benoit/iDRAC_fan_controller
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Benoit
2024-08-01 13:43:29 +02:00
commit ebf756a35a
11 changed files with 916 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
.devcontainer/devcontainer.json Normal file
View File

@@ -0,0 +1,29 @@
// For format details, see https://aka.ms/devcontainer.json. For config options, see the
// README at: https://github.com/devcontainers/templates/tree/main/src/docker-existing-dockerfile
{
"name": "Existing Dockerfile",
"image": "mcr.microsoft.com/devcontainers/universal",
"customizations": {
"vscode": {
"extensions": [
"mhutchie.git-graph",
"ms-azuretools.vscode-docker"
]
}
}
// Features to add to the dev container. More info: https://containers.dev/features.
// "features": {},
// Use 'forwardPorts' to make a list of ports inside the container available locally.
// "forwardPorts": [],
// Uncomment the next line to run commands after the container is created.
// "postCreateCommand": "cat /etc/os-release",
// Configure tool-specific properties.
// "customizations": {},
// Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
// "remoteUser": "devcontainer"
}

3
.dockerignore Normal file
View File

@@ -0,0 +1,3 @@
.github
.devcontainer
README.md

12
.github/dependabot.yml vendored Normal file
View File

@@ -0,0 +1,12 @@
# To get started with Dependabot version updates, you'll need to specify which
# package ecosystems to update and where the package manifests are located.
# Please see the documentation for more information:
# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
# https://containers.dev/guide/dependabot
version: 2
updates:
- package-ecosystem: "devcontainers"
directory: "/"
schedule:
interval: weekly

61
.github/workflows/build_and_publish_docker_image.yml vendored Normal file
View File

@@ -0,0 +1,61 @@
name: Docker image CI
on:
push:
branches: [ master ]
paths-ignore:
- '**/README.md'
jobs:
build:
name: Build and publish Docker image to Docker Hub and GitHub Containers Repository
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Remove "_Docker" suffix from GitHub repository name to use it as image name
uses: mad9000/actions-find-and-replace-string@3
id: docker_image_name
with:
source: ${{ github.repository }}
find: '_Docker'
replace: ''
- name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: |
${{ steps.docker_image_name.outputs.value }}
ghcr.io/${{ steps.docker_image_name.outputs.value }}
tags: type=raw,value=latest
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Build and publish Docker image
uses: docker/build-push-action@v4
with:
context: .
platforms: linux/amd64,linux/arm64
file: ./Dockerfile
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}

175
Dell_iDRAC_fan_controller.sh Normal file
View File

@@ -0,0 +1,175 @@
#!/bin/bash
# Enable strict bash mode to stop the script if an uninitialized variable is used, if a command fails, or if a command with a pipe fails
# Not working in some setups : https://github.com/tigerblue77/Dell_iDRAC_fan_controller/issues/48
# set -euo pipefail
source functions.sh
# Trap the signals for container exit and run gracefull_exit function
trap 'gracefull_exit' SIGQUIT SIGKILL SIGTERM
# Prepare, format and define initial variables
# readonly DELL_FRESH_AIR_COMPLIANCE=45
# Define the temperature thresholds and corresponding fan speeds
TEMP_THRESHOLDS=(35 45 55 70)
FAN_SPEEDS=(13 20 40 60 100) # Correspond aux seuils + vitesse max
# Check if the iDRAC host is set to 'local' or not then set the IDRAC_LOGIN_STRING accordingly
if [[ $IDRAC_HOST == "local" ]]
then
# Check that the Docker host IPMI device (the iDRAC) has been exposed to the Docker container
if [ ! -e "/dev/ipmi0" ] && [ ! -e "/dev/ipmi/0" ] && [ ! -e "/dev/ipmidev/0" ]; then
echo "/!\ Could not open device at /dev/ipmi0 or /dev/ipmi/0 or /dev/ipmidev/0, check that you added the device to your Docker container or stop using local mode. Exiting." >&2
exit 1
fi
IDRAC_LOGIN_STRING='open'
else
echo "iDRAC/IPMI username: $IDRAC_USERNAME"
echo "iDRAC/IPMI password: $IDRAC_PASSWORD"
IDRAC_LOGIN_STRING="lanplus -H $IDRAC_HOST -U $IDRAC_USERNAME -P $IDRAC_PASSWORD"
fi
get_Dell_server_model
if [[ ! $SERVER_MANUFACTURER == "DELL" ]]
then
echo "/!\ Your server isn't a Dell product. Exiting." >&2
exit 1
fi
# Log main informations
echo "Server model: $SERVER_MANUFACTURER $SERVER_MODEL"
echo "iDRAC/IPMI host: $IDRAC_HOST"
# Log the check interval
echo "Check interval: ${CHECK_INTERVAL}s"
echo ""
# Define the interval for printing
readonly TABLE_HEADER_PRINT_INTERVAL=10
i=$TABLE_HEADER_PRINT_INTERVAL
# Set the flag used to check if the active fan control profile has changed
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# Check present sensors
IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=true
IS_CPU2_TEMPERATURE_SENSOR_PRESENT=true
retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
if [ -z "$EXHAUST_TEMPERATURE" ]
then
echo "No exhaust temperature sensor detected."
IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=false
fi
if [ -z "$CPU2_TEMPERATURE" ]
then
echo "No CPU2 temperature sensor detected."
IS_CPU2_TEMPERATURE_SENSOR_PRESENT=false
fi
# Output new line to beautify output if one of the previous conditions have echoed
if ! $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT || ! $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
echo ""
fi
# Fonction pour régler la vitesse des ventilateurs
#set_fan_speed() {
# local speed=$1
# # Commande pour définir la vitesse des ventilateurs via l'iDRAC
# # Par exemple: ipmitool raw command
# ipmitool -I lanplus -H ${IDRAC_HOST} -U ${IDRAC_USERNAME} -P ${IDRAC_PASSWORD} raw 0x30 0x30 0x02 0xff ${speed}
#}
# Start monitoring
while true; do
# Sleep for the specified interval before taking another reading
sleep $CHECK_INTERVAL &
SLEEP_PROCESS_PID=$!
retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
# Define functions to check if CPU 1 and CPU 2 temperatures are above the threshold
function CPU1_OVERHEAT () { [ $CPU1_TEMPERATURE -gt $CPU_TEMPERATURE_THRESHOLD ]; }
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
function CPU2_OVERHEAT () { [ $CPU2_TEMPERATURE -gt $CPU_TEMPERATURE_THRESHOLD ]; }
fi
# Initialize a variable to store the comments displayed when the fan control profile changed
COMMENT=" -"
# Check if CPU 1 is overheating then apply Dell default dynamic fan control profile if true
if CPU1_OVERHEAT
then
apply_Dell_fan_control_profile
if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# If CPU 2 temperature sensor is present, check if it is overheating too.
# Do not apply Dell default dynamic fan control profile as it has already been applied before
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT && CPU2_OVERHEAT
then
COMMENT="CPU 1 and CPU 2 temperatures are too high, Dell default dynamic fan control profile applied for safety"
else
COMMENT="CPU 1 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi
fi
# If CPU 2 temperature sensor is present, check if it is overheating then apply Dell default dynamic fan control profile if true
elif $IS_CPU2_TEMPERATURE_SENSOR_PRESENT && CPU2_OVERHEAT
then
apply_Dell_fan_control_profile
if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
COMMENT="CPU 2 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi
else
# Adjust fan speed based on temperature thresholds
for i in ${!TEMP_THRESHOLDS[@]}; do
if [ $CPU1_TEMPERATURE -le ${TEMP_THRESHOLDS[$i]} ]; then
set_fan_speed ${FAN_SPEEDS[$i]}
break
fi
done
# Si la température est supérieure à tous les seuils, définir la vitesse maximale
if [ $CPU1_TEMPERATURE -gt ${TEMP_THRESHOLDS[-1]} ]; then
set_fan_speed ${FAN_SPEEDS[-1]}
fi
# apply_user_fan_control_profile
# Check if user fan control profile is applied then apply it if not
if $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=false
COMMENT="CPU temperature decreased and is now OK (<= $CPU_TEMPERATURE_THRESHOLD°C), user's fan control profile applied."
fi
fi
# Enable or disable, depending on the user's choice, third-party PCIe card Dell default cooling response
# No comment will be displayed on the change of this parameter since it is not related to the temperature of any device (CPU, GPU, etc...) but only to the settings made by the user when launching this Docker container
if $DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE
then
disable_third_party_PCIe_card_Dell_default_cooling_response
THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Disabled"
else
enable_third_party_PCIe_card_Dell_default_cooling_response
THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Enabled"
fi
# Print temperatures, active fan control profile and comment if any change happened during last time interval
if [ $i -eq $TABLE_HEADER_PRINT_INTERVAL ]
then
echo " ------- Temperatures -------"
echo " Date & time Inlet CPU 1 CPU 2 Exhaust Active fan speed profile Third-party PCIe card Dell default cooling response Comment"
i=0
fi
printf "%19s %3d°C %3d°C %3s°C %5s°C %40s %51s %s\n" "$(date +"%d-%m-%Y %T")" $INLET_TEMPERATURE $CPU1_TEMPERATURE "$CPU2_TEMPERATURE" "$EXHAUST_TEMPERATURE" "$CURRENT_FAN_CONTROL_PROFILE" "$THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS" "$COMMENT"
((i++))
wait $SLEEP
done

162
Dell_iDRAC_fan_controller.sh.default.sh Normal file
View File

@@ -0,0 +1,162 @@
#!/bin/bash
# Enable strict bash mode to stop the script if an uninitialized variable is used, if a command fails, or if a command with a pipe fails
# Not working in some setups : https://github.com/tigerblue77/Dell_iDRAC_fan_controller/issues/48
# set -euo pipefail
source functions.sh
# Trap the signals for container exit and run gracefull_exit function
trap 'gracefull_exit' SIGQUIT SIGKILL SIGTERM
# Prepare, format and define initial variables
# readonly DELL_FRESH_AIR_COMPLIANCE=45
# Check if FAN_SPEED variable is in hexadecimal format. If not, convert it to hexadecimal
if [[ $FAN_SPEED == 0x* ]]
then
readonly DECIMAL_FAN_SPEED=$(printf '%d' $FAN_SPEED)
readonly HEXADECIMAL_FAN_SPEED=$FAN_SPEED
else
readonly DECIMAL_FAN_SPEED=$FAN_SPEED
readonly HEXADECIMAL_FAN_SPEED=$(convert_decimal_value_to_hexadecimal $FAN_SPEED)
fi
# Check if the iDRAC host is set to 'local' or not then set the IDRAC_LOGIN_STRING accordingly
if [[ $IDRAC_HOST == "local" ]]
then
# Check that the Docker host IPMI device (the iDRAC) has been exposed to the Docker container
if [ ! -e "/dev/ipmi0" ] && [ ! -e "/dev/ipmi/0" ] && [ ! -e "/dev/ipmidev/0" ]; then
echo "/!\ Could not open device at /dev/ipmi0 or /dev/ipmi/0 or /dev/ipmidev/0, check that you added the device to your Docker container or stop using local mode. Exiting." >&2
exit 1
fi
IDRAC_LOGIN_STRING='open'
else
echo "iDRAC/IPMI username: $IDRAC_USERNAME"
echo "iDRAC/IPMI password: $IDRAC_PASSWORD"
IDRAC_LOGIN_STRING="lanplus -H $IDRAC_HOST -U $IDRAC_USERNAME -P $IDRAC_PASSWORD"
fi
get_Dell_server_model
if [[ ! $SERVER_MANUFACTURER == "DELL" ]]
then
echo "/!\ Your server isn't a Dell product. Exiting." >&2
exit 1
fi
# Log main informations
echo "Server model: $SERVER_MANUFACTURER $SERVER_MODEL"
echo "iDRAC/IPMI host: $IDRAC_HOST"
# Log the fan speed objective, CPU temperature threshold and check interval
echo "Fan speed objective: $DECIMAL_FAN_SPEED%"
echo "CPU temperature threshold: $CPU_TEMPERATURE_THRESHOLD°C"
echo "Check interval: ${CHECK_INTERVAL}s"
echo ""
# Define the interval for printing
readonly TABLE_HEADER_PRINT_INTERVAL=10
i=$TABLE_HEADER_PRINT_INTERVAL
# Set the flag used to check if the active fan control profile has changed
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# Check present sensors
IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=true
IS_CPU2_TEMPERATURE_SENSOR_PRESENT=true
retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
if [ -z "$EXHAUST_TEMPERATURE" ]
then
echo "No exhaust temperature sensor detected."
IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=false
fi
if [ -z "$CPU2_TEMPERATURE" ]
then
echo "No CPU2 temperature sensor detected."
IS_CPU2_TEMPERATURE_SENSOR_PRESENT=false
fi
# Output new line to beautify output if one of the previous conditions have echoed
if ! $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT || ! $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
echo ""
fi
# Start monitoring
while true; do
# Sleep for the specified interval before taking another reading
sleep $CHECK_INTERVAL &
SLEEP_PROCESS_PID=$!
retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
# Define functions to check if CPU 1 and CPU 2 temperatures are above the threshold
function CPU1_OVERHEAT () { [ $CPU1_TEMPERATURE -gt $CPU_TEMPERATURE_THRESHOLD ]; }
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
function CPU2_OVERHEAT () { [ $CPU2_TEMPERATURE -gt $CPU_TEMPERATURE_THRESHOLD ]; }
fi
# Initialize a variable to store the comments displayed when the fan control profile changed
COMMENT=" -"
# Check if CPU 1 is overheating then apply Dell default dynamic fan control profile if true
if CPU1_OVERHEAT
then
apply_Dell_fan_control_profile
if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# If CPU 2 temperature sensor is present, check if it is overheating too.
# Do not apply Dell default dynamic fan control profile as it has already been applied before
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT && CPU2_OVERHEAT
then
COMMENT="CPU 1 and CPU 2 temperatures are too high, Dell default dynamic fan control profile applied for safety"
else
COMMENT="CPU 1 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi
fi
# If CPU 2 temperature sensor is present, check if it is overheating then apply Dell default dynamic fan control profile if true
elif $IS_CPU2_TEMPERATURE_SENSOR_PRESENT && CPU2_OVERHEAT
then
apply_Dell_fan_control_profile
if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
COMMENT="CPU 2 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi
else
apply_user_fan_control_profile
# Check if user fan control profile is applied then apply it if not
if $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=false
COMMENT="CPU temperature decreased and is now OK (<= $CPU_TEMPERATURE_THRESHOLD°C), user's fan control profile applied."
fi
fi
# Enable or disable, depending on the user's choice, third-party PCIe card Dell default cooling response
# No comment will be displayed on the change of this parameter since it is not related to the temperature of any device (CPU, GPU, etc...) but only to the settings made by the user when launching this Docker container
if $DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE
then
disable_third_party_PCIe_card_Dell_default_cooling_response
THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Disabled"
else
enable_third_party_PCIe_card_Dell_default_cooling_response
THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Enabled"
fi
# Print temperatures, active fan control profile and comment if any change happened during last time interval
if [ $i -eq $TABLE_HEADER_PRINT_INTERVAL ]
then
echo " ------- Temperatures -------"
echo " Date & time Inlet CPU 1 CPU 2 Exhaust Active fan speed profile Third-party PCIe card Dell default cooling response Comment"
i=0
fi
printf "%19s %3d°C %3d°C %3s°C %5s°C %40s %51s %s\n" "$(date +"%d-%m-%Y %T")" $INLET_TEMPERATURE $CPU1_TEMPERATURE "$CPU2_TEMPERATURE" "$EXHAUST_TEMPERATURE" "$CURRENT_FAN_CONTROL_PROFILE" "$THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS" "$COMMENT"
((i++))
wait $SLEEP_PROCESS_PID
done

29
Dockerfile Normal file
View File

@@ -0,0 +1,29 @@
FROM ubuntu:latest
LABEL org.opencontainers.image.authors="tigerblue77"
RUN apt-get update
RUN apt-get install ipmitool -y
ADD functions.sh /app/functions.sh
ADD healthcheck.sh /app/healthcheck.sh
ADD Dell_iDRAC_fan_controller.sh /app/Dell_iDRAC_fan_controller.sh
RUN chmod 0777 /app/functions.sh /app/healthcheck.sh /app/Dell_iDRAC_fan_controller.sh
WORKDIR /app
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 CMD [ "/app/healthcheck.sh" ]
# you should override these default values when running. See README.md
# ENV IDRAC_HOST 192.168.1.100
ENV IDRAC_HOST local
# ENV IDRAC_USERNAME root
# ENV IDRAC_PASSWORD calvin
ENV FAN_SPEED 5
ENV CPU_TEMPERATURE_THRESHOLD 50
ENV CHECK_INTERVAL 60
ENV DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE false
CMD ["./Dell_iDRAC_fan_controller.sh"]

187
README.md Normal file
View File

@@ -0,0 +1,187 @@
<div id="top"></div>
> **Warning** If you update to the latest version, be sure to replace "CPU_TEMPERATURE_TRESHOLD" environment variable with "CPU_TEMPERATURE_T<ins>H</ins>RESHOLD" which was a typo
# Dell iDRAC fan controller Docker image
Download Docker image from :
- [Docker Hub](https://hub.docker.com/r/tigerblue77/dell_idrac_fan_controller)
- [GitHub Containers Repository](https://github.com/tigerblue77/Dell_iDRAC_fan_controller_Docker/pkgs/container/dell_idrac_fan_controller)
<!-- TABLE OF CONTENTS -->
<details>
<summary>Table of Contents</summary>
<ol>
<li><a href="#container-console-log-example">Container console log example</a></li>
<li><a href="#supported-architectures">Supported architectures</a></li>
<li><a href="#usage">Usage</a></li>
<li><a href="#parameters">Parameters</a></li>
<li><a href="#troubleshooting">Troubleshooting</a></li>
<li><a href="#contributing">Contributing</a></li>
</ol>
</details>
## Container console log example
![image](https://user-images.githubusercontent.com/37409593/216442212-d2ad7ff7-0d6f-443f-b8ac-c67b5f613b83.png)
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- PREREQUISITES -->
## Prerequisites
### iDRAC version
This Docker container only works on Dell PowerEdge servers that support IPMI commands, i.e. < iDRAC 9 firmware 3.30.30.30.
### To access iDRAC over LAN (not needed in "local" mode) :
1. Log into your iDRAC web console
![001](https://user-images.githubusercontent.com/37409593/210168273-7d760e47-143e-4a6e-aca7-45b483024139.png)
2. In the left side menu, expand "iDRAC settings", click "Network" then click "IPMI Settings" link at the top of the web page.
![002](https://user-images.githubusercontent.com/37409593/210168249-994f29cc-ac9e-4667-84f7-07f6d9a87522.png)
3. Check the "Enable IPMI over LAN" checkbox then click "Apply" button.
![003](https://user-images.githubusercontent.com/37409593/210168248-a68982c4-9fe7-40e7-8b2c-b3f06fbfee62.png)
4. Test access to IPMI over LAN running the following commands :
```bash
apt -y install ipmitool
ipmitool -I lanplus \
-H <iDRAC IP address> \
-U <iDRAC username> \
-P <iDRAC password> \
sdr elist all
```
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- SUPPORTED ARCHITECTURES -->
## Supported architectures
This Docker container is currently built and available for the following CPU architectures :
- AMD64
- ARM64
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- USAGE -->
## Usage
1. with local iDRAC:
```bash
docker run -d \
--name Dell_iDRAC_fan_controller \
--restart=unless-stopped \
-e IDRAC_HOST=local \
-e FAN_SPEED=<decimal or hexadecimal fan speed> \
-e CPU_TEMPERATURE_THRESHOLD=<decimal temperature threshold> \
-e CHECK_INTERVAL=<seconds between each check> \
-e DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE=<true or false> \
--device=/dev/ipmi0:/dev/ipmi0:rw \
tigerblue77/dell_idrac_fan_controller:latest
```
2. with LAN iDRAC:
```bash
docker run -d \
--name Dell_iDRAC_fan_controller \
--restart=unless-stopped \
-e IDRAC_HOST=<iDRAC IP address> \
-e IDRAC_USERNAME=<iDRAC username> \
-e IDRAC_PASSWORD=<iDRAC password> \
-e FAN_SPEED=<decimal or hexadecimal fan speed> \
-e CPU_TEMPERATURE_THRESHOLD=<decimal temperature threshold> \
-e CHECK_INTERVAL=<seconds between each check> \
-e DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE=<true or false> \
tigerblue77/dell_idrac_fan_controller:latest
```
`docker-compose.yml` examples:
1. to use with local iDRAC:
```yml
version: '3.8'
services:
Dell_iDRAC_fan_controller:
image: tigerblue77/dell_idrac_fan_controller:latest
container_name: Dell_iDRAC_fan_controller
restart: unless-stopped
environment:
- IDRAC_HOST=local
- FAN_SPEED=<decimal or hexadecimal fan speed>
- CPU_TEMPERATURE_THRESHOLD=<decimal temperature threshold>
- CHECK_INTERVAL=<seconds between each check>
- DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE=<true or false>
devices:
- /dev/ipmi0:/dev/ipmi0:rw
```
2. to use with LAN iDRAC:
```yml
version: '3.8'
services:
Dell_iDRAC_fan_controller:
image: tigerblue77/dell_idrac_fan_controller:latest
container_name: Dell_iDRAC_fan_controller
restart: unless-stopped
environment:
- IDRAC_HOST=<iDRAC IP address>
- IDRAC_USERNAME=<iDRAC username>
- IDRAC_PASSWORD=<iDRAC password>
- FAN_SPEED=<decimal or hexadecimal fan speed>
- CPU_TEMPERATURE_THRESHOLD=<decimal temperature threshold>
- CHECK_INTERVAL=<seconds between each check>
- DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE=<true or false>
```
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- PARAMETERS -->
## Parameters
All parameters are optional as they have default values (including default iDRAC username and password).
- `IDRAC_HOST` parameter can be set to "local" or to your distant iDRAC's IP address. **Default** value is "local".
- `IDRAC_USERNAME` parameter is only necessary if you're adressing a distant iDRAC. **Default** value is "root".
- `IDRAC_PASSWORD` parameter is only necessary if you're adressing a distant iDRAC. **Default** value is "calvin".
- `FAN_SPEED` parameter can be set as a decimal (from 0 to 100%) or hexadecimaladecimal value (from 0x00 to 0x64) you want to set the fans to. **Default** value is 5(%).
- `CPU_TEMPERATURE_THRESHOLD` parameter is the T°junction (junction temperature) threshold beyond which the Dell fan mode defined in your BIOS will become active again (to protect the server hardware against overheat). **Default** value is 50(°C).
- `CHECK_INTERVAL` parameter is the time (in seconds) between each temperature check and potential profile change. **Default** value is 60(s).
- `DISABLE_THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE` parameter is a boolean that allows to disable third-party PCIe card Dell default cooling response. **Default** value is false.
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- TROUBLESHOOTING -->
## Troubleshooting
If your server frequently switches back to the default Dell fan mode:
1. Check `Tcase` (case temperature) of your CPU on Intel Ark website and then set `CPU_TEMPERATURE_THRESHOLD` to a slightly lower value. Example with my CPUs ([Intel Xeon E5-2630L v2](https://www.intel.com/content/www/us/en/products/sku/75791/intel-xeon-processor-e52630l-v2-15m-cache-2-40-ghz/specifications.html)) : Tcase = 63°C, I set `CPU_TEMPERATURE_THRESHOLD` to 60(°C).
2. If it's already good, adapt your `FAN_SPEED` value to increase the airflow and thus further decrease the temperature of your CPU(s)
3. If neither increasing the fan speed nor increasing the threshold solves your problem, then it may be time to replace your thermal paste
<p align="right">(<a href="#top">back to top</a>)</p>
<!-- CONTRIBUTING -->
## Contributing
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".
Don't forget to give the project a star! Thanks again!
1. Fork the Project
2. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)
3. Commit your Changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the Branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
<p align="right">(<a href="#top">back to top</a>)</p>

122
functions.sh Normal file
View File

@@ -0,0 +1,122 @@
# Define global functions
# This function applies Dell's default dynamic fan control profile
function apply_Dell_fan_control_profile () {
# Use ipmitool to send the raw command to set fan control to Dell default
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x01 0x01 > /dev/null
CURRENT_FAN_CONTROL_PROFILE="Dell default dynamic fan control profile"
}
# This function applies a user-specified static fan control profile
function apply_user_fan_control_profile () {
# Use ipmitool to send the raw command to set fan control to user-specified value
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x01 0x00 > /dev/null
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x02 0xff $HEXADECIMAL_FAN_SPEED > /dev/null
CURRENT_FAN_CONTROL_PROFILE="User static fan control profile ($DECIMAL_FAN_SPEED%)"
}
# This function sets the fan speed to a specified value
# Usage: set_fan_speed <decimal_speed>
function set_fan_speed () {
local SPEED=$1
local HEX_SPEED=$(convert_decimal_value_to_hexadecimal $SPEED)
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x02 0xff $HEX_SPEED > /dev/null
CURRENT_FAN_CONTROL_PROFILE="User static fan control profile ($SPEED%)"
}
# Convert first parameter given ($DECIMAL_NUMBER) to hexadecimal
# Usage : convert_decimal_value_to_hexadecimal $DECIMAL_NUMBER
# Returns : hexadecimal value of DECIMAL_NUMBER
function convert_decimal_value_to_hexadecimal () {
local DECIMAL_NUMBER=$1
local HEXADECIMAL_NUMBER=$(printf '0x%02x' $DECIMAL_NUMBER)
echo $HEXADECIMAL_NUMBER
}
# Retrieve temperature sensors data using ipmitool
# Usage : retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
function retrieve_temperatures () {
if (( $# != 2 ))
then
printf "Illegal number of parameters.\nUsage: retrieve_temperatures \$IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT \$IS_CPU2_TEMPERATURE_SENSOR_PRESENT" >&2
return 1
fi
local IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=$1
local IS_CPU2_TEMPERATURE_SENSOR_PRESENT=$2
local DATA=$(ipmitool -I $IDRAC_LOGIN_STRING sdr type temperature | grep degrees)
# Parse CPU data
local CPU_DATA=$(echo "$DATA" | grep "3\." | grep -Po '\d{2}')
CPU1_TEMPERATURE=$(echo $CPU_DATA | awk '{print $1;}')
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
CPU2_TEMPERATURE=$(echo $CPU_DATA | awk '{print $2;}')
else
CPU2_TEMPERATURE="-"
fi
# Parse inlet temperature data
INLET_TEMPERATURE=$(echo "$DATA" | grep Inlet | grep -Po '\d{2}' | tail -1)
# If exhaust temperature sensor is present, parse its temperature data
if $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT
then
EXHAUST_TEMPERATURE=$(echo "$DATA" | grep Exhaust | grep -Po '\d{2}' | tail -1)
else
EXHAUST_TEMPERATURE="-"
fi
}
function enable_third_party_PCIe_card_Dell_default_cooling_response () {
# We could check the current cooling response before applying but it's not very useful so let's skip the test and apply directly
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x00 0x00 0x00 > /dev/null
}
function disable_third_party_PCIe_card_Dell_default_cooling_response () {
# We could check the current cooling response before applying but it's not very useful so let's skip the test and apply directly
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x01 0x00 0x00 > /dev/null
}
# Returns :
# - 0 if third-party PCIe card Dell default cooling response is currently DISABLED
# - 1 if third-party PCIe card Dell default cooling response is currently ENABLED
# - 2 if the current status returned by ipmitool command output is unexpected
# function is_third_party_PCIe_card_Dell_default_cooling_response_disabled() {
# THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE=$(ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x01 0x16 0x05 0x00 0x00 0x00)
# if [ "$THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" == "16 05 00 00 00 05 00 01 00 00" ]; then
# return 0
# elif [ "$THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" == "16 05 00 00 00 05 00 00 00 00" ]; then
# return 1
# else
# echo "Unexpected output: $THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" >&2
# return 2
# fi
# }
# Prepare traps in case of container exit
function gracefull_exit () {
apply_Dell_fan_control_profile
enable_third_party_PCIe_card_Dell_default_cooling_response
echo "/!\ WARNING /!\ Container stopped, Dell default dynamic fan control profile applied for safety."
exit 0
}
# Helps debugging when people are posting their output
function get_Dell_server_model () {
IPMI_FRU_content=$(ipmitool -I $IDRAC_LOGIN_STRING fru 2>/dev/null) # FRU stands for "Field Replaceable Unit"
SERVER_MANUFACTURER=$(echo "$IPMI_FRU_content" | grep "Product Manufacturer" | awk -F ': ' '{print $2}')
SERVER_MODEL=$(echo "$IPMI_FRU_content" | grep "Product Name" | awk -F ': ' '{print $2}')
# Check if SERVER_MANUFACTURER is empty, if yes, assign value based on "Board Mfg"
if [ -z "$SERVER_MANUFACTURER" ]; then
SERVER_MANUFACTURER=$(echo "$IPMI_FRU_content" | tr -s ' ' | grep "Board Mfg :" | awk -F ': ' '{print $2}')
fi
# Check if SERVER_MODEL is empty, if yes, assign value based on "Board Product"
if [ -z "$SERVER_MODEL" ]; then
SERVER_MODEL=$(echo "$IPMI_FRU_content" | tr -s ' ' | grep "Board Product :" | awk -F ': ' '{print $2}')
fi
}

112
functions.sh.default Normal file
View File

@@ -0,0 +1,112 @@
# Define global functions
# This function applies Dell's default dynamic fan control profile
function apply_Dell_fan_control_profile () {
# Use ipmitool to send the raw command to set fan control to Dell default
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x01 0x01 > /dev/null
CURRENT_FAN_CONTROL_PROFILE="Dell default dynamic fan control profile"
}
# This function applies a user-specified static fan control profile
function apply_user_fan_control_profile () {
# Use ipmitool to send the raw command to set fan control to user-specified value
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x01 0x00 > /dev/null
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0x30 0x02 0xff $HEXADECIMAL_FAN_SPEED > /dev/null
CURRENT_FAN_CONTROL_PROFILE="User static fan control profile ($DECIMAL_FAN_SPEED%)"
}
# Convert first parameter given ($DECIMAL_NUMBER) to hexadecimal
# Usage : convert_decimal_value_to_hexadecimal $DECIMAL_NUMBER
# Returns : hexadecimal value of DECIMAL_NUMBER
function convert_decimal_value_to_hexadecimal () {
local DECIMAL_NUMBER=$1
local HEXADECIMAL_NUMBER=$(printf '0x%02x' $DECIMAL_NUMBER)
echo $HEXADECIMAL_NUMBER
}
# Retrieve temperature sensors data using ipmitool
# Usage : retrieve_temperatures $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
function retrieve_temperatures () {
if (( $# != 2 ))
then
printf "Illegal number of parameters.\nUsage: retrieve_temperatures \$IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT \$IS_CPU2_TEMPERATURE_SENSOR_PRESENT" >&2
return 1
fi
local IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT=$1
local IS_CPU2_TEMPERATURE_SENSOR_PRESENT=$2
local DATA=$(ipmitool -I $IDRAC_LOGIN_STRING sdr type temperature | grep degrees)
# Parse CPU data
local CPU_DATA=$(echo "$DATA" | grep "3\." | grep -Po '\d{2}')
CPU1_TEMPERATURE=$(echo $CPU_DATA | awk '{print $1;}')
if $IS_CPU2_TEMPERATURE_SENSOR_PRESENT
then
CPU2_TEMPERATURE=$(echo $CPU_DATA | awk '{print $2;}')
else
CPU2_TEMPERATURE="-"
fi
# Parse inlet temperature data
INLET_TEMPERATURE=$(echo "$DATA" | grep Inlet | grep -Po '\d{2}' | tail -1)
# If exhaust temperature sensor is present, parse its temperature data
if $IS_EXHAUST_TEMPERATURE_SENSOR_PRESENT
then
EXHAUST_TEMPERATURE=$(echo "$DATA" | grep Exhaust | grep -Po '\d{2}' | tail -1)
else
EXHAUST_TEMPERATURE="-"
fi
}
function enable_third_party_PCIe_card_Dell_default_cooling_response () {
# We could check the current cooling response before applying but it's not very useful so let's skip the test and apply directly
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x00 0x00 0x00 > /dev/null
}
function disable_third_party_PCIe_card_Dell_default_cooling_response () {
# We could check the current cooling response before applying but it's not very useful so let's skip the test and apply directly
ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x01 0x00 0x00 > /dev/null
}
# Returns :
# - 0 if third-party PCIe card Dell default cooling response is currently DISABLED
# - 1 if third-party PCIe card Dell default cooling response is currently ENABLED
# - 2 if the current status returned by ipmitool command output is unexpected
# function is_third_party_PCIe_card_Dell_default_cooling_response_disabled() {
# THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE=$(ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x01 0x16 0x05 0x00 0x00 0x00)
# if [ "$THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" == "16 05 00 00 00 05 00 01 00 00" ]; then
# return 0
# elif [ "$THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" == "16 05 00 00 00 05 00 00 00 00" ]; then
# return 1
# else
# echo "Unexpected output: $THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" >&2
# return 2
# fi
# }
# Prepare traps in case of container exit
function gracefull_exit () {
apply_Dell_fan_control_profile
enable_third_party_PCIe_card_Dell_default_cooling_response
echo "/!\ WARNING /!\ Container stopped, Dell default dynamic fan control profile applied for safety."
exit 0
}
# Helps debugging when people are posting their output
function get_Dell_server_model () {
IPMI_FRU_content=$(ipmitool -I $IDRAC_LOGIN_STRING fru 2>/dev/null) # FRU stands for "Field Replaceable Unit"
SERVER_MANUFACTURER=$(echo "$IPMI_FRU_content" | grep "Product Manufacturer" | awk -F ': ' '{print $2}')
SERVER_MODEL=$(echo "$IPMI_FRU_content" | grep "Product Name" | awk -F ': ' '{print $2}')
# Check if SERVER_MANUFACTURER is empty, if yes, assign value based on "Board Mfg"
if [ -z "$SERVER_MANUFACTURER" ]; then
SERVER_MANUFACTURER=$(echo "$IPMI_FRU_content" | tr -s ' ' | grep "Board Mfg :" | awk -F ': ' '{print $2}')
fi
# Check if SERVER_MODEL is empty, if yes, assign value based on "Board Product"
if [ -z "$SERVER_MODEL" ]; then
SERVER_MODEL=$(echo "$IPMI_FRU_content" | tr -s ' ' | grep "Board Product :" | awk -F ': ' '{print $2}')
fi
}

24
healthcheck.sh Normal file
View File

@@ -0,0 +1,24 @@
#!/bin/bash
# Enable strict bash mode to stop the script if an uninitialized variable is used, if a command fails, or if a command with a pipe fails
# Not working in some setups : https://github.com/tigerblue77/Dell_iDRAC_fan_controller/issues/48
# set -euo pipefail
source functions.sh
# Check if the iDRAC host is set to 'local' or not then set the IDRAC_LOGIN_STRING accordingly
if [[ $IDRAC_HOST == "local" ]]
then
# Check that the Docker host IPMI device (the iDRAC) has been exposed to the Docker container
if [ ! -e "/dev/ipmi0" ] && [ ! -e "/dev/ipmi/0" ] && [ ! -e "/dev/ipmidev/0" ]; then
echo "/!\ Could not open device at /dev/ipmi0 or /dev/ipmi/0 or /dev/ipmidev/0, check that you added the device to your Docker container or stop using local mode. Exiting." >&2
exit 1
fi
IDRAC_LOGIN_STRING='open'
else
echo "iDRAC/IPMI username: $IDRAC_USERNAME"
echo "iDRAC/IPMI password: $IDRAC_PASSWORD"
IDRAC_LOGIN_STRING="lanplus -H $IDRAC_HOST -U $IDRAC_USERNAME -P $IDRAC_PASSWORD"
fi
ipmitool -I $IDRAC_LOGIN_STRING sdr type temperature