This is an automated email from the ASF dual-hosted git repository.
xiaoyekanren pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iotdb-docs.git
The following commit(s) were added to refs/heads/main by this push:
new 6bd6d2fd add resource configuration recommendations in table ainode
deployment (#1141)
6bd6d2fd is described below
commit 6bd6d2fd754db832ba86257652f0498b71bae4c0
Author: leto-b <[email protected]>
AuthorDate: Thu Jun 4 11:39:21 2026 +0800
add resource configuration recommendations in table ainode deployment
(#1141)
---
src/.vuepress/sidebar/V2.0.x/en-Table.ts | 2 +-
src/.vuepress/sidebar_timecho/V2.0.x/en-Table.ts | 2 +-
.../AINode_Deployment_Upgrade_timecho.md | 25 ++-
.../Database-Resources.md | 204 +--------------------
.../Database-Resources_apache.md} | 0
...-Resources.md => Database-Resources_timecho.md} | 1 +
.../Master/Table/QuickStart/QuickStart_apache.md | 2 +-
.../Master/Table/QuickStart/QuickStart_timecho.md | 2 +-
.../AINode_Deployment_Upgrade_timecho.md | 23 +++
.../Database-Resources.md | 203 +-------------------
...e-Resources.md => Database-Resources_apache.md} | 0
.../Database-Resources_timecho.md} | 1 +
.../latest-Table/QuickStart/QuickStart_apache.md | 2 +-
.../latest-Table/QuickStart/QuickStart_timecho.md | 2 +-
.../AINode_Deployment_Upgrade_timecho.md | 28 ++-
.../Database-Resources_timecho.md | 2 +
.../AINode_Deployment_Upgrade_timecho.md | 26 +++
.../Database-Resources_timecho.md | 2 +
18 files changed, 118 insertions(+), 409 deletions(-)
diff --git a/src/.vuepress/sidebar/V2.0.x/en-Table.ts
b/src/.vuepress/sidebar/V2.0.x/en-Table.ts
index 73d3d5fa..6fd4bc92 100644
--- a/src/.vuepress/sidebar/V2.0.x/en-Table.ts
+++ b/src/.vuepress/sidebar/V2.0.x/en-Table.ts
@@ -58,7 +58,7 @@ export const enSidebar = {
children: [
{ text: 'Deployment form', link: 'Deployment-form_apache' },
{ text: 'Obtain IoTDB', link: 'IoTDB-Package_apache' },
- { text: 'Database Resources', link: 'Database-Resources' },
+ { text: 'Database Resources', link: 'Database-Resources_apache'
},
{ text: 'Environment Requirements', link:
'Environment-Requirements' },
],
},
diff --git a/src/.vuepress/sidebar_timecho/V2.0.x/en-Table.ts
b/src/.vuepress/sidebar_timecho/V2.0.x/en-Table.ts
index 0d231ac4..66576be0 100644
--- a/src/.vuepress/sidebar_timecho/V2.0.x/en-Table.ts
+++ b/src/.vuepress/sidebar_timecho/V2.0.x/en-Table.ts
@@ -58,7 +58,7 @@ export const enSidebar = {
children: [
{ text: 'Deployment form', link: 'Deployment-form_timecho' },
{ text: 'Obtain TimechoDB', link: 'IoTDB-Package_timecho' },
- { text: 'Database Resources', link: 'Database-Resources' },
+ { text: 'Database Resources', link: 'Database-Resources_timecho'
},
{ text: 'Environment Requirements', link:
'Environment-Requirements' },
],
},
diff --git
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
index a5afb8ab..31a27cfb 100644
---
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
+++
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
@@ -87,7 +87,30 @@ sha512sum timechodb-2.0.6.1-ainode-bin.zip
### 2.3 Environment Requirements
- Recommended operating environment: Linux, macOS.
-- TimechoDB Version: >= V2.0.8-beta.
+- TimechoDB Version: >= V2.0.8.
+
+#### 2.3.1 Resource Configuration Recommendations
+
+> Note: The resource configuration recommendations in this section apply only
to **model inference tasks**. Guidelines for model training tasks will be
provided in subsequent releases.
+
+The following are baseline resource configurations for model inference running
on a single NVIDIA RTX 4090 (24 GB VRAM). For model inference on AINode,
overall throughput can be improved by horizontally scaling the number of GPUs.
It is generally recommended to deploy servers with 1, 2, 4 or 8 GPUs.
+
+Specifications of inference tasks used in benchmark tests:
+- **Univariate inference**: Historical sequence length: 2880, prediction
length: 720
+- **Covariate inference**: Historical sequence length: 2880, prediction
length: 720, with 20 known covariates
+
+| Number of GPUs (NVIDIA 4090, 24 GB VRAM) | Recommended CPU Cores |
Recommended Memory (GB) | Supported QPS for Univariate Inference | Supported
QPS for Covariate Inference |
+|------------------------------------------|-----------------------|-------------------------|-----------------------------------------|---------------------------------------|
+| 1 GPU | 16 cores | 24 GB
| 100 | 10
|
+| 2 GPUs | 32 cores | 48 GB
| 200 | 20
|
+| 4 GPUs | 64 cores | 96 GB
| 400 | 40
|
+| 8 GPUs | 128 cores | 192 GB
| 800 | 80
|
+
+**Notes**:
+- The CPU and memory configurations above follow this general rule: allocate
16 CPU cores per GPU, and set system memory equal to GPU VRAM at a ratio of 1:1.
+- The throughput figures are benchmark references. Actual performance may vary
depending on model type, data complexity and deployment environment.
+- The throughput of univariate and covariate inference shall be evaluated
separately as required, and the two values cannot be summed directly.
+
## 3. Installation, Deployment, and Usage
diff --git
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
index 557d61ed..81e812ac 100644
---
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
+++
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
@@ -1,3 +1,6 @@
+---
+redirectTo: Database-Resources_apache.html
+---
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -18,204 +21,3 @@
under the License.
-->
-# Database Resources
-## 1. CPU
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th rowspan="2">Number of timeseries (frequency<=1HZ)</th>
- <th rowspan="2">CPU</th>
- <th colspan="3">Number of nodes</th>
- </tr>
- <tr>
- <th>standalone</th>
- <th>Dual-Active</th>
- <th>Distributed</th>
- </tr>
- <tr>
- <td>Within 100000</td>
- <td>2-4 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 300000</td>
- <td>4-8 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 500000</td>
- <td>8-16 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 1000000</td>
- <td>16-32 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 2000000</td>
- <td>32-48 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 10000000</td>
- <td>48core</td>
- <td>1</td>
- <td>2</td>
- <td>Please contact Timecho Business for consultation</td>
- </tr>
- <tr>
- <td>Over 10000000</td>
- <td colspan="4">Please contact Timecho Business for
consultation</td>
- </tr>
-</tbody>
-</table>
-
-> Supported CPU models: Kunpeng, Phytium, Sunway, Hygon, Zhaoxin, Loongson
-
-## 2. Memory
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th rowspan="2">Number of timeseries (frequency<=1HZ)</th>
- <th rowspan="2">Memory</th>
- <th colspan="3">Number of nodes</th>
- </tr>
- <tr>
- <th>standalone</th>
- <th>Dual-Active</th>
- <th>Distributed</th>
- </tr>
- <tr>
- <td>Within 100000</td>
- <td>2-4G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 300000</td>
- <td>6-12G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 500000</td>
- <td>12-24G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 1000000</td>
- <td>24-48G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 2000000</td>
- <td>48-96G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 10000000</td>
- <td>128G</td>
- <td>1</td>
- <td>2</td>
- <td>Please contact Timecho Business for consultation</td>
- </tr>
- <tr>
- <td>Over 10000000</td>
- <td colspan="4">Please contact Timecho Business for
consultation</td>
- </tr>
-</tbody>
-</table>
-
-> Flexible memory configuration options are provided. Users can adjust them in
the datanode-env file. For details and configuration guidelines, please refer
to [datanode-env](../Reference/System-Config-Manual.md#_3-2-datanode-env-sh-bat)
-
-
-## 3. Storage (Disk)
-### 3.1 Storage space
-Calculation Formula:
-
-```Plain
-Storage Space = Number of Measurement Points * Sampling Frequency (Hz) * Size
of Each Data Point (Bytes, see the table below) * Storage Duration *
Replication Factor / Compression Ratio
-```
-
-Data Point Size Calculation Table:
-
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th>Data Type</th>
- <th>Timestamp (Bytes)</th>
- <th> Value (Bytes)</th>
- <th> Total Data Point Size (Bytes)
- </th>
- </tr>
- <tr>
- <td>Boolean</td>
- <td>8</td>
- <td>1</td>
- <td>9</td>
- </tr>
- <tr>
- <td> INT32 / FLOAT (Single Precision)</td>
- <td>8</td>
- <td>4</td>
- <td>12</td>
- </tr>
- <tr>
- <td>INT64 / DOUBLE (Double Precision)</td>
- <td>8</td>
- <td>8</td>
- <td>16</td>
- </tr>
- <tr>
- <td>TEXT (String)</td>
- <td>8</td>
- <td>Average = a</td>
- <td>8+a</td>
- </tr>
-</tbody>
-</table>
-Example:
-
-- Scenario: 1,000 devices, 100 measurement points per device, i.e. 100,000
sequences in total. Data type is INT32. Sampling frequency is 1Hz (once per
second). Storage duration is 1 year. Replication factor is 3.
-- Full Calculation:
- ```Plain
- 1,000 devices * 100 measurement points * 12 bytes per data point * 86,400
seconds per day * 365 days per year * 3 replicas / 10 compression ratio = 11 TB
- ```
-- Simplified Calculation:
- ```Plain
- 1,000 * 100 * 12 * 86,400 * 365 * 3 / 10 = 11 TB
- ```
-### 3.2 Storage Configuration
-
-- For systems with > 10 million measurement points or high query loads, SSD is
recommended.
-
-## 4. Network (NIC)
-When the write throughput does not exceed 10 million points per second, a
gigabit network card is required. When the write throughput exceeds 10 million
points per second, a 10-gigabit network card is required.
-
-| **Write** **Throughput** **(Data Points/Second)** | **NIC** **Speed** |
-| ------------------------------------------------- | -------------------- |
-| < 10 million | 1 Gbps (Gigabit) |
-| ≥ 10 million | 10 Gbps (10 Gigabit) |
-
-## 5. Additional Notes
-
-- IoTDB supports second-level cluster scaling . Data migration is not required
when adding new nodes, so there is no need to worry about limited cluster
capacity based on current data estimates. You can add new nodes to the cluster
when scaling is needed in the future.
\ No newline at end of file
diff --git
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_apache.md
similarity index 100%
copy from
src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
copy to
src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_apache.md
diff --git
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
similarity index 95%
copy from
src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
copy to
src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
index 557d61ed..bb15f8a3 100644
---
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
+++
b/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
@@ -147,6 +147,7 @@
> Flexible memory configuration options are provided. Users can adjust them in
> the datanode-env file. For details and configuration guidelines, please
> refer to
> [datanode-env](../Reference/System-Config-Manual.md#_3-2-datanode-env-sh-bat)
+**Note**: For dedicated hardware allocation and throughput references for AI
model inference scenarios, refer to Section **[2.3.1 Resource Configuration
Recommendations](../Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md#_2-3-1-resource-configuration-recommendations)**
in the AINode deployment documentation.
## 3. Storage (Disk)
### 3.1 Storage space
diff --git a/src/UserGuide/Master/Table/QuickStart/QuickStart_apache.md
b/src/UserGuide/Master/Table/QuickStart/QuickStart_apache.md
index fa5d0364..1fbf7213 100644
--- a/src/UserGuide/Master/Table/QuickStart/QuickStart_apache.md
+++ b/src/UserGuide/Master/Table/QuickStart/QuickStart_apache.md
@@ -27,7 +27,7 @@ This document will guide you through methods to get started
quickly with IoTDB.
This guide will assist you in quickly installing and deploying IoTDB. You can
quickly navigate to the content you need to review through the following
document links:
-1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources.md)
+1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources_apache.md)
2. Complete system configuration preparations: IoTDB's system configuration
involves multiple aspects. For an introduction to key system configurations,
please see [System
Requirements](../Deployment-and-Maintenance/Environment-Requirements.md)
diff --git a/src/UserGuide/Master/Table/QuickStart/QuickStart_timecho.md
b/src/UserGuide/Master/Table/QuickStart/QuickStart_timecho.md
index 6bbd2c07..918214f3 100644
--- a/src/UserGuide/Master/Table/QuickStart/QuickStart_timecho.md
+++ b/src/UserGuide/Master/Table/QuickStart/QuickStart_timecho.md
@@ -27,7 +27,7 @@ This document will guide you through methods to get started
quickly with IoTDB.
This guide will assist you in quickly installing and deploying IoTDB. You can
quickly navigate to the content you need to review through the following
document links:
-1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources.md)
+1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources_timecho.md)
2. Complete system configuration preparations: IoTDB's system configuration
involves multiple aspects. For an introduction to key system configurations,
please see [System
Requirements](../Deployment-and-Maintenance/Environment-Requirements.md)
diff --git
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
index 1caa99ba..31a27cfb 100644
---
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
+++
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
@@ -89,6 +89,29 @@ sha512sum timechodb-2.0.6.1-ainode-bin.zip
- Recommended operating environment: Linux, macOS.
- TimechoDB Version: >= V2.0.8.
+#### 2.3.1 Resource Configuration Recommendations
+
+> Note: The resource configuration recommendations in this section apply only
to **model inference tasks**. Guidelines for model training tasks will be
provided in subsequent releases.
+
+The following are baseline resource configurations for model inference running
on a single NVIDIA RTX 4090 (24 GB VRAM). For model inference on AINode,
overall throughput can be improved by horizontally scaling the number of GPUs.
It is generally recommended to deploy servers with 1, 2, 4 or 8 GPUs.
+
+Specifications of inference tasks used in benchmark tests:
+- **Univariate inference**: Historical sequence length: 2880, prediction
length: 720
+- **Covariate inference**: Historical sequence length: 2880, prediction
length: 720, with 20 known covariates
+
+| Number of GPUs (NVIDIA 4090, 24 GB VRAM) | Recommended CPU Cores |
Recommended Memory (GB) | Supported QPS for Univariate Inference | Supported
QPS for Covariate Inference |
+|------------------------------------------|-----------------------|-------------------------|-----------------------------------------|---------------------------------------|
+| 1 GPU | 16 cores | 24 GB
| 100 | 10
|
+| 2 GPUs | 32 cores | 48 GB
| 200 | 20
|
+| 4 GPUs | 64 cores | 96 GB
| 400 | 40
|
+| 8 GPUs | 128 cores | 192 GB
| 800 | 80
|
+
+**Notes**:
+- The CPU and memory configurations above follow this general rule: allocate
16 CPU cores per GPU, and set system memory equal to GPU VRAM at a ratio of 1:1.
+- The throughput figures are benchmark references. Actual performance may vary
depending on model type, data complexity and deployment environment.
+- The throughput of univariate and covariate inference shall be evaluated
separately as required, and the two values cannot be summed directly.
+
+
## 3. Installation, Deployment, and Usage
### 3.1 Installing AINode
diff --git
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
index 8977215f..81e812ac 100644
---
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
+++
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
@@ -1,3 +1,6 @@
+---
+redirectTo: Database-Resources_apache.html
+---
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -18,203 +21,3 @@
under the License.
-->
-# Database Resources
-## 1. CPU
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th rowspan="2">Number of timeseries (frequency<=1HZ)</th>
- <th rowspan="2">CPU</th>
- <th colspan="3">Number of nodes</th>
- </tr>
- <tr>
- <th>standalone</th>
- <th>Dual-Active</th>
- <th>Distributed</th>
- </tr>
- <tr>
- <td>Within 100000</td>
- <td>2-4 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 300000</td>
- <td>4-8 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 500000</td>
- <td>8-16 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 1000000</td>
- <td>16-32 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 2000000</td>
- <td>32-48 cores</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 10000000</td>
- <td>48core</td>
- <td>1</td>
- <td>2</td>
- <td>Please contact Timecho Business for consultation</td>
- </tr>
- <tr>
- <td>Over 10000000</td>
- <td colspan="4">Please contact Timecho Business for
consultation</td>
- </tr>
-</tbody>
-</table>
-
-> Supported CPU models: Kunpeng, Phytium, Sunway, Hygon, Zhaoxin, Loongson
-
-## 2. Memory
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th rowspan="2">Number of timeseries (frequency<=1HZ)</th>
- <th rowspan="2">Memory</th>
- <th colspan="3">Number of nodes</th>
- </tr>
- <tr>
- <th>standalone</th>
- <th>Dual-Active</th>
- <th>Distributed</th>
- </tr>
- <tr>
- <td>Within 100000</td>
- <td>2-4G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 300000</td>
- <td>6-12G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 500000</td>
- <td>12-24G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 1000000</td>
- <td>24-48G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 2000000</td>
- <td>48-96G</td>
- <td>1</td>
- <td>2</td>
- <td>3</td>
- </tr>
- <tr>
- <td>Within 10000000</td>
- <td>128G</td>
- <td>1</td>
- <td>2</td>
- <td>Please contact Timecho Business for consultation</td>
- </tr>
- <tr>
- <td>Over 10000000</td>
- <td colspan="4">Please contact Timecho Business for
consultation</td>
- </tr>
-</tbody>
-</table>
-
-> Flexible memory configuration options are provided. Users can adjust them in
the datanode-env file. For details and configuration guidelines, please refer
to [datanode-env](../Reference/System-Config-Manual.md#_3-2-datanode-env-sh-bat)
-
-## 3. Storage (Disk)
-### 3.1 Storage space
-Calculation Formula:
-
-```Plain
-Storage Space = Number of Measurement Points * Sampling Frequency (Hz) * Size
of Each Data Point (Bytes, see the table below) * Storage Duration *
Replication Factor / Compression Ratio
-```
-
-Data Point Size Calculation Table:
-
-<table style="text-align: center;">
- <tbody>
- <tr>
- <th>Data Type</th>
- <th>Timestamp (Bytes)</th>
- <th> Value (Bytes)</th>
- <th> Total Data Point Size (Bytes)
- </th>
- </tr>
- <tr>
- <td>Boolean</td>
- <td>8</td>
- <td>1</td>
- <td>9</td>
- </tr>
- <tr>
- <td> INT32 / FLOAT (Single Precision)</td>
- <td>8</td>
- <td>4</td>
- <td>12</td>
- </tr>
- <tr>
- <td>INT64 / DOUBLE (Double Precision)</td>
- <td>8</td>
- <td>8</td>
- <td>16</td>
- </tr>
- <tr>
- <td>TEXT (String)</td>
- <td>8</td>
- <td>Average = a</td>
- <td>8+a</td>
- </tr>
-</tbody>
-</table>
-Example:
-
-- Scenario: 1,000 devices, 100 measurement points per device, i.e. 100,000
sequences in total. Data type is INT32. Sampling frequency is 1Hz (once per
second). Storage duration is 1 year. Replication factor is 3.
-- Full Calculation:
- ```Plain
- 1,000 devices * 100 measurement points * 12 bytes per data point * 86,400
seconds per day * 365 days per year * 3 replicas / 10 compression ratio = 11 TB
- ```
-- Simplified Calculation:
- ```Plain
- 1,000 * 100 * 12 * 86,400 * 365 * 3 / 10 = 11 TB
- ```
-### 3.2 Storage Configuration
-
-- For systems with > 10 million measurement points or high query loads, SSD is
recommended.
-
-## 4. Network (NIC)
-When the write throughput does not exceed 10 million points per second, a
gigabit network card is required. When the write throughput exceeds 10 million
points per second, a 10-gigabit network card is required.
-
-| **Write** **Throughput** **(Data Points/Second)** | **NIC** **Speed** |
-| ------------------------------------------------- | -------------------- |
-| < 10 million | 1 Gbps (Gigabit) |
-| ≥ 10 million | 10 Gbps (10 Gigabit) |
-
-## 5. Additional Notes
-
-- IoTDB supports second-level cluster scaling . Data migration is not required
when adding new nodes, so there is no need to worry about limited cluster
capacity based on current data estimates. You can add new nodes to the cluster
when scaling is needed in the future.
\ No newline at end of file
diff --git
a/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_apache.md
similarity index 100%
copy from
src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources.md
copy to
src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_apache.md
diff --git
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
similarity index 95%
copy from
src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
copy to
src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
index 557d61ed..bb15f8a3 100644
---
a/src/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources.md
+++
b/src/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
@@ -147,6 +147,7 @@
> Flexible memory configuration options are provided. Users can adjust them in
> the datanode-env file. For details and configuration guidelines, please
> refer to
> [datanode-env](../Reference/System-Config-Manual.md#_3-2-datanode-env-sh-bat)
+**Note**: For dedicated hardware allocation and throughput references for AI
model inference scenarios, refer to Section **[2.3.1 Resource Configuration
Recommendations](../Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md#_2-3-1-resource-configuration-recommendations)**
in the AINode deployment documentation.
## 3. Storage (Disk)
### 3.1 Storage space
diff --git a/src/UserGuide/latest-Table/QuickStart/QuickStart_apache.md
b/src/UserGuide/latest-Table/QuickStart/QuickStart_apache.md
index fa5d0364..1fbf7213 100644
--- a/src/UserGuide/latest-Table/QuickStart/QuickStart_apache.md
+++ b/src/UserGuide/latest-Table/QuickStart/QuickStart_apache.md
@@ -27,7 +27,7 @@ This document will guide you through methods to get started
quickly with IoTDB.
This guide will assist you in quickly installing and deploying IoTDB. You can
quickly navigate to the content you need to review through the following
document links:
-1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources.md)
+1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources_apache.md)
2. Complete system configuration preparations: IoTDB's system configuration
involves multiple aspects. For an introduction to key system configurations,
please see [System
Requirements](../Deployment-and-Maintenance/Environment-Requirements.md)
diff --git a/src/UserGuide/latest-Table/QuickStart/QuickStart_timecho.md
b/src/UserGuide/latest-Table/QuickStart/QuickStart_timecho.md
index 6bbd2c07..918214f3 100644
--- a/src/UserGuide/latest-Table/QuickStart/QuickStart_timecho.md
+++ b/src/UserGuide/latest-Table/QuickStart/QuickStart_timecho.md
@@ -27,7 +27,7 @@ This document will guide you through methods to get started
quickly with IoTDB.
This guide will assist you in quickly installing and deploying IoTDB. You can
quickly navigate to the content you need to review through the following
document links:
-1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources.md)
+1. Prepare the necessary machine resources: The deployment and operation of
IoTDB require consideration of various aspects of machine resource
configuration. For specific resource configurations, please refer to [Database
Resource](../Deployment-and-Maintenance/Database-Resources_timecho.md)
2. Complete system configuration preparations: IoTDB's system configuration
involves multiple aspects. For an introduction to key system configurations,
please see [System
Requirements](../Deployment-and-Maintenance/Environment-Requirements.md)
diff --git
a/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
b/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
index be000d67..7b865ecc 100644
---
a/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
+++
b/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
@@ -83,7 +83,33 @@ sha512sum timechodb-2.0.6.1-ainode-bin.zip
### 2.3 环境要求
* 建议操作环境: Linux, MacOS；
-* TimechoDB 版本：>= V 2.0.8-beta；
+* TimechoDB 版本：>= V 2.0.8；
+
+#### 2.3.1 资源配置建议
+
+> 说明：本节资源配置建议仅针对**模型推理任务**。模型训练任务的资源配置建议将在后续版本中补充。
+
+以下为基于单张 NVIDIA 4090（24 GB 显存）运行模型推理任务的资源配置基准线。AINode
中的模型推理任务支持通过横向扩展显卡数量来提升整体吞吐，通常建议按 1、2、4、8 张显卡四种规格配置机器。
+
+基准测试使用的推理任务规格如下：
+
+* **单变量推理**：历史序列长度 2880，预测长度 720；
+* **协变量推理**：历史序列长度 2880，预测长度 720，包含 20 个已知协变量。
+
+
+| GPU 数量（NVIDIA 4090, 24 GB 显存） | 推荐 CPU 核数 | 推荐内存（GB） | 可支持单变量推理吞吐（QPS） |
可支持协变量推理吞吐（QPS） |
+| ------------------------------------- | --------------- | ---------------- |
----------------------------- | ----------------------------- |
+| 1 卡 | 16 核 | 24 GB | 100
| 10 |
+| 2 卡 | 32 核 | 48 GB | 200
| 20 |
+| 4 卡 | 64 核 | 96 GB | 400
| 40 |
+| 8 卡 | 128 核 | 192 GB | 800
| 80 |
+
+**注意**：
+
+* 上表中的 CPU 和内存配置遵循以下通用原则：每张显卡配置 16 核 CPU，内存容量与显存容量按 1:1 比例配置
+* 以上吞吐数据为基准测试参考值，实际性能可能因模型类型、数据复杂度及部署环境差异而有所不同
+* 单变量与协变量推理任务的吞吐可按需独立评估，不可直接相加
+
## 3. 安装部署及使用
diff --git
a/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
b/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
index 4bf223c7..4da0bf72 100644
---
a/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
+++
b/src/zh/UserGuide/Master/Table/Deployment-and-Maintenance/Database-Resources_timecho.md
@@ -148,6 +148,8 @@
> 提供灵活的内存配置选项，用户可在datanode-env文件中进行调整，详细信息和配置指南请参见
> [datanode-env](../Reference/System-Config-Manual_timecho.md#_2-2-datanode-env-sh-bat)
+**注意：** 如需查看 AI 模型推理场景的专项硬件配比与吞吐参考，可查看 AINode 部署文档【[2.3.1
资源配置建议](../Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md#_2-3-1-资源配置建议)】章节：
+
## 3. 存储(磁盘)
### 3.1 存储空间
diff --git
a/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
b/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
index dfff7a9a..7b865ecc 100644
---
a/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
+++
b/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md
@@ -85,6 +85,32 @@ sha512sum timechodb-2.0.6.1-ainode-bin.zip
* 建议操作环境: Linux, MacOS；
* TimechoDB 版本：>= V 2.0.8；
+#### 2.3.1 资源配置建议
+
+> 说明：本节资源配置建议仅针对**模型推理任务**。模型训练任务的资源配置建议将在后续版本中补充。
+
+以下为基于单张 NVIDIA 4090（24 GB 显存）运行模型推理任务的资源配置基准线。AINode
中的模型推理任务支持通过横向扩展显卡数量来提升整体吞吐，通常建议按 1、2、4、8 张显卡四种规格配置机器。
+
+基准测试使用的推理任务规格如下：
+
+* **单变量推理**：历史序列长度 2880，预测长度 720；
+* **协变量推理**：历史序列长度 2880，预测长度 720，包含 20 个已知协变量。
+
+
+| GPU 数量（NVIDIA 4090, 24 GB 显存） | 推荐 CPU 核数 | 推荐内存（GB） | 可支持单变量推理吞吐（QPS） |
可支持协变量推理吞吐（QPS） |
+| ------------------------------------- | --------------- | ---------------- |
----------------------------- | ----------------------------- |
+| 1 卡 | 16 核 | 24 GB | 100
| 10 |
+| 2 卡 | 32 核 | 48 GB | 200
| 20 |
+| 4 卡 | 64 核 | 96 GB | 400
| 40 |
+| 8 卡 | 128 核 | 192 GB | 800
| 80 |
+
+**注意**：
+
+* 上表中的 CPU 和内存配置遵循以下通用原则：每张显卡配置 16 核 CPU，内存容量与显存容量按 1:1 比例配置
+* 以上吞吐数据为基准测试参考值，实际性能可能因模型类型、数据复杂度及部署环境差异而有所不同
+* 单变量与协变量推理任务的吞吐可按需独立评估，不可直接相加
+
+
## 3. 安装部署及使用
### 3.1 安装 AINode
diff --git
a/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
b/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
index 4bf223c7..4da0bf72 100644
---
a/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
+++
b/src/zh/UserGuide/latest-Table/Deployment-and-Maintenance/Database-Resources_timecho.md
@@ -148,6 +148,8 @@
> 提供灵活的内存配置选项，用户可在datanode-env文件中进行调整，详细信息和配置指南请参见
> [datanode-env](../Reference/System-Config-Manual_timecho.md#_2-2-datanode-env-sh-bat)
+**注意：** 如需查看 AI 模型推理场景的专项硬件配比与吞吐参考，可查看 AINode 部署文档【[2.3.1
资源配置建议](../Deployment-and-Maintenance/AINode_Deployment_Upgrade_timecho.md#_2-3-1-资源配置建议)】章节：
+
## 3. 存储(磁盘)
### 3.1 存储空间
