vpruthi/doc-exports
1
0
Fork 0
forked from docs/doc-exports
Code Pull Requests Activity
doc-exports/docs/modelarts/umn/inference-modelarts-0018.html
Lai, Weijian 4e4b2d5f6d ModelArts UMN 23.3.0 Version. 
Reviewed-by: Hasko, Vladimir <vladimir.hasko@t-systems.com>
Co-authored-by: Lai, Weijian <laiweijian4@huawei.com>
Co-committed-by: Lai, Weijian <laiweijian4@huawei.com>
2024-06-26 07:03:02 +00:00

149 lines
22 KiB
HTML
Raw Permalink Blame History

<a name="EN-US_TOPIC_0000001910014974"></a><a name="EN-US_TOPIC_0000001910014974"></a>
<h1 class="topictitle1">Deploying as a Real-Time Service</h1>
<div id="body0000001209920195"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1626935755620">After an AI application is prepared, you can deploy the AI application as a real-time service and predict and call the service.</p>
<div class="section" id="EN-US_TOPIC_0000001910014974__section8362102913197"><h4 class="sectiontitle">Constraints</h4><p id="EN-US_TOPIC_0000001910014974__p10275195051910">A maximum of 20 real-time services can be deployed by a user.</p>
</div>
<div class="section" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_section588716131207"><h4 class="sectiontitle">Prerequisites</h4><ul id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_ul153712018018"><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li1937182017010">Data has been prepared. Specifically, you have created an AI application in the <span class="parmname" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_parmname1783718913212"><b>Normal</b></span> state in ModelArts.</li></ul>
</div>
<div class="section" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_section1466310143398"><h4 class="sectiontitle">Note</h4><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1869121718392">Real-time services deployed using the public resource pool also occupy quota resources when the services are <span class="parmname" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_parmname10342124184018"><b>Abnormal</b></span> or <span class="parmname" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_parmname446312266400"><b>Stopped</b></span>. If the quota is insufficient and no more services can be deployed, delete some abnormal services to release resources.</p>
<p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p10214114818617">Quota calculation:</p>
<ul id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_ul93818276"><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li113858471">If a dedicated resource pool is used to deploy real-time services, the quota is not decreased. The quota is increased or decreased only when the dedicated pool is created, modified, or deleted.</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li15381484716">When a shared resource pool is used to deploy a real-time service, the quota will be increased or decreased when you create, change the number of, or delete instances.</li></ul>
<p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p6214144815617">Metering calculation:</p>
<ul id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_ul20899115270"><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li18990512712">If a real-time service is deployed using a dedicated pool, only the data of the dedicated pool to which the service belongs is metered.</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li18991351279">When a shared pool is used to deploy a real-time service, the specifications used by the service will be metered.</li></ul>
</div>
<div class="section" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_section210412592420"><h4 class="sectiontitle">Procedure</h4><ol id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_ol118835914516"><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li41881359556">Log in to the ModelArts management console. In the left navigation pane, choose <span class="uicontrol" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_uicontrol54328471294"><b>Service Deployment</b></span> &gt; <span class="uicontrol" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_uicontrol848345132711"><b>Real-Time Services</b></span>. By default, the system switches to the <span class="wintitle" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_wintitle243434712910"><b>Real-Time Services</b></span> page.</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li517243918618">In the real-time service list, click <span class="uicontrol" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_uicontrol685318711303"><b>Deploy</b></span> in the upper left corner. The <span class="wintitle" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_wintitle1585518712300"><b>Deploy</b></span> page is displayed.</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li105537178719">Set parameters for a real-time service.<ol type="a" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_ol156031301865"><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li45623018616">Set basic information about model deployment. For details about the parameters, see <a href="#EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table16373156155613">Table 1</a>.
<div class="tablenoborder"><a name="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table16373156155613"></a><a name="en-us_topic_0165025304_table16373156155613"></a><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table16373156155613" frame="border" border="1" rules="all"><caption><b>Table 1 </b>Basic parameters of model deployment</caption><thead align="left"><tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row137318605613"><th align="left" class="cellrowborder" valign="top" width="21.32%" id="mcps1.3.5.2.3.1.1.2.2.3.1.1"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1373565563">Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="78.68%" id="mcps1.3.5.2.3.1.1.2.2.3.1.2"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p8373116195619">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row29981091564"><td class="cellrowborder" valign="top" width="21.32%" headers="mcps1.3.5.2.3.1.1.2.2.3.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p179984912563">Name</p>
</td>
<td class="cellrowborder" valign="top" width="78.68%" headers="mcps1.3.5.2.3.1.1.2.2.3.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1099889125612">Name of the real-time service. Set this parameter as prompted.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row116005243566"><td class="cellrowborder" valign="top" width="21.32%" headers="mcps1.3.5.2.3.1.1.2.2.3.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p36004242567">Description</p>
</td>
<td class="cellrowborder" valign="top" width="78.68%" headers="mcps1.3.5.2.3.1.1.2.2.3.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p9600724195610">Brief description of the real-time service.</p>
</td>
</tr>
</tbody>
</table>
</div>
</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li31131228711">Enter key information including the resource pool and AI application configurations. For details, see <a href="#EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table10352134481117">Table 2</a>.
<div class="tablenoborder"><a name="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table10352134481117"></a><a name="en-us_topic_0165025304_table10352134481117"></a><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_table10352134481117" frame="border" border="1" rules="all"><caption><b>Table 2 </b>Parameters</caption><thead align="left"><tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row103535447116"><th align="left" class="cellrowborder" valign="top" width="12.93%" id="mcps1.3.5.2.3.1.2.2.2.4.1.1"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p193531244161110">Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="14.24%" id="mcps1.3.5.2.3.1.2.2.2.4.1.2"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p5242154917598">Sub-Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="72.83%" id="mcps1.3.5.2.3.1.2.2.2.4.1.3"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p4353204421116">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row93531344151114"><td class="cellrowborder" valign="top" width="12.93%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p14353114412113">Resource Pool</p>
</td>
<td class="cellrowborder" valign="top" width="14.24%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p640016175012">Public resource pools</p>
</td>
<td class="cellrowborder" valign="top" width="72.83%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.3 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p8899202810015">Instances in the public resource pool can be of the CPU or GPU type. </p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1310003117590"><td class="cellrowborder" valign="top" width="12.93%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1525720367245">Resource Pool</p>
</td>
<td class="cellrowborder" valign="top" width="14.24%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1724217492597">Dedicated resource pools</p>
</td>
<td class="cellrowborder" valign="top" width="72.83%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.3 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p4100731185918">Select a specification from the dedicated resource pool specifications.</p>
<div class="note" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_note114821751145512"><span class="notetitle"> NOTE: </span><div class="notebody"><ul id="EN-US_TOPIC_0000001910014974__ul34757229"><li id="EN-US_TOPIC_0000001910014974__li8671523111615">The data of old-version dedicated resource pools will be gradually migrated to the new-version dedicated resource pools.</li><li id="EN-US_TOPIC_0000001910014974__li158234284810">For new users and the existing users who have migrated data from old-version dedicated resource pools to new ones, there is only one entry to new-version dedicated resource pools on the ModelArts management console.</li><li id="EN-US_TOPIC_0000001910014974__li04105714218">For the existing users who have not migrated data from old-version dedicated resource pools to new ones, there are two entries to dedicated resource pools on the ModelArts management console, where the entry marked with <strong id="EN-US_TOPIC_0000001910014974__b64521392541">New</strong> is to the new version.</li></ul>
<p id="EN-US_TOPIC_0000001910014974__p433332618166">For more details about the new-version dedicated resource pools, see <a href="resmgmt-modelarts_0002.html">Comprehensive Upgrades to ModelArts Resource Pool Management Functions</a>.</p>
</div></div>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__row11558853123016"><td class="cellrowborder" valign="top" width="12.93%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__p1639657173112"><strong id="EN-US_TOPIC_0000001910014974__b9980172654518">Multi-Pool Load Balancing</strong></p>
</td>
<td class="cellrowborder" valign="top" width="14.24%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__p15396973317">N/A</p>
</td>
<td class="cellrowborder" valign="top" width="72.83%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.3 "><p id="EN-US_TOPIC_0000001910014974__p143968716311">After this function is enabled, the service will be deployed in two dedicated resource pools, and service traffic will be evenly distributed among the pools through a load balancer. This minimizes the impact on the service after one resource pool fails, improving service reliability.</p>
<p id="EN-US_TOPIC_0000001910014974__p11396473310">After this function is enabled, the number of compute nodes must be a multiple of 2 and the minimum value is <strong id="EN-US_TOPIC_0000001910014974__b1797014402516">2</strong>.</p>
<div class="note" id="EN-US_TOPIC_0000001910014974__note1639612753110"><span class="notetitle"> NOTE: </span><div class="notebody"><ul id="EN-US_TOPIC_0000001910014974__ul03971179317"><li id="EN-US_TOPIC_0000001910014974__li53971783116">Multi-pool load balancing is supported only when a dedicated resource pool is selected.</li><li id="EN-US_TOPIC_0000001910014974__li153978793112">Multi-pool load balancing requires that the compute nodes in the two resource pools have the same specifications.</li><li id="EN-US_TOPIC_0000001910014974__li18487124412272">Both resource pools must be old or new resource pools.</li></ul>
</div></div>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row117313244916"><td class="cellrowborder" rowspan="9" valign="top" width="12.93%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1100131175916">AI Application and Configuration</p>
</td>
<td class="cellrowborder" valign="top" width="14.24%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p817313216498">AI Application Source</p>
</td>
<td class="cellrowborder" valign="top" width="72.83%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.3 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p14173193214915">Select <span class="parmname" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_parmname189641821762"><b>My AI Applications</b></span> based on your requirements.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row17100731145918"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1227512689">AI Application and Version</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p327131211818">Select the AI application and version that are in the <span class="parmname" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_parmname3895151144618"><b>Normal</b></span> state.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1875153415599"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1127141220814">Traffic Ratio (%)</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1027312982">Set the traffic proportion of the current instance node. Service calling requests are allocated to the current version based on this proportion.</p>
<p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p102781211814">If you deploy only one version of an AI application, set this parameter to <strong id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_b1454317349562">100%</strong>. If you select multiple versions for gated launch, ensure that the sum of the traffic ratios of multiple versions is <strong id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_b7817620135415">100%</strong>.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1575133419597"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p38611655112416">Specifications</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p14669016181010">Select available specifications based on the list displayed on the console. The specifications in gray cannot be used in the current environment.</p>
<p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p1058423714296">If specifications in the public resource pools are unavailable, no public resource pool is available in the current environment. In this case, use a dedicated resource pool or contact the administrator to create a public resource pool.</p>
<div class="note" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_note451815813528"><span class="notetitle"> NOTE: </span><div class="notebody"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p12518680521">When the selected flavor is used to deploy the service, necessary system consumption is generated. Therefore, the resources actually occupied by the service are slightly greater than the selected flavor.</p>
</div></div>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row147516348594"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p18612556247">Compute Nodes</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p122820121820">Set the number of instances for the current AI application version. If you set <strong id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_b19381962339">Instances</strong> to <strong id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_b113823612338">1</strong>, the standalone computing mode is used. If you set <strong id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_b93836693320">Instances</strong> to a value greater than 1, the distributed computing mode is used. Select a computing mode based on the actual requirements.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1630173817596"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p7287121782">Environment Variable</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p3285129812">Set environment variables and inject them to the pod. To ensure data security, do not enter sensitive information in environment variables.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__row77413351538"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__p475123516316">Timeout</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__p7761535637">Timeout of a single model, including both the deployment and startup time. The default value is 20 minutes. The value must range from 3 to 120.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__row1784919374180"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__p684933741819"><strong id="EN-US_TOPIC_0000001910014974__b12700113314113">WebSocket</strong></p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__p6850183713187">Whether to deploy a real-time service as a WebSocket service.</p>
<div class="note" id="EN-US_TOPIC_0000001910014974__note17971216132312"><span class="notetitle"> NOTE: </span><div class="notebody"><ul id="EN-US_TOPIC_0000001910014974__ul9849204018252"><li id="EN-US_TOPIC_0000001910014974__li8849114072516">This function is supported only if the AI application is WebSocket-compliant and comes from a container image.</li><li id="EN-US_TOPIC_0000001910014974__li01311148182510">After this function is enabled, <strong id="EN-US_TOPIC_0000001910014974__b13918131132220">Traffic Limit</strong> and <strong id="EN-US_TOPIC_0000001910014974__b182521634152213">Data Collection</strong> cannot be set.</li><li id="EN-US_TOPIC_0000001910014974__li697813561719">This parameter cannot be changed after the service is deployed.</li></ul>
</div></div>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1430153875910"><td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p14286126814">Add AI Application Version and Configuration</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p13777312296">If the selected AI application has multiple versions, you can add multiple versions and configure a traffic ratio. You can use gray launch to smoothly upgrade the AI application version.</p>
<div class="note" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_note10281512989"><span class="notetitle"> NOTE: </span><div class="notebody"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p02815124812">Free compute specifications do not support the gray launch of multiple versions.</p>
</div></div>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_row1354314356338"><td class="cellrowborder" valign="top" width="12.93%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.1 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p19544193563312">Data Collection</p>
</td>
<td class="cellrowborder" valign="top" width="14.24%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.2 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p0544133553318">N/A</p>
</td>
<td class="cellrowborder" valign="top" width="72.83%" headers="mcps1.3.5.2.3.1.2.2.2.4.1.3 "><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p10544163553315">This function is disabled by default. When enabled, it collects and stores data generated when a real-time service is called based on configured rules.</p>
</td>
</tr>
</tbody>
</table>
</div>
</li></ol>
</li><li id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_li0335165819514">After confirming the entered information, complete service deployment as prompted. Generally, service deployment jobs run for a period of time, which may be several minutes or tens of minutes depending on the amount of your selected data and resources.<div class="note" id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_note26817055513"><img src="public_sys-resources/note_3.0-en-us.png"><span class="notetitle"> </span><div class="notebody"><p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p156918005513">After a real-time service is deployed, it is started immediately. </p>
</div></div>
<p id="EN-US_TOPIC_0000001910014974__en-us_topic_0165025304_p199943452522">In the real-time service list, after the status of the newly deployed service changes from <span class="parmname" id="EN-US_TOPIC_0000001910014974__parmname850811711179"><b>Deploying</b></span> to <span class="parmname" id="EN-US_TOPIC_0000001910014974__parmname75081817141719"><b>Running</b></span>, the service is deployed successfully.</p>
</li></ol>
</div>
</div>
<div>
<div class="familylinks">
<div class="parentlink"><strong>Parent topic:</strong> <a href="inference-modelarts-0016.html">Deploying AI Applications as Real-Time Services</a></div>
</div>
</div>
View Git Blame Copy Permalink