter the **Admin** page and click the **Diagnosis** button in the lower
left corner.
+
+ > **Note**: Only the system administrator can generate the system
diagnostic package in web ui for the time being.
+
+2. Select **Time Range**: You can select *last one hour*, *last one day*,
*last three days* and *last one month*, or self-defined.
+
+ > **Note:** The selected time range must include the period of incidents.
+
+3. Select **Server**.
+
+ > **Note:** If Kylin is deployed on multiple nodes, please locate the
specific node on which your issue happened by selecting the right server name,
otherwise the generated system diagnostic package may not include useful
information about the issue.
+
+4. Click **Generate and Download** button: After the diagnostic package is
generated, the downloads will be triggered automatically. If the diagnostic
package generation fails, you can view the details of the failure on the
interface.
+
+### Generate Job Diagnostic Package in Web UI
+
+Job diagnostic package includes all diagnostic information of a specific job,
and users can generate job diagnostic package on Web UI by following the
following steps:
+
+
+
+1. After logging in to Kylin, click **Monitor** in the left navigation bar. In
the action bar of a job on the **Jobs List** page, click the **Download Job
Diagnostic Package** button.
+2. Select **Server**.
+3. Click **Generate and Download** button: After the diagnostic package is
generated, the downloads will be triggered automatically. If the diagnostic
package generation fails, you can view the details of the failure on the
interface.
+
+### Generate Query Diagnosis Package in Web UI
+
+Query diagnosis package includes all diagnostic information of a specific
query, and users can generate query diagnosis package on Web UI by following
the following steps:
+
+
+
+1. After logging in to Kylin, click **Query** in the left navigation bar. In
the action bar of a query on the **History** page, click the **Download Query
Diagnostic Package** button in **Action**.
+2. Click **Generate and Download** button: After the diagnosis package is
generated, the downloads will be triggered automatically. If the diagnosis
package generation fails, you can view the details of the failure on the
interface.
+
+By default, all users with project query permissions can download the query
diagnostic package to facilitate query problem diagnosis.
+Since the query diagnostic package contains some configuration information, if
you want to reduce the relevant permissions for downloading the query
diagnostic package, you can add configuration
`kylin.security.allow-non-admin-generate-query-diag-package=false` in
`$KYLIN_HOME/conf/kylin.properties`, only system administrators and users with
project ADMIN permissions are allowed to download the query diagnostic package.
+
+### FAQ
+
+**Q: What are the differences in the contents of the three diagnostic
packages?**
+
+For the contents of the three diagnostic packages, please refer to [Diagnosis
Package Tool](../cli_tool/diagnosis.md).
+
+**Q: If I failed to generate diagnostic packages because of timeout.**
+
+Please change parameter `kylin.diag.package.timeout-seconds`(in seconds, the
default value is one hour) in `$KYLIN_HOME/conf/kylin.properties` and restart
Kylin.
+
+**Q: What should I do if the page does not download the diagnostic package
automatically after the packaging is completed?**
+
+If the system has generated the diagnostic package successfully but fails to
download it automatically, you can click **Download Manually** at the bottom
left, select the diagnostic package you want to download, and then click the
download button to download manually.
+
+**Q: What should I do if the hostname used by Kylin contains an underscore
(`_`) and generates a diagnostic package has exception?**
+
+Please add service discovery parameter
`spring.cloud.zookeeper.discovery.instance-host=IP` in
`$KYLIN_HOME/kylin.properties.override` and restart Kylin.
diff --git
a/website/docs/operations/system-operation/diagnosis/images/diagnosis_web_en.png
b/website/docs/operations/system-operation/diagnosis/images/diagnosis_web_en.png
new file mode 100644
index 0000000000..329ee9c778
Binary files /dev/null and
b/website/docs/operations/system-operation/diagnosis/images/diagnosis_web_en.png
differ
diff --git
a/website/docs/operations/system-operation/diagnosis/images/job_diagnosis_web_en.png
b/website/docs/operations/system-operation/diagnosis/images/job_diagnosis_web_en.png
new file mode 100644
index 0000000000..5a6f0457e2
Binary files /dev/null and
b/website/docs/operations/system-operation/diagnosis/images/job_diagnosis_web_en.png
differ
diff --git
a/website/docs/operations/system-operation/diagnosis/images/query_diagnosis_web.png
b/website/docs/operations/system-operation/diagnosis/images/query_diagnosis_web.png
new file mode 100644
index 0000000000..9c84ffd914
Binary files /dev/null and
b/website/docs/operations/system-operation/diagnosis/images/query_diagnosis_web.png
differ
diff --git a/website/docs/operations/system-operation/diagnosis/intro.md
b/website/docs/operations/system-operation/diagnosis/intro.md
new file mode 100644
index 0000000000..d4a4705068
--- /dev/null
+++ b/website/docs/operations/system-operation/diagnosis/intro.md
@@ -0,0 +1,17 @@
+---
+title: Diagnosis
+language: en
+sidebar_label: Diagnosis
+pagination_label: Diagnosis
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - diagnosis
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+Kylin provides a diagnosis function to help users solve problems they may
encounter, such as job failure, SQL query failure, SQL query overtime, etc.
diff --git
a/website/docs/operations/system-operation/diagnosis/query_flame_graph.md
b/website/docs/operations/system-operation/diagnosis/query_flame_graph.md
new file mode 100644
index 0000000000..117b28c8fa
--- /dev/null
+++ b/website/docs/operations/system-operation/diagnosis/query_flame_graph.md
@@ -0,0 +1,58 @@
+---
+title: Query Flame Graph
+language: en
+sidebar_label: Query Flame Graph
+pagination_label: Query Flame Graph
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - query flame graph
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+Kylin has built-in async-profiler. When flame graphs are needed to diagnose
query performance, users can generate query flame graphs for Spark Driver and
Executor by calling the API interface.
+
+Since the flame graph is generated at the system level, it will affect all
projects. Only the Admin user has the authority to use this function.
+
+### Configs
+| Config | Comment
|
+| ----------------------------------------------------------- |
------------------------------------------------------------ |
+| kylin.query.async-profiler-enabled | enable the
profiling feature (default to TRUE). After enables, you can trigger the
generation and download of the flame graph by calling the API |
+| kylin.query.async-profiler-result-timeout | the timeout
for the result collection (default to 60s) |
+| kylin.query.async-profiler-profile-timeout | the timeout
for the profiling (default to 5min) |
+
+
+### Start Profiling
+invoke the below HTTP API to start generating flame graph
+
+- GET `http://host:port/kylin/api/query/profile/start?params={params}`
+
+- URL Parameters
+ - `params`, Optional, String, specify async-profiler params to start
profiling, default to `start,event=cpu` (profile the cpu only), ref to
https://github.com/jvm-profiling-tools/async-profiler for more parameters
+
+- HTTP Header
+ - `Accept: application/vnd.apache.kylin-v4-public+json`
+ - `Accept-Language: en`
+ - `Content-Type: application/json;charset=utf-8`
+
+### Stop Profiling
+invoke the below HTTP API to stop generating flame graph and download flame
graph
+
+- GET `http://host:port/kylin//api/query/profile/dump?params={params}`
+
+- URL Parameters
+ - `params`, Optional, String, specify async-profiler params to start
profiling, default to `flamegraph` (dump the result as flamegraph), ref to
https://github.com/jvm-profiling-tools/async-profiler for more parameters
+
+- HTTP Header
+ - `Accept: application/vnd.apache.kylin-v4-public+json`
+ - `Accept-Language: en`
+ - `Content-Type: application/json;charset=utf-8`
+
+### Limitations
+1. Current async-profiler version comes with Kylin is Linux x64 (glibc):
async-profiler-2.5-linux-x64.tar.gz, Other platforms are not supported.
+2. The profiling may have some impact on the performance of Kylin, avoid doing
a long time profiling in production.
+3. The flame graph result can only be downloaded once.
diff --git a/website/docs/operations/system-operation/guardian.md
b/website/docs/operations/system-operation/guardian.md
new file mode 100755
index 0000000000..ec80d2fc7e
--- /dev/null
+++ b/website/docs/operations/system-operation/guardian.md
@@ -0,0 +1,62 @@
+---
+title: Kylin Guardian Process
+language: en
+sidebar_label: Kylin Guardian Process
+pagination_label: Kylin Guardian Process
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - guardian process
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+Since Kylin 5.0, the system added a function of a daemon process for
monitoring the health state of Kylin. This function is called **Kylin Guardian
Process**. If the Kylin Guardian Process detects Kylin is in an unhealthy
state, it will restart Kylin server or downgrade service.
+
+### Usage
+
+#### Turn On
+Kylin Guardian Process is **disabled** by default. If you want to enable it,
you need to add the configuration `kylin.guardian.enabled = true` in the global
configuration file `$KYLIN_HOME/conf/kylin.properties`.
+> **Note**: All the following configurations take effect if
`kylin.guardian.enabled = true`
+
+If Kylin Guardian Process is enabled, a daemon process will be automatically
started after starting Kylin. This process is bound to environment variable
`KYLIN_HOME`, which means each Kylin instance has only one Kylin Guardian
Process corresponding to it.
+
+Kylin Guardian Process description:
+- The process ID is recorded in `$KYLIN_HOME/kgid`.
+
+- The log of the process is output in `$KYLIN_HOME/logs/guardian.log`.
+
+- Kylin Guardian Process will periodically check the health status of Kylin.
The time delay of the first check is configured by the parameter
`kylin.guardian.check-init-delay` (Unit: minutes), the default is 5 minutes,
and the check interval is set by the parameter `kylin.guardian.check-interval`
(Unit: minutes), the default is 1 minute.
+
+
+#### Check Items
+Kylin Guardian Process currently checks the following 4 aspects of Kylin
instance's health.
+
+- Kylin process status
+
+ If the process number file `$KYLIN_HOME/pid` exists and the corresponding
process does not exist, it means Kylin server is in an abnormal down state, and
Kylin Guardian Process will restart it.
+
+- Spark Context restart failure check
+
+ If the number of Spark Context restart failure times is greater than or
equals to the value of configuration
`kylin.guardian.restart-spark-fail-threshold`, which is 3 times by default,
Kylin Guardian Process will restart Kylin. This function is enabled by default.
If you want to disable it, please add the configuration
`kylin.guardian.restart-spark-fail-restart-enabled = false` in
`$KYLIN_HOME/conf/kylin.properties`.
+
+- **Bad Query** canceled failed check
+
+ >**Note**: Some queries will be forcibly closed due to abnormal reasons. At
this time, the query is **Bad Query**, and the common case is a timeout query.
+
+ If Kylin Guardian Process detects the number of Bad Query cancellation times
is greater than or equals to the value of configuration
`kylin.guardian.kill-slow-query-fail-threshold`, which is 3 times by default,
Kylin Guardian Process will restart Kylin. It is enabled by default. If you
want to disable it, you can add the configuration
`kylin.guardian.kill-slow-query-fail-restart-enabled = false` in
`$KYLIN_HOME/conf/kylin.properties`.
+
+- Full GC(Garbage Collection, Garbage collection mechanism in Java) duration
check
+
+ If the Full GC duration ratio in most recent period (default is value of
`kylin.guardian.full-gc-check-factor` * value of
`kylin.guardian.check-interval`) is greater than or equals to the value of
configuration `kylin.guardian.full-gc-duration-ratio-threshold` which is 75% by
default, Kylin Guardian Process will restart Kylin. It is enabled by default.
If you want to disable it, you can add the configuration
`kylin.guardian.full-gc-duration-ratio-restart-enabled = false` in `$KYLIN_HOM
[...]
+
+
+#### Kylin Guardian Process High Availability
+To ensure the high availability of Kylin Guardian Process, Kylin will also
periodically check the status of Kylin Guardian Process. If Kylin detects the
Kylin Guardian Process does not exist, it will automatically start it. The
feature is enabled by default. If you want to disable it, you can add the
configuration `kylin.guardian.ha-enabled=false` in
`$$KYLIN_HOME/conf/kylin.properties`. The time delay of the first check is
configured by the parameter `kylin.guardian.ha-check-init-delay` [...]
+
+
+#### Kylin OOM(Out of Memory) restarts automatically
+Kylin Guardian Process supports restarting Kylin when the JVM of Kylin appears
OOM.
diff --git
a/website/docs/operations/system-operation/images/forbidden_modify_metadata_during_maintenance_mode.png
b/website/docs/operations/system-operation/images/forbidden_modify_metadata_during_maintenance_mode.png
new file mode 100644
index 0000000000..b5fdfd120d
Binary files /dev/null and
b/website/docs/operations/system-operation/images/forbidden_modify_metadata_during_maintenance_mode.png
differ
diff --git
a/website/docs/operations/system-operation/images/forbidden_modify_metadata_promoting_during_maintenance_mode.png
b/website/docs/operations/system-operation/images/forbidden_modify_metadata_promoting_during_maintenance_mode.png
new file mode 100644
index 0000000000..6f5c7afdd2
Binary files /dev/null and
b/website/docs/operations/system-operation/images/forbidden_modify_metadata_promoting_during_maintenance_mode.png
differ
diff --git
a/website/docs/operations/system-operation/images/maintenance_mode.png
b/website/docs/operations/system-operation/images/maintenance_mode.png
new file mode 100644
index 0000000000..2becffa013
Binary files /dev/null and
b/website/docs/operations/system-operation/images/maintenance_mode.png differ
diff --git
a/website/docs/operations/system-operation/images/system_recover_from_maintenance_mode.png
b/website/docs/operations/system-operation/images/system_recover_from_maintenance_mode.png
new file mode 100644
index 0000000000..23b1050322
Binary files /dev/null and
b/website/docs/operations/system-operation/images/system_recover_from_maintenance_mode.png
differ
diff --git a/website/docs/operations/system-operation/intro.md
b/website/docs/operations/system-operation/intro.md
new file mode 100644
index 0000000000..c78f5ee144
--- /dev/null
+++ b/website/docs/operations/system-operation/intro.md
@@ -0,0 +1,17 @@
+---
+title: System Operation
+language: en
+sidebar_label: System Operation
+pagination_label: System Operation
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - system operation
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+This chapter introduces how to do system operation.
diff --git a/website/docs/operations/system-operation/junk_file_clean.md
b/website/docs/operations/system-operation/junk_file_clean.md
new file mode 100644
index 0000000000..6bd6008ed8
--- /dev/null
+++ b/website/docs/operations/system-operation/junk_file_clean.md
@@ -0,0 +1,90 @@
+---
+title: Junk File Cleanup
+language: en
+sidebar_label: Junk File Cleanup
+pagination_label: Junk File Cleanup
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - junk file cleanup
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+
+## Junk File Cleanup
+
+After Kylin runs for a period of time, the system may generate a certain
number of junk files, which may occupy a large amount of storage space. At this
time, junk cleaning is required.
+
+Junk file cleaning can improve the stability and performance of the Kylin
system. Effective junk file cleaning can not only save storage space, but also
ensure the ecological health of the cluster where Kylin is located.
+
+
+### Default recommended regular junk file cleaning method
+
+By default, the system will automatically clean up junk every day at 0:00 AM.
+
+- To modify the time and frequency of regular junk file cleaning, adjust the
parameters in `$KYLIN_HOME/conf/kylin.properties`. The default configuration is
`kylin.metadata.ops-cron=0 0 0 * * *`, which refers to junk file cleaning at
0:00 a.m. every day. The parameters from left to right in the configuration
items represent: seconds, minutes, hours, Day, month, day of the week. By
modifying the cron configuration, users can customize the junk file cleaning
time, for example, every Saturd [...]
+
+- The default 4-hour timeout for automatic junk file cleaning, and it will
automatically terminate after the timeout. The default configuration is
`kylin.metadata.ops-cron-timeout=4h`.
+
+- Before the system regularly cleans up junk files, the metadata will be
automatically backed up to the HDFS path
`{kylin.env.hdfs-working-dir}/{MetadataIdentitiy}/_backup/{yyyy-MM-dd-HH-mm-ss}_backup/
metadata.zip`.
+
+- The system regularly cleans up junk files and will not enter system
maintenance mode.
+
+- For more details on cron configuration, please refer to [Introduction to
CronTrigger](http://www.quartz-scheduler.org/documentation/quartz-2.3.0/tutorials/crontrigger.html).
+
+### Junk file cleanup range
+
+The scope of junk file cleanup includes:
+- Invalid or expired metadata:
+ - Query history.
+ - The total number of query history for all projects. The query history
that exceeds this threshold number
`kylin.query.queryhistory.project-max-size=10000000` (default) will be cleared.
+ - The query history of a single project exceeds this threshold
`kylin.query.queryhistory.project-max-size=1000000` (default) The query history
will be cleared.
+ - The query history time of all projects. The query history that exceeds
this threshold `kylin.query.queryhistory.survival-time-threshold=30d` (default
30 days) will be cleared. This configuration also supports units: milliseconds
ms, microseconds us, minutes m or min, hours h.
+ - Real-time job status/record table. Realtime jobs that exceed this
threshold `kylin.streaming.jobstats.survival-time-threshold=7d` (default 7
days) will be cleaned up.
+ - Invalid optimization suggestion table data.
+ - Expired capacity billing metadata. Capacity billing information that
exceeds this threshold
`kylin.garbage.storage.sourceusage-survival-time-threshold=90d` (default 90
days) will be cleaned up.
+ - Invalid or out-of-date item-related metadata.
+ - `kylin.garbage.storage.executable-survival-time-threshold=30d` (default
30 days) above this threshold and completed metadata tasks are cleaned up.
+ - Audit log. Audit logs that exceed this threshold
`kylin.metadata.audit-log.max-size=500000` (default) will be cleaned up.
+- Invalid or expired HDFS data:
+ - Asynchronous query result file. HDFS asynchronous query result files that
exceed this threshold `kylin.query.async.result-retain-days=7d` (default 7
days) will be cleaned up.
+ - Invalid or expired files on HDFS. Include invalid or expired indexes,
snapshots, dictionaries, etc.
+ - Invalid files on HDFS that exceed this threshold
`kylin.garbage.storage.cuboid-layout-survival-time-threshold=7d` (default 7
days) are cleaned up.
+ - Low Usage indexes on HDFS.
+ - Low usage storage refers to indexes whose usage frequency is lower than
a certain threshold and data built under them within a certain time interval.
You can configure the definition of low usage storage under a project in the
project's Settings > Basic Settings > Index Optimization > Low Usage Storage .
+ - If recommendation is turned off, indexes with low cost performance will
be cleaned according to the index optimization strategy during junk file
cleaning. You can also manually clean up by clicking the **Clear** button under
**Dashboard > Storage Quota > Low Usage Storage**.
+ - If recommendation is turned on, the cleanup of Low Usage storage will no
longer be triggered during junk file cleaning, and the corresponding
inefficient index will be converted to **model optimization suggestions**, and
the button to clean up junk file will not appear in the dashboard.
+
+ > Note: The default timed junk file cleaning method starts from Kylin 5.0
and later, will clean up invalid or expired HDFS data.
+
+### Compatible with historically supported junk cleaning tools
+
+> Note: In order to be compatible with the command-line tool cleanup that has
been provided in history, the behavior of the previously provided tools has not
changed. Users who have used this method can gradually abandon this method
according to the actual situation. Users who are not using this tool could not
pay attention to this section.
+
+Kylin provides a junk file cleaning command line tool for checking and
cleaning HDFS data, so as to ensure that the system is in a good running state.
Please execute the following command in the terminal:
+
+````sh
+$KYLIN_HOME/bin/kylin.sh org.apache.kylin.tool.routine.RoutineTool
+````
+
+When executing this command without any parameters, it will only list the data
in HDFS that can be cleaned, but will not perform the actual cleaning action.
+
+This command supports standard short and long parameters. The parameter
descriptions are as follows:
+- `-m, --metadata`: Perform metadata junk file cleaning.
+- `-c, --cleanup`: Perform data junk file cleanup. Without this parameter, the
tool will not make any modification to the HDFS data.
+- `-p [project...], --projects=[project...]`: Specifies the projects to clean.
When specifying multiple items, separate them with commas. Without this
parameter, the tool will clean up all items.
+- `-h, --help`: Print help information.
+- `-r number`: The number of requests per second when accessing cloud
environment object storage. `-r 10` means 10 requests per second. You can use
this parameter to limit the frequency of requests for object storage in the
cloud environment by the junk file cleaning tool to avoid errors due to
exceeding the request frequency limit.
+- `-t number`: The number of request retries when accessing the cloud
environment object storage fails. `-t 3` means to retry 3 times.
+
+**Note**: Whether this command executes metadata junk file cleaning through -m
or data junk file cleaning through -c, Kylin will enter maintenance mode. If
junk file cleaning is forcibly interrupted, you need to manually exit
maintenance mode. Refer to [ Maintenance
Mode](system-operation/maintenance_mode.en.md).
+
+In addition, from Kylin 4.5.6, the new command line tool `FastRoutineTool`
+````sh
+$KYLIN_HOME/bin/kylin.sh org.apache.kylin.tool.routine.FastRoutineTool
+````
+The only difference compared to `RoutineTool` is that when performing data
junk file cleaning with the `-c` parameter, it does not enter maintenance mode.
Maintenance mode is still entered when performing metadata junk file cleanup
via -m.
diff --git a/website/docs/operations/system-operation/limit_query.md
b/website/docs/operations/system-operation/limit_query.md
new file mode 100644
index 0000000000..b53e46b151
--- /dev/null
+++ b/website/docs/operations/system-operation/limit_query.md
@@ -0,0 +1,72 @@
+---
+title: Limit query current capacity, protect query stability
+language: en
+sidebar_label: Limit query current capacity, protect query stability
+pagination_label: Limit query current capacity, protect query stability
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - limit query current capacity
+ - protect query stability
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+Query resources are usually limited. During certain periods of time, the query
volume suddenly increases, or when a small number of large queries occupy too
many resources, query resource competition may occur, resulting in large
fluctuations in overall query performance.
+
+In order to avoid the above situation, we can adopt the query current capacity
limiting strategy, by rejecting or limiting the performance of part of large
queries, to ensure that most of the small queries are not affected, and to
ensure the overall stability of the query.
+
+
+### Query classification
+
+Through long-term observation, we can roughly divide queries into two
categories: large queries and small queries. They have different typical
characteristics:
+
+- **Big query**: The number is small and the resources are occupied. The
fluctuation of the big query has a great impact on the overall stability of the
query.
+- **Small queries**: The number is large, each small query occupies less
resources, protecting small queries can effectively ensure the overall
stability of the query.
+
+According to the characteristics of these two types of queries, we have
designed different query current limiting strategies, which can be selected as
needed. For details, see **two query current limiting strategies** below.
+
+At the same time, for the judgment of large and small queries, we also provide
parameters, allowing users to fine-tune according to the actual situation. See
below for **Determination of Large Query**.
+
+### Two query current capacity limiting strategies
+
+**Strategy 1: Small query priority scheduling strategy**
+
+After enabling the priority scheduling policy for small queries, small queries
will be scheduled first, and large queries will be scheduled later.
+
+Set `kylin.query.query-limit-enabled = true` in `kylin.properties`, the
default value is **false**. Also configure Ops Plan to enable large query
rejection policy.
+
+**Strategy 2: Large query rejection strategy**
+
+Different from the post-scheduling of large queries in strategy 1, when
strategy 2 is used, large queries will be rejected directly after reaching the
upper limit of Spark task load. Spark task load refers to the ratio of the
number of tasks in the Pending state to the number of tasks in the Running
state in the Spark cluster. This strategy requires the cooperation of the Ops
Plan to collect the task load indicator, and when the indicator value reaches
the upper limit, it triggers the re [...]
+
+Set `kylin.query.share-state-switch-implement=jdbc` in `kylin.properties`, and
configure Ops Plan to enable large query rejection policy. The default value is
**close**.
+
+Among them, the default value of Spark task load is 50. Generally, it is not
recommended to modify it.
+
+To configure the Ops Plan to turn on the large query rejection strategy,
please contact the [Kyligence Technical Support
Team](https://support.kyligence.io/#/) for help.
+
+
+### Judgment of large query
+
+An important factor that affects the effect of the above query current
limiting strategy is the determination of large queries. We provide both
default values and allow flexible adjustments based on actual queries and
system conditions.
+
+**Main principle:**
+
+The system mainly uses **data scan rows** as the basis for judging whether it
is a large query. The sum of the number of rows scanned for a query data, when
this value exceeds the threshold, it is determined as a large query, otherwise
it is a small query. This value may be different from the "Number of records
scanned by query" displayed on the page of the query result. This number of
rows refers to the number of rows of the parquet file scanned after **pruning**.
+
+**Judgment settings for large queries:**
+
+The system provides the initial threshold setting for determining whether it
is a large query and the number of data scan rows, and also provides a
mechanism to automatically update this threshold. The configuration of related
parameters will be described in detail below.
+
+To adjust, adjust the following parameters in `kylin.properties`:
+- `kylin.query.big-query-source-scan-rows-threshold`: Determines whether it is
a big query, the initial threshold of the number of rows to be scanned. The
default value is `-1` , which means that the user does not specify, and the
system automatically calculates the initial threshold at startup. In addition,
this threshold can be automatically updated to suit the cluster environment by
collecting query information during system operation.
+- `kylin.query.auto-adjust-big-query-rows-threshold-enabled`: Whether to
automatically update the above thresholds. The default value is false, set to
true to enable automatic update.
+- `kylin.query.big-query-threshold-update-interval-second`: Interval to
automatically update the above threshold. The default value is 10800, in
seconds.
+- `kylin.query.big-query-second`: The time limit that the big query needs to
meet when the above threshold is automatically updated, the default value is
10, in seconds.
+
+In addition, when the query contains limit, the following optimizations can
also be enabled to make the automatic update threshold more accurate and avoid
misjudgment of large queries.
+- `kylin.query.apply-limit-info-to-source-scan-rows-enabled`: Whether to apply
limit information to optimize scan row count estimation. The default value is
false.
diff --git a/website/docs/operations/system-operation/maintenance_mode.md
b/website/docs/operations/system-operation/maintenance_mode.md
new file mode 100644
index 0000000000..1765bb97d9
--- /dev/null
+++ b/website/docs/operations/system-operation/maintenance_mode.md
@@ -0,0 +1,76 @@
+---
+title: Maintenance Mode
+language: en
+sidebar_label: Maintenance Mode
+pagination_label: Maintenance Mode
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - maintenance mode
+draft: true
+last_update:
+ date: 08/16/2022
+---
+
+## Basic Concepts
+
+When in maintenance mode, Kylin nodes will not be able to modify metadata, and
only read operations such as queries will not be affected
+
+## Entering maintenance mode
+ Run the following command to enter maintenance mode:
+ ```sh
+ ${KYLIN_HOME}/bin/kylin.sh org.apache.kylin.tool.MaintainModeTool -on
-reason ${reason}
+ ```
+
+ **Note**:
+
+- You need to use the argument -reason to explain why you turn on maintenance
mode。
+
+ - When it is in maintenance mode, it is not allowed to enter maintenance
mode again. You need to manually exit maintenance mode first
+
+- ${reason} refers to the reason for entering maintenance mode. There are no
fixed characters. You can enter any word, such as `upgrade`
+
+ When in maintenance mode, you will get following prompt:
+
+ 
+
+ metadata modification operations, such as create project, load/unload
tables, create/update models, etc.,
+ can't be executed.
+
+ If you do the above, the following errors will occur:
+
+ 
+
+ 
+
+## Exiting Maintenance mode
+ Run the following command to exit maintenance mode:
+ ```sh
+ ${KYLIN_HOME}/bin/kylin.sh org.apache.kylin.tool.MaintainModeTool -off
+ ```
+ **Note**：While system is already in maintenance mode, the system will prompt
you after executing command. In speciality, you can use `-f` or `--force`
parameter to force to turn off maintenance mode,
+ to release all occupation of project.
+
+ After the command was executed, you may not modify metadata immediately. It
should be waiting Kylin nodes to
+ get the resources. You can refer following properties:
+ ```properties
+ kylin.server.leader-race.heart-beat-interval=30
+ ```
+ Its unit is seconds. You should wait up to 30 seconds.
+
+ During the maintenance, if you try to modify metadata, you will get
following prompt:
+
+ 
+
+
+## Recommendations for the use of maintenance mode
+
+Maintenance mode is provided to prevent metadata write conflicts in the system.
+In principle, users are not recommended to turn on or turn off this function
manually.
+When running the following commands, the system will automatically turn on the
maintenance mode, and turn off the maintenance mode after the operation ends.
+
+ - [reset admin password](../access-control/user_management.md)
+ - [junk file clean](junk_file_clean.md)
+ - [metadata
restore](cli_tool/metadata_tool/metadata_backup_restore.en.md#metadata-restore----metadata_restore)
diff --git a/website/docs/operations/system-operation/update-session-table.md
b/website/docs/operations/system-operation/update-session-table.md
new file mode 100644
index 0000000000..01f1b15af5
--- /dev/null
+++ b/website/docs/operations/system-operation/update-session-table.md
@@ -0,0 +1,46 @@
+---
+title: Update Session Table Tool
+language: en
+sidebar_label: Update Session Table Tool
+pagination_label: Update Session Table Tool
+toc_min_heading_level: 2
+toc_max_heading_level: 6
+pagination_prev: null
+pagination_next: null
+keywords:
+ - update session table tool
+draft: false
+last_update:
+ date: 08/12/2022
+---
+
+When configured `kylin.web.session.secure-random-create-enabled=true` or
`kylin.web.session.jdbc-encode-enabled=true`, the session table needs to be
upgraded, otherwise the user cannot log in.
+
+**How to Use**
+
+- Use tools to update
+
+ ```bash
+ $KYLIN_HOME/bin/kylin.sh
org.apache.kylin.tool.upgrade.UpdateSessionTableCLI
+ ```
+
+> Note: During the upgrade process, the update may fail due to permission
reasons. At this time, the operation and maintenance personnel need to manually
execute the statement to update the session table.
+
+### Sql
+
+**Use PostgreSQL as Metastore**
+
+```sql
+ALTER TABLE spring_session ALTER COLUMN SESSION_ID TYPE VARCHAR(180) , ALTER
COLUMN SESSION_ID SET NOT NULL;
+
+ALTER TABLE spring_session_ATTRIBUTES ALTER COLUMN SESSION_ID TYPE
VARCHAR(180) , ALTER COLUMN SESSION_ID SET NOT NULL;
+```
+
+**Use MySQL as Metastore**
+
+```sql
+ALTER TABLE spring_session MODIFY COLUMN SESSION_ID VARCHAR(180) NOT NULL;
+
+ALTER TABLE spring_session_ATTRIBUTES MODIFY COLUMN SESSION_ID VARCHAR(180)
NOT NULL;
+```
+
diff --git a/website/sidebars.js b/website/sidebars.js
index 37f85b5db4..ec86ae733f 100644
--- a/website/sidebars.js
+++ b/website/sidebars.js
@@ -30,7 +30,6 @@ const sidebars = {
{
type: 'category',
label: 'Tutorial',
-
items: [
{
type: 'doc',
@@ -143,9 +142,265 @@ const sidebars = {
id: 'deployment/deploy_mode/rw_separation'
},
]
+ },
+ {
+ type: 'category',
+ label: 'System Configuration',
+ link: {
+ type: 'doc',
+ id: 'configuration/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id: 'configuration/configuration'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/spark_dynamic_allocation'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/hadoop_queue_config'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/query_cache'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/https'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/spark_rpc_encryption'
+ },
+ {
+ type: 'doc',
+ id: 'configuration/log_rotate'
+ },
+ ],
+ },
+ {
+ type: 'doc',
+ id: 'deployment/installation/uninstallation'
}
],
},
+ {
+ type: 'category',
+ label: 'Operation and Maintenance Guide',
+ link: {
+ type: 'doc',
+ id: 'operations/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id: 'operations/overview'
+ },
+ {
+ type: 'category',
+ label: 'Project Operation',
+ link: {
+ type: 'doc',
+ id: 'operations/project-operation/intro'
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/project-operation/project_management'
+ },
+ {
+ type: 'doc',
+ id: 'operations/project-operation/project_settings'
+ },
+ {
+ type: 'doc',
+ id: 'operations/project-operation/alerting'
+ },
+ ],
+ },
+ {
+ type: 'category',
+ label: 'Access Control',
+ link: {
+ type: 'doc',
+ id: 'operations/access-control/intro'
+ },
+ items: [
+ {
+ type: 'doc',
+ id: 'operations/access-control/user_management'
+ },
+ {
+ type: 'doc',
+ id: 'operations/access-control/group_management'
+ },
+ {
+ type: 'category',
+ label: 'Data Access Control',
+ link: {
+ type: 'doc',
+ id:
'operations/access-control/data-access-control/intro'
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/access-control/data-access-control/project_acl'
+ },
+ {
+ type: 'doc',
+ id:
'operations/access-control/data-access-control/acl_table'
+ },
+ ],
+ },
+ ],
+ },
+ {
+ type: 'category',
+ label: 'System Operation',
+ link: {
+ type: 'doc',
+ id: 'operations/system-operation/intro',
+ },
+ items: [
+ {
+ type: 'category',
+ label: 'Diagnosis',
+ link: {
+ type: 'doc',
+ id:
'operations/system-operation/diagnosis/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/system-operation/diagnosis/diagnosis',
+ },
+ {
+ type: 'doc',
+ id:
'operations/system-operation/diagnosis/query_flame_graph',
+ },
+ {
+ type: 'doc',
+ id:
'operations/system-operation/diagnosis/build_flame_graph',
+ },
+ ],
+ },
+ {
+ type: 'doc',
+ id:
'operations/system-operation/update-session-table',
+ },
+ {
+ type: 'category',
+ label: 'CLI Operation Tool',
+ link: {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/environment_dependency_check',
+ },
+ {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/diagnosis'
+ },
+ {
+ type: 'category',
+ label: 'Metadata Tool',
+ link: {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/metadata_tool/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/metadata_tool/metadata_backup_restore'
+ },
+ ],
+ },
+ {
+ type: 'doc',
+ id:
'operations/system-operation/cli_tool/rollback'
+ },
+ ],
+ },
+ {
+ type: 'doc',
+ id: 'operations/system-operation/maintenance_mode'
+ },
+ {
+ type: 'doc',
+ id: 'operations/system-operation/guardian',
+ },
+ {
+ type: 'doc',
+ id: 'operations/system-operation/junk_file_clean',
+ },
+ {
+ type: 'doc',
+ id: 'operations/system-operation/limit_query',
+ },
+ ],
+ },
+ {
+ type: 'category',
+ label: 'Monitoring',
+ link: {
+ type: 'doc',
+ id: 'operations/monitoring/intro',
+ },
+ items: [
+ {
+ type: 'category',
+ label: 'InfluxDB',
+ link: {
+ type: 'doc',
+ id: 'operations/monitoring/influxdb/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id:
'operations/monitoring/influxdb/influxdb'
+ },
+ {
+ type: 'doc',
+ id:
'operations/monitoring/influxdb/influxdb_maintenance'
+ },
+ ],
+ },
+ {
+ type: 'doc',
+ id: 'operations/monitoring/metrics_intro',
+ },
+ {
+ type: 'doc',
+ id: 'operations/monitoring/service'
+ },
+ ],
+ },
+ {
+ type: 'category',
+ label: 'Logs',
+ link: {
+ type: 'doc',
+ id: 'operations/logs/intro',
+ },
+ items: [
+ {
+ type: 'doc',
+ id: 'operations/logs/system_log'
+ },
+ {
+ type: 'doc',
+ id: 'operations/logs/audit_log'
+ },
+ ],
+ },
+ ],
+ },
{
type: 'category',
label: 'Modeling',
@@ -272,54 +527,7 @@ const sidebars = {
},
],
},
- {
- type: 'category',
- label: 'Operation and Maintenance Guide',
- link: {
- type: 'doc',
- id: 'operations/intro',
- },
- items: [
- {
- type: 'category',
- label: 'Monitoring',
- link: {
- type: 'doc',
- id: 'operations/monitoring/intro',
- },
- items: [
- {
- type: 'category',
- label: 'InfluxDB',
- link: {
- type: 'doc',
- id: 'operations/monitoring/influxdb/intro',
- },
- items: [
- {
- type: 'doc',
- id:
'operations/monitoring/influxdb/influxdb'
- },
- {
- type: 'doc',
- id:
'operations/monitoring/influxdb/influxdb_maintenance'
- },
- ],
- },
- ],
- },
- ],
- },
- {
- type: 'category',
- label: 'Configuration Guide',
- items: [
- {
- type: 'doc',
- id: 'configuration/intro'
- },
- ],
- },
+
],
DevelopmentSideBar: [
{
