This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch asf-site
in repository
https://gitbox.apache.org/repos/asf/incubator-dolphinscheduler-website.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 8dcef02 Automated deployment: Wed Oct 14 14:19:16 UTC 2020
0a888d6a44d34a3c8b9348b1a6536937b0767b23
8dcef02 is described below
commit 8dcef023f4d8020d27f52228a2d6b674fa6af1c3
Author: dailidong <[email protected]>
AuthorDate: Wed Oct 14 14:19:17 2020 +0000
Automated deployment: Wed Oct 14 14:19:16 UTC 2020
0a888d6a44d34a3c8b9348b1a6536937b0767b23
---
en-us/docs/1.3.2/user_doc/cluster-deployment.html | 2 +-
en-us/docs/1.3.2/user_doc/cluster-deployment.json | 2 +-
en-us/docs/1.3.2/user_doc/system-manual.html | 1026 +++++++++++++++++++++
en-us/docs/1.3.2/user_doc/system-manual.json | 6 +
img/complement_en1.png | Bin 0 -> 197427 bytes
img/create_project_en1.png | Bin 0 -> 231406 bytes
6 files changed, 1034 insertions(+), 2 deletions(-)
diff --git a/en-us/docs/1.3.2/user_doc/cluster-deployment.html
b/en-us/docs/1.3.2/user_doc/cluster-deployment.html
index 17d4a17..a461c36 100644
--- a/en-us/docs/1.3.2/user_doc/cluster-deployment.html
+++ b/en-us/docs/1.3.2/user_doc/cluster-deployment.html
@@ -252,7 +252,7 @@ sslTrust="smtp.qq.com"
#</span><span class="bash"> resource storage <span
class="hljs-built_in">type</span>：HDFS,S3,NONE</span>
resourceStorageType="HDFS"
<span class="hljs-meta">
-#</span><span class="bash"> <span class="hljs-keyword">if</span>
resourceStorageType is HDFS，defaultFS write namenode address，HA you need to put
core-site.xml and hdfs-site.xml <span class="hljs-keyword">in</span> the conf
directory.</span>
+#</span><span class="bash"> If resourceStorageType = HDFS, and your Hadoop
Cluster NameNode has HA enabled, you need to put core-site.xml and
hdfs-site.xml <span class="hljs-keyword">in</span> the installPath/conf
directory. In this example, it is placed under /opt/soft/dolphinscheduler/conf,
and configure the namenode cluster name; <span class="hljs-keyword">if</span>
the NameNode is not HA, modify it to a specific IP or host name.</span>
<span class="hljs-meta">#</span><span class="bash"> <span
class="hljs-keyword">if</span> S3，write S3 address，HA，<span
class="hljs-keyword">for</span> example ：s3a://dolphinscheduler，</span>
<span class="hljs-meta">#</span><span class="bash"> Note，s3 be sure to create
the root directory /dolphinscheduler</span>
defaultFS="hdfs://mycluster:8020"
diff --git a/en-us/docs/1.3.2/user_doc/cluster-deployment.json
b/en-us/docs/1.3.2/user_doc/cluster-deployment.json
index 5f9951d..ef1fc42 100644
--- a/en-us/docs/1.3.2/user_doc/cluster-deployment.json
+++ b/en-us/docs/1.3.2/user_doc/cluster-deployment.json
@@ -1,6 +1,6 @@
{
"filename": "cluster-deployment.md",
- "__html": "<h1>Cluster Deployment</h1>\n<h1>1、Before you begin (please
install requirement basic software by yourself)</h1>\n<ul>\n<li>PostgreSQL
(8.2.15+) or MySQL (5.7) : Choose One</li>\n<li><a
href=\"https://www.oracle.com/technetwork/java/javase/downloads/index.html\";>JDK</a>
(1.8+) : Required. Double-check configure JAVA_HOME and PATH environment
variables in /etc/profile</li>\n<li>ZooKeeper (3.4.6+)
：Required</li>\n<li>Hadoop (2.6+) or MinIO ：Optional. If you need to upload a
[...]
+ "__html": "<h1>Cluster Deployment</h1>\n<h1>1、Before you begin (please
install requirement basic software by yourself)</h1>\n<ul>\n<li>PostgreSQL
(8.2.15+) or MySQL (5.7) : Choose One</li>\n<li><a
href=\"https://www.oracle.com/technetwork/java/javase/downloads/index.html\";>JDK</a>
(1.8+) : Required. Double-check configure JAVA_HOME and PATH environment
variables in /etc/profile</li>\n<li>ZooKeeper (3.4.6+)
：Required</li>\n<li>Hadoop (2.6+) or MinIO ：Optional. If you need to upload a
[...]
"link": "/en-us/docs/1.3.2/user_doc/cluster-deployment.html",
"meta": {}
}
\ No newline at end of file
diff --git a/en-us/docs/1.3.2/user_doc/system-manual.html
b/en-us/docs/1.3.2/user_doc/system-manual.html
new file mode 100644
index 0000000..8274929
--- /dev/null
+++ b/en-us/docs/1.3.2/user_doc/system-manual.html
@@ -0,0 +1,1026 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0,
maximum-scale=1.0, user-scalable=no">
+ <meta name="keywords" content="system-manual" />
+ <meta name="description" content="system-manual" />
+ <!-- 网页标签标题 -->
+ <title>system-manual</title>
+ <link rel="shortcut icon" href="/img/docsite.ico"/>
+ <link rel="stylesheet" href="/build/documentation.css" />
+</head>
+<body>
+ <div id="root"><div class="documentation-page"
data-reactroot=""><header class="header-container header-container-normal"><div
class="header-body"><a href="/en-us/index.html"><img class="logo"
src="/img/hlogo_colorful.svg"/></a><div class="search search-normal"><span
class="icon-search"></span></div><span class="language-switch
language-switch-normal">中</span><div class="header-menu"><img
class="header-menu-toggle" src="/img/system/menu_gray.png"/><div><ul
class="ant-menu blackClass ant [...]
+<h2>Get started quickly</h2>
+<blockquote>
+<p>Please refer to <a href="quick-start.html">Quick Start</a></p>
+</blockquote>
+<h2>Operation guide</h2>
+<h3>1. Home</h3>
+<p>The home page contains task status statistics, process status statistics,
and workflow definition statistics for all projects of the user.</p>
+<p align="center">
+<img src="/img/home_en.png" width="80%" />
+</p>
+<h3>2. Project management</h3>
+<h4>2.1 Create project</h4>
+<ul>
+<li>
+<p>Click "Project Management" to enter the project management page,
click the "Create Project" button, enter the project name, project
description, and click "Submit" to create a new project.</p>
+<p align="center">
+ <img src="/img/create_project_en1.png" width="80%" />
+</p>
+</li>
+</ul>
+<h4>2.2 Project home</h4>
+<ul>
+<li>
+<p>Click the project name link on the project management page to enter the
project home page, as shown in the figure below, the project home page contains
the task status statistics, process status statistics, and workflow definition
statistics of the project.</p>
+<p align="center">
+ <img src="/img/project_home_en.png" width="80%" />
+</p>
+</li>
+<li>
+<p>Task status statistics: within the specified time range, count the number
of task instances as successful submission, running, ready to pause, pause,
ready to stop, stop, failure, success, fault tolerance, kill, and waiting
threads</p>
+</li>
+<li>
+<p>Process status statistics: within the specified time range, count the
number of the status of the workflow instance as submission success, running,
ready to pause, pause, ready to stop, stop, failure, success, fault tolerance,
kill, and waiting threads</p>
+</li>
+<li>
+<p>Workflow definition statistics: Count the workflow definitions created by
this user and the workflow definitions granted to this user by the
administrator</p>
+</li>
+</ul>
+<h4>2.3 Workflow definition</h4>
+<h4><span id=creatDag>2.3.1 Create workflow definition</span></h4>
+<ul>
+<li>Click Project Management -> Workflow -> Workflow Definition to enter
the workflow definition page, and click the "Create Workflow" button
to enter the <strong>workflow DAG edit</strong> page, as shown in the following
figure:<p align="center">
+ <img src="/img/dag5.png" width="80%" />
+</p>
+</li>
+<li>Drag in the toolbar <img src="/img/shell.png" width="35"/> Add a Shell
task to the drawing board, as shown in the figure below:<p align="center">
+ <img src="/img/shell-en.png" width="80%" />
+</p>
+</li>
+<li><strong>Add parameter settings for this shell task:</strong></li>
+</ul>
+<ol>
+<li>Fill in the "Node Name", "Description", and
"Script" fields;</li>
+<li>Check “Normal” for “Run Flag”. If “Prohibit Execution” is checked, the
task will not be executed when the workflow runs;</li>
+<li>Select "Task Priority": When the number of worker threads is
insufficient, high-level tasks will be executed first in the execution queue,
and tasks with the same priority will be executed in the order of first in,
first out;</li>
+<li>Timeout alarm (optional): Check the timeout alarm, timeout failure, and
fill in the "timeout period". When the task execution time exceeds
<strong>timeout period</strong>, an alert email will be sent and the task
timeout fails;</li>
+<li>Resources (optional). Resource files are files created or uploaded on the
Resource Center -> File Management page. For example, the file name is
<code>test.sh</code>, and the command to call the resource in the script is
<code>sh test.sh</code>;</li>
+<li>Custom parameters (optional), refer to <a
href="#UserDefinedParameters">Custom Parameters</a>;</li>
+<li>Click the "Confirm Add" button to save the task settings.</li>
+</ol>
+<ul>
+<li>
+<p><strong>Increase the order of task execution:</strong> Click the icon in
the upper right corner <img src="/img/line.png" width="35"/> to connect the
task; as shown in the figure below, task 2 and task 3 are executed in parallel,
When task 1 finished execute, tasks 2 and 3 will be executed simultaneously.</p>
+<p align="center">
+ <img src="/img/dag6.png" width="80%" />
+</p>
+</li>
+<li>
+<p><strong>Delete dependencies:</strong> Click the "arrow" icon in
the upper right corner <img src="/img/arrow.png" width="35"/>, select the
connection line, and click the "Delete" icon in the upper right
corner <img src= "/img/delete.png" width="35"/>, delete dependencies between
tasks.</p>
+<p align="center">
+ <img src="/img/dag7.png" width="80%" />
+</p>
+</li>
+<li>
+<p><strong>Save workflow definition:</strong> Click the "Save"
button, and the "Set DAG chart name" pop-up box will pop up, as shown
in the figure below. Enter the workflow definition name, workflow definition
description, and set global parameters (optional, refer to <a
href="#UserDefinedParameters"> Custom parameters</a>), click the
"Add" button, and the workflow definition is created successfully.</p>
+<p align="center">
+ <img src="/img/dag8.png" width="80%" />
+ </p>
+</li>
+</ul>
+<blockquote>
+<p>For other types of tasks, please refer to <a href="#TaskParamers">Task Node
Type and Parameter Settings</a>.</p>
+</blockquote>
+<h4>2.3.2 Workflow definition operation function</h4>
+<p>Click Project Management -> Workflow -> Workflow Definition to enter
the workflow definition page, as shown below:</p>
+<p align="center">
+<img src="/img/work_list_en.png" width="80%" />
+</p>
+The operation functions of the workflow definition list are as follows:
+<ul>
+<li><strong>Edit:</strong> Only "offline" workflow definitions can
be edited. Workflow DAG editing is the same as <a href="#creatDag">Create
Workflow Definition</a>.</li>
+<li><strong>Online:</strong> When the workflow status is "Offline",
used to online workflow. Only the workflow in the "Online" state can
run, but cannot be edited.</li>
+<li><strong>Offline:</strong> When the workflow status is "Online",
used to offline workflow. Only the workflow in the "Offline" state
can be edited, but not run.</li>
+<li><strong>Run:</strong> Only workflow in the online state can run. See <a
href="#runWorkflow">2.3.3 Run Workflow</a> for the operation steps</li>
+<li><strong>Timing:</strong> Timing can only be set in online workflows, and
the system automatically schedules the workflow to run on a regular basis. The
status after creating a timing is "offline", and the timing must be
online on the timing management page to take effect. See <a
href="#creatTiming">2.3.4 Workflow Timing</a> for timing operation steps.</li>
+<li><strong>Timing Management:</strong> The timing management page can be
edited, online/offline, and deleted.</li>
+<li><strong>Delete:</strong> Delete the workflow definition.</li>
+<li><strong>Download:</strong> Download workflow definition to local.</li>
+<li><strong>Tree Diagram:</strong> Display the task node type and task status
in a tree structure, as shown in the figure below:<p align="center">
+ <img src="/img/tree_en.png" width="80%" />
+</p>
+</li>
+</ul>
+<h4><span id=runWorkflow>2.3.3 Run the workflow</span></h4>
+<ul>
+<li>
+<p>Click Project Management -> Workflow -> Workflow Definition to enter
the workflow definition page, as shown in the figure below, click the "Go
Online" button <img src="/img/online.png" width="35"/>，Go online
workflow.</p>
+<p align="center">
+ <img src="/img/work_list_en.png" width="80%" />
+</p>
+</li>
+<li>
+<p>Click the "Run" button to pop up the startup parameter setting
pop-up box, as shown in the figure below, set the startup parameters, click the
"Run" button in the pop-up box, the workflow starts running, and the
workflow instance page generates a workflow instance.</p>
+ <p align="center">
+ <img src="/img/run_work_en.png" width="80%" />
+ </p>
+<span id=runParamers>Description of workflow operating parameters:</span>
+<pre><code>* Failure strategy: When a task node fails to execute, other
parallel task nodes need to execute the strategy. "Continue" means:
after a certain task fails, other task nodes execute normally; "End"
means: terminate all tasks being executed, and terminate the entire process.
+* Notification strategy: When the process is over, the process execution
information notification email is sent according to the process status,
including any status is not sent, successful sent, failed sent, successful or
failed sent.
+* Process priority: The priority of process operation, divided into five
levels: highest (HIGHEST), high (HIGH), medium (MEDIUM), low (LOW), and lowest
(LOWEST). When the number of master threads is insufficient, high-level
processes will be executed first in the execution queue, and processes with the
same priority will be executed in a first-in first-out order.
+* Worker group: The process can only be executed in the specified worker
machine group. The default is Default, which can be executed on any worker.
+* Notification group: select notification strategy||timeout alarm||when fault
tolerance occurs, process information or email will be sent to all members in
the notification group.
+* Recipient: Select notification policy||Timeout alarm||When fault tolerance
occurs, process information or alarm email will be sent to the recipient list.
+* Cc: Select the notification strategy||Timeout alarm||When fault tolerance
occurs, the process information or warning email will be copied to the CC list.
+* Complement: Two modes including serial complement and parallel complement.
Serial complement: within the specified time range, the complement is executed
sequentially from the start date to the end date, and only one process instance
is generated; parallel complement: within the specified time range, multiple
days are complemented at the same time to generate N process instances.
+</code></pre>
+<ul>
+<li>For example, you need to fill in the data from May 1 to May 10.</li>
+</ul>
+ <p align="center">
+ <img src="/img/complement_en1.png" width="80%" />
+ </p>
+<blockquote>
+<p>Serial mode: The complement is executed sequentially from May 1 to May 10,
and a process instance is generated on the process instance page;</p>
+</blockquote>
+<blockquote>
+<p>Parallel mode: The tasks from May 1 to may 10 are executed simultaneously,
and 10 process instances are generated on the process instance page.</p>
+</blockquote>
+</li>
+</ul>
+<h4><span id=creatTiming>2.3.4 Workflow timing</span></h4>
+<ul>
+<li>Create timing: Click Project Management->Workflow->Workflow
Definition, enter the workflow definition page, go online the workflow, click
the "timing" button <img src="/img/timing.png" width="35"/> ,The
timing parameter setting dialog box pops up, as shown in the figure below:<p
align="center">
+ <img src="/img/time_schedule_en.png" width="80%" />
+</p>
+</li>
+<li>Choose the start and end time. In the start and end time range, the
workflow is run at regular intervals; not in the start and end time range, no
more regular workflow instances are generated.</li>
+<li>Add a timing that is executed once every day at 5 AM, as shown in the
following figure:<p align="center">
+ <img src="/img/timer-en.png" width="80%" />
+</p>
+</li>
+<li>Failure strategy, notification strategy, process priority, worker group,
notification group, recipient, and CC are the same as <a
href="#runParamers">workflow running parameters</a>.</li>
+<li>Click the "Create" button to create the timing successfully. At
this time, the timing status is "<strong>Offline</strong>" and the
timing needs to be <strong>Online</strong> to take effect.</li>
+<li>Timing online: Click the "timing management" button <img
src="/img/timeManagement.png" width="35"/>, enter the timing management page,
click the "online" button, the timing status will change to
"online", as shown in the below figure, the workflow takes effect
regularly.<p align="center">
+ <img src="/img/time-manage-list-en.png" width="80%" />
+</p>
+</li>
+</ul>
+<h4>2.3.5 Import workflow</h4>
+<p>Click Project Management -> Workflow -> Workflow Definition to enter
the workflow definition page, click the "Import Workflow" button to
import the local workflow file, the workflow definition list displays the
imported workflow, and the status is offline.</p>
+<h4>2.4 Workflow instance</h4>
+<h4>2.4.1 View workflow instance</h4>
+<ul>
+<li>Click Project Management -> Workflow -> Workflow Instance to enter
the Workflow Instance page, as shown in the figure below: <p align="center">
+ <img src="/img/instance-list-en.png" width="80%" />
+ </p>
+</li>
+<li>Click the workflow name to enter the DAG view page to view the task
execution status, as shown in the figure below.<p align="center">
+ <img src="/img/instance-runs-en.png" width="80%" />
+</p>
+</li>
+</ul>
+<h4>2.4.2 View task log</h4>
+<ul>
+<li>Enter the workflow instance page, click the workflow name, enter the DAG
view page, double-click the task node, as shown in the following figure: <p
align="center">
+ <img src="/img/instanceViewLog-en.png" width="80%" />
+ </p>
+</li>
+<li>Click "View Log", a log pop-up box will pop up, as shown in the
figure below, the task log can also be viewed on the task instance page, refer
to <a href="#taskLog">Task View Log</a>。 <p align="center">
+ <img src="/img/task-log-en.png" width="80%" />
+ </p>
+</li>
+</ul>
+<h4>2.4.3 View task history</h4>
+<ul>
+<li>Click Project Management -> Workflow -> Workflow Instance to enter
the workflow instance page, and click the workflow name to enter the workflow
DAG page;</li>
+<li>Double-click the task node, as shown in the figure below, click "View
History" to jump to the task instance page, and display a list of task
instances running by the workflow instance <p align="center">
+ <img src="/img/task_history_en.png" width="80%" />
+ </p>
+</li>
+</ul>
+<h4>2.4.4 View operating parameters</h4>
+<ul>
+<li>Click Project Management -> Workflow -> Workflow Instance to enter
the workflow instance page, and click the workflow name to enter the workflow
DAG page;</li>
+<li>Click the icon in the upper left corner <img
src="/img/run_params_button.png" width="35"/>，View the startup parameters of
the workflow instance; click the icon <img src="/img/global_param.png"
width="35"/>，View the global and local parameters of the workflow instance, as
shown in the following figure: <p align="center">
+ <img src="/img/run_params_en.png" width="80%" />
+ </p>
+</li>
+</ul>
+<h4>2.4.4 Workflow instance operation function</h4>
+<p>Click Project Management -> Workflow -> Workflow Instance to enter
the Workflow Instance page, as shown in the figure below:</p>
+ <p align="center">
+ <img src="/img/instance-list-en.png" width="80%" />
+ </p>
+<ul>
+<li><strong>Edit：</strong> Only terminated processes can be edited. Click the
"Edit" button or the name of the workflow instance to enter the DAG
edit page. After edit, click the "Save" button to pop up the Save DAG
pop-up box, as shown in the figure below. In the pop-up box, check
"Whether to update to workflow definition" and save After that, the
workflow definition will be updated; if it is not checked, the workflow
definition will not be updated. <p al [...]
+ <img src="/img/editDag-en.png" width="80%" />
+ </p>
+</li>
+<li><strong>Rerun：</strong> Re-execute the terminated process.</li>
+<li><strong>Recovery failed：</strong> For failed processes, you can perform
recovery operations, starting from the failed node.</li>
+<li><strong>Stop：</strong> To <strong>stop</strong> the running process, the
background will first <code>kill</code>worker process, and then execute
<code>kill -9</code> operation</li>
+<li><strong>Pause:</strong> Perform a <strong>pause</strong> operation on the
running process, the system status will change to <strong>waiting for
execution</strong>, it will wait for the end of the task being executed, and
pause the next task to be executed.</li>
+<li><strong>Resume pause:</strong> To resume the paused process, start running
directly from the <strong>paused node</strong></li>
+<li><strong>Delete:</strong> Delete the workflow instance and the task
instance under the workflow instance</li>
+<li><strong>Gantt chart:</strong> The vertical axis of the Gantt chart is the
topological sorting of task instances under a certain workflow instance, and
the horizontal axis is the running time of the task instances, as shown in the
figure: <p align="center">
+ <img src="/img/gantt-en.png" width="80%" />
+ </p>
+</li>
+</ul>
+<h4>2.5 Task instance</h4>
+<ul>
+<li>
+<p>Click Project Management -> Workflow -> Task Instance to enter the
task instance page, as shown in the figure below, click the name of the
workflow instance, you can jump to the workflow instance DAG chart to view the
task status.</p>
+ <p align="center">
+ <img src="/img/task-list-en.png" width="80%" />
+ </p>
+</li>
+<li>
+<p><span id=taskLog>View log：</span>Click the "view log" button in
the operation column to view the log of task execution.</p>
+ <p align="center">
+ <img src="/img/task-log2-en.png" width="80%" />
+ </p>
+</li>
+</ul>
+<h3>3. Resource Center</h3>
+<h4>3.1 hdfs resource configuration</h4>
+<ul>
+<li>Upload resource files and udf functions, all uploaded files and resources
will be stored on hdfs, so the following configuration items are required:</li>
+</ul>
+<pre><code>
+conf/common/common.properties
+ # Users who have permission to create directories under the HDFS root path
+ hdfs.root.user=hdfs
+ # data base dir, resource file will store to this hadoop hdfs path, self
configuration, please make sure the directory exists on hdfs and have read
write permissions。"/escheduler" is recommended
+ data.store2hdfs.basepath=/dolphinscheduler
+ # resource upload startup type : HDFS,S3,NONE
+ res.upload.startup.type=HDFS
+ # whether kerberos starts
+ hadoop.security.authentication.startup.state=false
+ # java.security.krb5.conf path
+ java.security.krb5.conf.path=/opt/krb5.conf
+ # loginUserFromKeytab user
+ [email protected]
+ # loginUserFromKeytab path
+ login.user.keytab.path=/opt/hdfs.headless.keytab
+
+conf/common/hadoop.properties
+ # ha or single namenode,If namenode ha needs to copy core-site.xml and
hdfs-site.xml
+ # to the conf directory，support s3，for example : s3a://dolphinscheduler
+ fs.defaultFS=hdfs://mycluster:8020
+ #resourcemanager ha note this need ips , this empty if single
+ yarn.resourcemanager.ha.rm.ids=192.168.xx.xx,192.168.xx.xx
+ # If it is a single resourcemanager, you only need to configure one host
name. If it is resourcemanager HA, the default configuration is fine
+ yarn.application.status.address=http://xxxx:8088/ws/v1/cluster/apps/%s
+
+</code></pre>
+<ul>
+<li>Only one address needs to be configured for yarn.resourcemanager.ha.rm.ids
and yarn.application.status.address, and the other address is empty.</li>
+<li>You need to copy core-site.xml and hdfs-site.xml from the conf directory
of the Hadoop cluster to the conf directory of the dolphinscheduler project,
and restart the api-server service.</li>
+</ul>
+<h4>3.2 File management</h4>
+<blockquote>
+<p>It is the management of various resource files, including creating basic
txt/log/sh/conf/py/java and other files, uploading jar packages and other types
of files, and can do edit, rename, download, delete and other operations.</p>
+</blockquote>
+ <p align="center">
+ <img src="/img/file-manage-en.png" width="80%" />
+ </p>
+<ul>
+<li>Create a file
+<blockquote>
+<p>The file format supports the following types: txt, log, sh, conf, cfg, py,
java, sql, xml, hql, properties</p>
+</blockquote>
+</li>
+</ul>
+<p align="center">
+ <img src="/img/file_create_en.png" width="80%" />
+ </p>
+<ul>
+<li>upload files</li>
+</ul>
+<blockquote>
+<p>Upload file: Click the "Upload File" button to upload, drag the
file to the upload area, the file name will be automatically completed with the
uploaded file name</p>
+</blockquote>
+<p align="center">
+ <img src="/img/file-upload-en.png" width="80%" />
+ </p>
+<ul>
+<li>File View</li>
+</ul>
+<blockquote>
+<p>For the file types that can be viewed, click the file name to view the file
details</p>
+</blockquote>
+<p align="center">
+ <img src="/img/file_detail_en.png" width="80%" />
+ </p>
+<ul>
+<li>download file</li>
+</ul>
+<blockquote>
+<p>Click the "Download" button in the file list to download the file
or click the "Download" button in the upper right corner of the file
details to download the file</p>
+</blockquote>
+<ul>
+<li>File rename</li>
+</ul>
+<p align="center">
+ <img src="/img/file_rename_en.png" width="80%" />
+ </p>
+<ul>
+<li>delete
+<blockquote>
+<p>File list -> Click the "Delete" button to delete the specified
file</p>
+</blockquote>
+</li>
+</ul>
+<h4>3.3 UDF management</h4>
+<h4>3.3.1 Resource management</h4>
+<blockquote>
+<p>The resource management and file management functions are similar. The
difference is that the resource management is the uploaded UDF function, and
the file management uploads the user program, script and configuration file.
+Operation function: rename, download, delete.</p>
+</blockquote>
+<ul>
+<li>Upload udf resources
+<blockquote>
+<p>Same as uploading files.</p>
+</blockquote>
+</li>
+</ul>
+<h4>3.3.2 Function management</h4>
+<ul>
+<li>Create UDF function
+<blockquote>
+<p>Click "Create UDF Function", enter the udf function parameters,
select the udf resource, and click "Submit" to create the udf
function.</p>
+</blockquote>
+</li>
+</ul>
+<blockquote>
+<p>Currently only supports temporary UDF functions of HIVE</p>
+</blockquote>
+<ul>
+<li>UDF function name: the name when the UDF function is entered</li>
+<li>Package name Class name: Enter the full path of the UDF function</li>
+<li>UDF resource: Set the resource file corresponding to the created UDF</li>
+</ul>
+<p align="center">
+ <img src="/img/udf_edit_en.png" width="80%" />
+ </p>
+<h3>4. Create data source</h3>
+<blockquote>
+<p>Data source center supports MySQL, POSTGRESQL, HIVE/IMPALA, SPARK,
CLICKHOUSE, ORACLE, SQLSERVER and other data sources</p>
+</blockquote>
+<h4>4.1 Create/Edit MySQL data source</h4>
+<ul>
+<li>
+<p>Click "Data Source Center -> Create Data Source" to create
different types of data sources according to requirements.</p>
+</li>
+<li>
+<p>Data source: select MYSQL</p>
+</li>
+<li>
+<p>Data source name: enter the name of the data source</p>
+</li>
+<li>
+<p>Description: Enter a description of the data source</p>
+</li>
+<li>
+<p>IP hostname: enter the IP to connect to MySQL</p>
+</li>
+<li>
+<p>Port: Enter the port to connect to MySQL</p>
+</li>
+<li>
+<p>Username: Set the username for connecting to MySQL</p>
+</li>
+<li>
+<p>Password: Set the password for connecting to MySQL</p>
+</li>
+<li>
+<p>Database name: Enter the name of the database connected to MySQL</p>
+</li>
+<li>
+<p>Jdbc connection parameters: parameter settings for MySQL connection, filled
in in JSON form</p>
+</li>
+</ul>
+<p align="center">
+ <img src="/img/mysql-en.png" width="80%" />
+ </p>
+<blockquote>
+<p>Click "Test Connection" to test whether the data source can be
successfully connected.</p>
+</blockquote>
+<h4>4.2 Create/Edit POSTGRESQL data source</h4>
+<ul>
+<li>Data source: select POSTGRESQL</li>
+<li>Data source name: enter the name of the data source</li>
+<li>Description: Enter a description of the data source</li>
+<li>IP/Host Name: Enter the IP to connect to POSTGRESQL</li>
+<li>Port: Enter the port to connect to POSTGRESQL</li>
+<li>Username: Set the username for connecting to POSTGRESQL</li>
+<li>Password: Set the password for connecting to POSTGRESQL</li>
+<li>Database name: Enter the name of the database connected to POSTGRESQL</li>
+<li>Jdbc connection parameters: parameter settings for POSTGRESQL connection,
filled in in JSON form</li>
+</ul>
+<p align="center">
+ <img src="/img/postgresql-en.png" width="80%" />
+ </p>
+<h4>4.3 Create/Edit HIVE data source</h4>
+<p>1.Use HiveServer2 to connect</p>
+ <p align="center">
+ <img src="/img/hive-en.png" width="80%" />
+ </p>
+<ul>
+<li>
+<p>Data source: select HIVE</p>
+</li>
+<li>
+<p>Data source name: enter the name of the data source</p>
+</li>
+<li>
+<p>Description: Enter a description of the data source</p>
+</li>
+<li>
+<p>IP/Host Name: Enter the IP connected to HIVE</p>
+</li>
+<li>
+<p>Port: Enter the port connected to HIVE</p>
+</li>
+<li>
+<p>Username: Set the username for connecting to HIVE</p>
+</li>
+<li>
+<p>Password: Set the password for connecting to HIVE</p>
+</li>
+<li>
+<p>Database name: Enter the name of the database connected to HIVE</p>
+</li>
+<li>
+<p>Jdbc connection parameters: parameter settings for HIVE connection, filled
in in JSON form</p>
+<p>2.Use HiveServer2 HA Zookeeper to connect</p>
+</li>
+</ul>
+ <p align="center">
+ <img src="/img/hive1-en.png" width="80%" />
+ </p>
+<p>Note: If you enable <strong>kerberos</strong>, you need to fill in
<strong>Principal</strong></p>
+<p align="center">
+ <img src="/img/hive-en.png" width="80%" />
+ </p>
+<h4>4.4 Create/Edit Spark data source</h4>
+<p align="center">
+ <img src="/img/spark-en.png" width="80%" />
+ </p>
+<ul>
+<li>Data source: select Spark</li>
+<li>Data source name: enter the name of the data source</li>
+<li>Description: Enter a description of the data source</li>
+<li>IP/Hostname: Enter the IP connected to Spark</li>
+<li>Port: Enter the port connected to Spark</li>
+<li>Username: Set the username for connecting to Spark</li>
+<li>Password: Set the password for connecting to Spark</li>
+<li>Database name: Enter the name of the database connected to Spark</li>
+<li>Jdbc connection parameters: parameter settings for Spark connection,
filled in in JSON form</li>
+</ul>
+<h3>5. Security Center (Permission System)</h3>
+<pre><code> * Only the administrator account in the security center has the
authority to operate. It has functions such as queue management, tenant
management, user management, alarm group management, worker group management,
token management, etc. In the user management module, resources, data sources,
projects, etc. Authorization
+ * Administrator login, default user name and password:
admin/dolphinscheduler123
+</code></pre>
+<h4>5.1 Create queue</h4>
+<ul>
+<li>Queue is used when the "queue" parameter is needed to execute
programs such as spark and mapreduce.</li>
+<li>The administrator enters the Security Center->Queue Management page and
clicks the "Create Queue" button to create a queue.</li>
+</ul>
+<p align="center">
+ <img src="/img/create-queue-en.png" width="80%" />
+ </p>
+<h4>5.2 Add tenant</h4>
+<ul>
+<li>The tenant corresponds to the Linux user, which is used by the worker to
submit the job. If Linux does not have this user, the worker will create this
user when executing the script.</li>
+<li>Tenant Code: <strong>Tenant Code is the only user on Linux and cannot be
repeated</strong></li>
+<li>The administrator enters the Security Center->Tenant Management page
and clicks the "Create Tenant" button to create a tenant.</li>
+</ul>
+ <p align="center">
+ <img src="/img/addtenant-en.png" width="80%" />
+ </p>
+<h4>5.3 Create normal user</h4>
+<ul>
+<li>
+<p>Users are divided into <strong>administrator users</strong> and
<strong>normal users</strong></p>
+<ul>
+<li>The administrator has authorization and user management authority, but
does not have the authority to create project and workflow definition
operations.</li>
+<li>Ordinary users can create projects and create, edit, and execute workflow
definitions.</li>
+<li>Note: If the user switches tenants, all resources under the tenant where
the user belongs will be copied to the new tenant that is switched.</li>
+</ul>
+</li>
+<li>
+<p>The administrator enters the Security Center -> User Management page and
clicks the "Create User" button to create a user.</p>
+</li>
+</ul>
+<p align="center">
+ <img src="/img/user-en.png" width="80%" />
+ </p>
+<blockquote>
+<p><strong>Edit user information</strong></p>
+</blockquote>
+<ul>
+<li>The administrator enters the Security Center->User Management page and
clicks the "Edit" button to edit user information.</li>
+<li>After an ordinary user logs in, click the user information in the user
name drop-down box to enter the user information page, and click the
"Edit" button to edit the user information.</li>
+</ul>
+<blockquote>
+<p><strong>Modify user password</strong></p>
+</blockquote>
+<ul>
+<li>The administrator enters the Security Center->User Management page and
clicks the "Edit" button. When editing user information, enter the
new password to modify the user password.</li>
+<li>After a normal user logs in, click the user information in the user name
drop-down box to enter the password modification page, enter the password and
confirm the password and click the "Edit" button, then the password
modification is successful.</li>
+</ul>
+<h4>5.4 Create alarm group</h4>
+<ul>
+<li>The alarm group is a parameter set at startup. After the process ends, the
status of the process and other information will be sent to the alarm group in
the form of email.</li>
+</ul>
+<ul>
+<li>
+<p>The administrator enters the Security Center -> Alarm Group Management
page and clicks the "Create Alarm Group" button to create an alarm
group.</p>
+<p align="center">
+ <img src="/img/mail-en.png" width="80%" />
+</li>
+</ul>
+<h4>5.5 Token management</h4>
+<blockquote>
+<p>Since the back-end interface has login check, token management provides a
way to perform various operations on the system by calling the interface.</p>
+</blockquote>
+<ul>
+<li>
+<p>The administrator enters the Security Center -> Token Management page,
clicks the "Create Token" button, selects the expiration time and
user, clicks the "Generate Token" button, and clicks the
"Submit" button, then the selected user's token is created
successfully.</p>
+<p align="center">
+ <img src="/img/create-token-en.png" width="80%" />
+ </p>
+<ul>
+<li>After an ordinary user logs in, click the user information in the user
name drop-down box, enter the token management page, select the expiration
time, click the "generate token" button, and click the
"submit" button, then the user creates a token successfully.</li>
+<li>Call example:</li>
+</ul>
+</li>
+</ul>
+<pre><code>Token call example
+ /**
+ * test token
+ */
+ public void doPOSTParam()throws Exception{
+ // create HttpClient
+ CloseableHttpClient httpclient = HttpClients.createDefault();
+
+ // create http post request
+ HttpPost httpPost = new
HttpPost("http://127.0.0.1:12345/escheduler/projects/create");
+ httpPost.setHeader("token", "123");
+ // set parameters
+ List<NameValuePair> parameters = new
ArrayList<NameValuePair>();
+ parameters.add(new BasicNameValuePair("projectName",
"qzw"));
+ parameters.add(new BasicNameValuePair("desc",
"qzw"));
+ UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(parameters);
+ httpPost.setEntity(formEntity);
+ CloseableHttpResponse response = null;
+ try {
+ // execute
+ response = httpclient.execute(httpPost);
+ // response status code 200
+ if (response.getStatusLine().getStatusCode() == 200) {
+ String content = EntityUtils.toString(response.getEntity(),
"UTF-8");
+ System.out.println(content);
+ }
+ } finally {
+ if (response != null) {
+ response.close();
+ }
+ httpclient.close();
+ }
+ }
+</code></pre>
+<h4>5.6 Granted permission</h4>
+<pre><code>* Granted permissions include project permissions, resource
permissions, data source permissions, UDF function permissions.
+* The administrator can authorize the projects, resources, data sources and
UDF functions not created by ordinary users. Because the authorization methods
for projects, resources, data sources and UDF functions are the same, we take
project authorization as an example.
+* Note: For projects created by users themselves, the user has all
permissions. The project list and the selected project list will not be
displayed.
+</code></pre>
+<ul>
+<li>The administrator enters the Security Center -> User Management page
and clicks the "Authorize" button of the user who needs to be
authorized, as shown in the figure below:</li>
+</ul>
+ <p align="center">
+ <img src="/img/auth-en.png" width="80%" />
+</p>
+<ul>
+<li>Select the project to authorize the project.</li>
+</ul>
+<p align="center">
+ <img src="/img/authproject-en.png" width="80%" />
+ </p>
+<ul>
+<li>Resources, data sources, and UDF function authorization are the same as
project authorization.</li>
+</ul>
+<h3>6. monitoring Center</h3>
+<h4>6.1 Service management</h4>
+<ul>
+<li>Service management is mainly to monitor and display the health status and
basic information of each service in the system</li>
+</ul>
+<h4>6.1.1 master monitoring</h4>
+<ul>
+<li>Mainly related to master information.</li>
+</ul>
+<p align="center">
+ <img src="/img/master-jk-en.png" width="80%" />
+ </p>
+<h4>6.1.2 worker monitoring</h4>
+<ul>
+<li>Mainly related to worker information.</li>
+</ul>
+<p align="center">
+ <img src="/img/worker-jk-en.png" width="80%" />
+ </p>
+<h4>6.1.3 Zookeeper monitoring</h4>
+<ul>
+<li>Mainly related configuration information of each worker and master in
zookpeeper.</li>
+</ul>
+<p align="center">
+ <img src="/img/zookeeper-monitor-en.png" width="80%" />
+ </p>
+<h4>6.1.4 DB monitoring</h4>
+<ul>
+<li>Mainly the health of the DB</li>
+</ul>
+<p align="center">
+ <img src="/img/mysql-jk-en.png" width="80%" />
+ </p>
+<h4>6.2 Statistics management</h4>
+<p align="center">
+ <img src="/img/statistics-en.png" width="80%" />
+ </p>
+<ul>
+<li>Number of commands to be executed: statistics on the t_ds_command
table</li>
+<li>The number of failed commands: statistics on the t_ds_error_command
table</li>
+<li>Number of tasks to run: Count the data of task_queue in Zookeeper</li>
+<li>Number of tasks to be killed: Count the data of task_kill in Zookeeper</li>
+</ul>
+<h3>7. <span id=TaskParamers>Task node type and parameter settings</span></h3>
+<h4>7.1 Shell node</h4>
+<blockquote>
+<p>Shell node, when the worker is executed, a temporary shell script is
generated, and the linux user with the same name as the tenant executes the
script.</p>
+</blockquote>
+<ul>
+<li>
+<p>Click Project Management-Project Name-Workflow Definition, and click the
"Create Workflow" button to enter the DAG editing page.</p>
+</li>
+<li>
+<p>Drag <img src="/img/shell.png" width="35"/> from the toolbar to the drawing
board, as shown in the figure below:</p>
+<p align="center">
+ <img src="/img/shell-en.png" width="80%" />
+</p>
+</li>
+<li>
+<p>Node name: The node name in a workflow definition is unique.</p>
+</li>
+<li>
+<p>Run flag: Identifies whether this node can be scheduled normally, if it
does not need to be executed, you can turn on the prohibition switch.</p>
+</li>
+<li>
+<p>Descriptive information: describe the function of the node.</p>
+</li>
+<li>
+<p>Task priority: When the number of worker threads is insufficient, they are
executed in order from high to low, and when the priority is the same, they are
executed according to the first-in first-out principle.</p>
+</li>
+<li>
+<p>Worker grouping: Tasks are assigned to the machines of the worker group to
execute. If Default is selected, a worker machine will be randomly selected for
execution.</p>
+</li>
+<li>
+<p>Number of failed retry attempts: The number of times the task failed to be
resubmitted. It supports drop-down and hand-filling.</p>
+</li>
+<li>
+<p>Failed retry interval: The time interval for resubmitting the task after a
failed task. It supports drop-down and hand-filling.</p>
+</li>
+<li>
+<p>Timeout alarm: Check the timeout alarm and timeout failure. When the task
exceeds the "timeout period", an alarm email will be sent and the
task execution will fail.</p>
+</li>
+<li>
+<p>Script: SHELL program developed by users.</p>
+</li>
+<li>
+<p>Resource: Refers to the list of resource files that need to be called in
the script, and the files uploaded or created by the resource center-file
management.</p>
+</li>
+<li>
+<p>User-defined parameters: It is a user-defined parameter that is part of
SHELL, which will replace the content with ${variable} in the script.</p>
+</li>
+</ul>
+<h4>7.2 Sub-process node</h4>
+<ul>
+<li>The sub-process node is to execute a certain external workflow definition
as a task node.
+<blockquote>
+<p>Drag the <img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SUB_PROCESS.png";
alt="PNG"> task node in the toolbar to the drawing board, as shown in the
following figure:</p>
+</blockquote>
+</li>
+</ul>
+<p align="center">
+ <img src="/img/sub-process-en.png" width="80%" />
+ </p>
+<ul>
+<li>Node name: The node name in a workflow definition is unique</li>
+<li>Run flag: identify whether this node can be scheduled normally</li>
+<li>Descriptive information: describe the function of the node</li>
+<li>Timeout alarm: Check the timeout alarm and timeout failure. When the task
exceeds the "timeout period", an alarm email will be sent and the
task execution will fail.</li>
+<li>Sub-node: It is the workflow definition of the selected sub-process. Enter
the sub-node in the upper right corner to jump to the workflow definition of
the selected sub-process</li>
+</ul>
+<h4>7.3 DEPENDENT node</h4>
+<ul>
+<li>Dependent nodes are <strong>dependency check nodes</strong>. For example,
process A depends on the successful execution of process B yesterday, and the
dependent node will check whether process B has a successful execution
yesterday.</li>
+</ul>
+<blockquote>
+<p>Drag the <img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_DEPENDENT.png";
alt="PNG"> task node in the toolbar to the drawing board, as shown in the
following figure:</p>
+</blockquote>
+<p align="center">
+ <img src="/img/dependent-nodes-en.png" width="80%" />
+ </p>
+<blockquote>
+<p>The dependent node provides a logical judgment function, such as checking
whether the B process was successful yesterday, or whether the C process was
executed successfully.</p>
+</blockquote>
+ <p align="center">
+ <img src="/img/depend-node-en.png" width="80%" />
+ </p>
+<blockquote>
+<p>For example, process A is a weekly report task, processes B and C are daily
tasks, and task A requires tasks B and C to be successfully executed every day
of the last week, as shown in the figure:</p>
+</blockquote>
+ <p align="center">
+ <img src="/img/depend-node1-en.png" width="80%" />
+ </p>
+<blockquote>
+<p>If the weekly report A also needs to be executed successfully last
Tuesday:</p>
+</blockquote>
+ <p align="center">
+ <img src="/img/depend-node3-en.png" width="80%" />
+ </p>
+<h4>7.4 Stored procedure node</h4>
+<ul>
+<li>According to the selected data source, execute the stored procedure.
+<blockquote>
+<p>Drag in the toolbar<img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PROCEDURE.png";
alt="PNG">The task node to the drawing board, as shown in the following
figure:</p>
+</blockquote>
+</li>
+</ul>
+<p align="center">
+ <img src="/img/procedure-en.png" width="80%" />
+ </p>
+<ul>
+<li>Data source: The data source type of the stored procedure supports MySQL
and POSTGRESQL, select the corresponding data source</li>
+<li>Method: is the method name of the stored procedure</li>
+<li>Custom parameters: The custom parameter types of the stored procedure
support IN and OUT, and the data types support nine data types: VARCHAR,
INTEGER, LONG, FLOAT, DOUBLE, DATE, TIME, TIMESTAMP, and BOOLEAN</li>
+</ul>
+<h4>7.5 SQL node</h4>
+<ul>
+<li>Drag in the toolbar<img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SQL.png";
alt="PNG">Task node into the drawing board</li>
+<li>Non-query SQL function: edit non-query SQL task information, select
non-query for sql type, as shown in the figure below:</li>
+</ul>
+ <p align="center">
+ <img src="/img/sql-en.png" width="80%" />
+</p>
+<ul>
+<li>Query SQL function: Edit and query SQL task information, sql type
selection query, select form or attachment to send mail to the specified
recipient, as shown in the figure below.</li>
+</ul>
+<p align="center">
+ <img src="/img/sql-node-en.png" width="80%" />
+ </p>
+<ul>
+<li>Data source: select the corresponding data source</li>
+<li>sql type: supports query and non-query. The query is a select type query,
which is returned with a result set. You can specify three templates for email
notification as form, attachment or form attachment. Non-queries are returned
without a result set, and are for three types of operations: update, delete,
and insert.</li>
+<li>sql parameter: the input parameter format is
key1=value1;key2=value2...</li>
+<li>sql statement: SQL statement</li>
+<li>UDF function: For data sources of type HIVE, you can refer to UDF
functions created in the resource center. UDF functions are not supported for
other types of data sources.</li>
+<li>Custom parameters: SQL task type, and stored procedure is a custom
parameter order to set values for the method. The custom parameter type and
data type are the same as the stored procedure task type. The difference is
that the SQL task type custom parameter will replace the ${variable} in the SQL
statement.</li>
+<li>Pre-sql: Pre-sql is executed before the sql statement.</li>
+<li>Post-sql: Post-sql is executed after the sql statement.</li>
+</ul>
+<h4>7.6 SPARK node</h4>
+<ul>
+<li>Through the SPARK node, you can directly execute the SPARK program. For
the spark node, the worker will use the <code>spark-submit</code> method to
submit tasks</li>
+</ul>
+<blockquote>
+<p>Drag in the toolbar<img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SPARK.png";
alt="PNG">The task node to the drawing board, as shown in the following
figure:</p>
+</blockquote>
+<p align="center">
+ <img src="/img/spark-submit-en.png" width="80%" />
+ </p>
+<ul>
+<li>Program type: supports JAVA, Scala and Python three languages</li>
+<li>The class of the main function: is the full path of the Spark program’s
entry Main Class</li>
+<li>Main jar package: Spark jar package</li>
+<li>Deployment mode: support three modes of yarn-cluster, yarn-client and
local</li>
+<li>Driver core number: You can set the number of Driver cores and the number
of memory</li>
+<li>Number of Executors: You can set the number of Executors, the number of
Executor memory, and the number of Executor cores</li>
+<li>Command line parameters: Set the input parameters of the Spark program and
support the substitution of custom parameter variables.</li>
+<li>Other parameters: support --jars, --files, --archives, --conf format</li>
+<li>Resource: If the resource file is referenced in other parameters, you need
to select and specify in the resource</li>
+<li>User-defined parameter: It is a user-defined parameter of the MR part,
which will replace the content with ${variable} in the script</li>
+</ul>
+<p>Note: JAVA and Scala are only used for identification, there is no
difference, if it is Spark developed by Python, there is no main function
class, and the others are the same</p>
+<h4>7.7 MapReduce(MR) node</h4>
+<ul>
+<li>Using the MR node, you can directly execute the MR program. For the mr
node, the worker will use the <code>hadoop jar</code> method to submit
tasks</li>
+</ul>
+<blockquote>
+<p>Drag the <img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_MR.png";
alt="PNG"> task node in the toolbar to the drawing board, as shown in the
following figure:</p>
+</blockquote>
+<ol>
+<li>JAVA program</li>
+</ol>
+ <p align="center">
+ <img src="/img/mr_java_en.png" width="80%" />
+ </p>
+<ul>
+<li>The class of the main function: is the full path of the Main Class, the
entry point of the MR program</li>
+<li>Program type: select JAVA language</li>
+<li>Main jar package: is the MR jar package</li>
+<li>Command line parameters: set the input parameters of the MR program and
support the substitution of custom parameter variables</li>
+<li>Other parameters: support -D, -files, -libjars, -archives format</li>
+<li>Resource: If the resource file is referenced in other parameters, you need
to select and specify in the resource</li>
+<li>User-defined parameter: It is a user-defined parameter of the MR part,
which will replace the content with ${variable} in the script</li>
+</ul>
+<ol start="2">
+<li>Python program</li>
+</ol>
+<p align="center">
+ <img src="/img/mr_edit_en.png" width="80%" />
+ </p>
+<ul>
+<li>Program type: select Python language</li>
+<li>Main jar package: is the Python jar package for running MR</li>
+<li>Other parameters: support -D, -mapper, -reducer, -input -output format,
here you can set the input of user-defined parameters, such as:</li>
+<li>-mapper "<a href="http://mapper.py";>mapper.py</a> 1" -file <a
href="http://mapper.py";>mapper.py</a> -reducer <a
href="http://reducer.py";>reducer.py</a> -file <a
href="http://reducer.py";>reducer.py</a> –input /journey/words.txt -output
/journey/out/mr/${currentTimeMillis}</li>
+<li>The <a href="http://mapper.py";>mapper.py</a> 1 after -mapper is two
parameters, the first parameter is <a href="http://mapper.py";>mapper.py</a>,
and the second parameter is 1</li>
+<li>Resource: If the resource file is referenced in other parameters, you need
to select and specify in the resource</li>
+<li>User-defined parameter: It is a user-defined parameter of the MR part,
which will replace the content with ${variable} in the script</li>
+</ul>
+<h4>7.8 Python Node</h4>
+<ul>
+<li>Using python nodes, you can directly execute python scripts. For python
nodes, workers will use <code>python **</code> to submit tasks.</li>
+</ul>
+<blockquote>
+<p>Drag in the toolbar<img
src="https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PYTHON.png";
alt="PNG">The task node to the drawing board, as shown in the following
figure:</p>
+</blockquote>
+<p align="center">
+ <img src="/img/python-en.png" width="80%" />
+ </p>
+<ul>
+<li>Script: Python program developed by the user</li>
+<li>Resources: refers to the list of resource files that need to be called in
the script</li>
+<li>User-defined parameter: It is a local user-defined parameter of Python,
which will replace the content with ${variable} in the script</li>
+</ul>
+<h4>7.9 Flink Node</h4>
+<ul>
+<li>Drag in the toolbar<img src="/img/flink.png" width="35"/>The task node to
the drawing board, as shown in the following figure:</li>
+</ul>
+<p align="center">
+ <img src="/img/flink-en.png" width="80%" />
+</p>
+<ul>
+<li>Program type: supports JAVA, Scala and Python three languages</li>
+<li>The class of the main function: is the full path of the Main Class, the
entry point of the Flink program</li>
+<li>Main jar package: is the Flink jar package</li>
+<li>Deployment mode: support three modes of cluster and local</li>
+<li>Number of slots: You can set the number of slots</li>
+<li>Number of taskManage: You can set the number of taskManage</li>
+<li>JobManager memory number: You can set the jobManager memory number</li>
+<li>TaskManager memory number: You can set the taskManager memory number</li>
+<li>Command line parameters: Set the input parameters of the Spark program and
support the substitution of custom parameter variables.</li>
+<li>Other parameters: support --jars, --files, --archives, --conf format</li>
+<li>Resource: If the resource file is referenced in other parameters, you need
to select and specify in the resource</li>
+<li>Custom parameter: It is a local user-defined parameter of Flink, which
will replace the content with ${variable} in the script</li>
+</ul>
+<p>Note: JAVA and Scala are only used for identification, there is no
difference, if it is Flink developed by Python, there is no class of the main
function, the others are the same</p>
+<h4>7.10 http Node</h4>
+<ul>
+<li>Drag in the toolbar<img src="/img/http.png" width="35"/>The task node to
the drawing board, as shown in the following figure:</li>
+</ul>
+<p align="center">
+ <img src="/img/http-en.png" width="80%" />
+ </p>
+<ul>
+<li>Node name: The node name in a workflow definition is unique.</li>
+<li>Run flag: Identifies whether this node can be scheduled normally, if it
does not need to be executed, you can turn on the prohibition switch.</li>
+<li>Descriptive information: describe the function of the node.</li>
+<li>Task priority: When the number of worker threads is insufficient, they are
executed in order from high to low, and when the priority is the same, they are
executed according to the first-in first-out principle.</li>
+<li>Worker grouping: Tasks are assigned to the machines of the worker group to
execute. If Default is selected, a worker machine will be randomly selected for
execution.</li>
+<li>Number of failed retry attempts: The number of times the task failed to be
resubmitted. It supports drop-down and hand-filling.</li>
+<li>Failed retry interval: The time interval for resubmitting the task after a
failed task. It supports drop-down and hand-filling.</li>
+<li>Timeout alarm: Check the timeout alarm and timeout failure. When the task
exceeds the "timeout period", an alarm email will be sent and the
task execution will fail.</li>
+<li>Request address: http request URL.</li>
+<li>Request type: support GET, POSt, HEAD, PUT, DELETE.</li>
+<li>Request parameters: Support Parameter, Body, Headers.</li>
+<li>Verification conditions: support default response code, custom response
code, content included, content not included.</li>
+<li>Verification content: When the verification condition selects a custom
response code, the content contains, and the content does not contain, the
verification content is required.</li>
+<li>Custom parameter: It is a user-defined parameter of http part, which will
replace the content with ${variable} in the script.</li>
+</ul>
+<h4>7.11 DATAX Node</h4>
+<ul>
+<li>
+<p>Drag in the toolbar<img src="/img/datax.png" width="35"/>Task node into the
drawing board</p>
+<p align="center">
+ <img src="/img/datax-en.png" width="80%" />
+</p>
+</li>
+<li>
+<p>Custom template: When you turn on the custom template switch, you can
customize the content of the json configuration file of the datax node
(applicable when the control configuration does not meet the requirements)</p>
+</li>
+<li>
+<p>Data source: select the data source to extract the data</p>
+</li>
+<li>
+<p>sql statement: the sql statement used to extract data from the target
database, the sql query column name is automatically parsed when the node is
executed, and mapped to the target table synchronization column name. When the
source table and target table column names are inconsistent, they can be
converted by column alias (as)</p>
+</li>
+<li>
+<p>Target library: select the target library for data synchronization</p>
+</li>
+<li>
+<p>Target table: the name of the target table for data synchronization</p>
+</li>
+<li>
+<p>Pre-sql: Pre-sql is executed before the sql statement (executed by the
target library).</p>
+</li>
+<li>
+<p>Post-sql: Post-sql is executed after the sql statement (executed by the
target library).</p>
+</li>
+<li>
+<p>json: json configuration file for datax synchronization</p>
+</li>
+<li>
+<p>Custom parameters: SQL task type, and stored procedure is a custom
parameter order to set values for the method. The custom parameter type and
data type are the same as the stored procedure task type. The difference is
that the SQL task type custom parameter will replace the ${variable} in the SQL
statement.</p>
+</li>
+</ul>
+<h4>8. parameter</h4>
+<h4>8.1 System parameters</h4>
+<table>
+ <tr><th>variable</th><th>meaning</th></tr>
+ <tr>
+ <td>${system.biz.date}</td>
+ <td>The day before the scheduled time of the daily scheduling
instance, the format is yyyyMMdd, when the data is supplemented, the date is
+1</td>
+ </tr>
+ <tr>
+ <td>${system.biz.curdate}</td>
+ <td>The timing time of the daily scheduling instance, the format is
yyyyMMdd, when the data is supplemented, the date is +1</td>
+ </tr>
+ <tr>
+ <td>${system.datetime}</td>
+ <td>The timing time of the daily scheduling instance, the format is
yyyyMMddHHmmss, when the data is supplemented, the date is +1</td>
+ </tr>
+</table>
+<h4>8.2 Time custom parameters</h4>
+<ul>
+<li>
+<p>Support custom variable names in the code, declaration method: ${variable
name}. It can refer to "system parameters" or specify
"constants".</p>
+</li>
+<li>
+<p>We define this benchmark variable as $[...] format, $[yyyyMMddHHmmss] can
be decomposed and combined arbitrarily, such as: $[yyyyMMdd], $[HHmmss],
$[yyyy-MM-dd], etc.</p>
+</li>
+<li>
+<p>The following format can also be used:</p>
+<pre><code>* Next N years：$[add_months(yyyyMMdd,12*N)]
+* N years before：$[add_months(yyyyMMdd,-12*N)]
+* Next N months：$[add_months(yyyyMMdd,N)]
+* N months before：$[add_months(yyyyMMdd,-N)]
+* Next N weeks：$[yyyyMMdd+7*N]
+* First N weeks：$[yyyyMMdd-7*N]
+* Next N days：$[yyyyMMdd+N]
+* N days before：$[yyyyMMdd-N]
+* Next N hours：$[HHmmss+N/24]
+* First N hours：$[HHmmss-N/24]
+* Next N minutes：$[HHmmss+N/24/60]
+* First N minutes：$[HHmmss-N/24/60]
+</code></pre>
+</li>
+</ul>
+<h4>8.3 <span id=UserDefinedParameters>User-defined parameters</span></h4>
+<ul>
+<li>User-defined parameters are divided into global parameters and local
parameters. Global parameters are global parameters passed when saving workflow
definitions and workflow instances. Global parameters can be referenced in the
local parameters of any task node in the entire process.
+example：</li>
+</ul>
+<p align="center">
+ <img src="/img/local_parameter_en.png" width="80%" />
+ </p>
+<ul>
+<li>global_bizdate is a global parameter, which refers to a system
parameter.</li>
+</ul>
+<p align="center">
+ <img src="/img/global_parameter_en.png" width="80%" />
+ </p>
+<ul>
+<li>In the task, local_param_bizdate uses ${global_bizdate} to refer to global
parameters. For scripts, you can use ${local_param_bizdate} to refer to the
value of global variable global_bizdate, or directly set the value of
local_param_bizdate through JDBC.</li>
+</ul>
+</div></section><footer class="footer-container"><div class="footer-body"><img
src="/img/ds_gray.svg"/><div class="cols-container"><div class="col
col-12"><h3>Disclaimer</h3><p>Apache DolphinScheduler (incubating) is an effort
undergoing incubation at The Apache Software Foundation (ASF), sponsored by
Incubator.
+Incubation is required of all newly accepted projects until a further review
indicates
+that the infrastructure, communications, and decision making process have
stabilized in a manner consistent with other successful ASF projects.
+While incubation status is not necessarily a reflection of the completeness or
stability of the code,
+it does indicate that the project has yet to be fully endorsed by the
ASF.</p></div><div class="col col-6"><dl><dt>Documentation</dt><dd><a
href="/en-us/docs/development/architecture-design.html"
target="_self">Overview</a></dd><dd><a
href="/en-us/docs/1.2.0/user_doc/quick-start.html" target="_self">Quick
start</a></dd><dd><a href="/en-us/docs/development/backend-development.html"
target="_self">Developer guide</a></dd></dl></div><div class="col
col-6"><dl><dt>ASF</dt><dd><a href="http:/ [...]
+ <script
src="https://f.alicdn.com/react/15.4.1/react-with-addons.min.js";></script>
+ <script
src="https://f.alicdn.com/react/15.4.1/react-dom.min.js";></script>
+ <script>
+ window.rootPath = '';
+ </script>
+ <script src="/build/documentation.js"></script>
+</body>
+</html>
\ No newline at end of file
diff --git a/en-us/docs/1.3.2/user_doc/system-manual.json
b/en-us/docs/1.3.2/user_doc/system-manual.json
new file mode 100644
index 0000000..1687db9
--- /dev/null
+++ b/en-us/docs/1.3.2/user_doc/system-manual.json
@@ -0,0 +1,6 @@
+{
+ "filename": "system-manual.md",
+ "__html": "<h1>System User Manual</h1>\n<h2>Get started
quickly</h2>\n<blockquote>\n<p>Please refer to <a
href=\"quick-start.html\">Quick Start</a></p>\n</blockquote>\n<h2>Operation
guide</h2>\n<h3>1. Home</h3>\n<p>The home page contains task status statistics,
process status statistics, and workflow definition statistics for all projects
of the user.</p>\n<p align=\"center\">\n<img src=\"/img/home_en.png\"
width=\"80%\" />\n</p>\n<h3>2. Project management</h3>\n<h4>2.1 Create project<
[...]
+ "link": "/en-us/docs/1.3.2/user_doc/system-manual.html",
+ "meta": {}
+}
\ No newline at end of file
diff --git a/img/complement_en1.png b/img/complement_en1.png
new file mode 100644
index 0000000..8d706aa
Binary files /dev/null and b/img/complement_en1.png differ
diff --git a/img/create_project_en1.png b/img/create_project_en1.png
new file mode 100644
index 0000000..29df496
Binary files /dev/null and b/img/create_project_en1.png differ
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SUB_PROCESS.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SUB_PROCESS.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_DEPENDENT.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_DEPENDENT.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PROCEDURE.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PROCEDURE.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SQL.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SQL.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SPARK.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_SPARK.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_MR.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_MR.png"){kind=link}
![https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PYTHON.png"](https://analysys.github.io/easyscheduler_docs_cn/images/toolbar_PYTHON.png"){kind=link}