Add comments for clarity + minor improvements (#39)

* Added comments for clarity.

* Updated comments

* Update Dell_iDRAC_fan_controller.sh

* Added more comments

* Improved PR

---------

Co-authored-by: Ryan Bush <20880666+rpbush@users.noreply.github.com>
This commit is contained in:
Tigerblue77 2023-02-04 13:09:27 +01:00 committed by GitHub
parent a3f070f1b4
commit 9f320e5e0e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -1,25 +1,29 @@
#!/bin/bash #!/bin/bash
# Define global functions # Define global functions
function apply_Dell_profile () { # This function applies Dell's default dynamic fan control profile
ipmitool -I $LOGIN_STRING raw 0x30 0x30 0x01 0x01 > /dev/null 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" CURRENT_FAN_CONTROL_PROFILE="Dell default dynamic fan control profile"
} }
function apply_user_profile () { # This function applies a user-specified static fan control profile
ipmitool -I $LOGIN_STRING raw 0x30 0x30 0x01 0x00 > /dev/null function apply_user_fan_control_profile () {
ipmitool -I $LOGIN_STRING raw 0x30 0x30 0x02 0xff $HEXADECIMAL_FAN_SPEED > /dev/null # 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%)" CURRENT_FAN_CONTROL_PROFILE="User static fan control profile ($DECIMAL_FAN_SPEED%)"
} }
function enable_third_party_PCIe_card_Dell_default_cooling_response () { 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 # 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 $LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x00 0x00 0x00 > /dev/null 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 () { 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 # 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 $LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x01 0x00 0x00 > /dev/null ipmitool -I $IDRAC_LOGIN_STRING raw 0x30 0xce 0x00 0x16 0x05 0x00 0x00 0x00 0x05 0x00 0x01 0x00 0x00 > /dev/null
} }
# Returns : # Returns :
@ -27,7 +31,7 @@ function disable_third_party_PCIe_card_Dell_default_cooling_response () {
# - 1 if third-party PCIe card Dell default cooling response is currently ENABLED # - 1 if third-party PCIe card Dell default cooling response is currently ENABLED
# - 2 if the current status returned by ipmitool command output is unexpected # - 2 if the current status returned by ipmitool command output is unexpected
# function is_third_party_PCIe_card_Dell_default_cooling_response_disabled() { # function is_third_party_PCIe_card_Dell_default_cooling_response_disabled() {
# THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE=$(ipmitool -I $LOGIN_STRING raw 0x30 0xce 0x01 0x16 0x05 0x00 0x00 0x00) # THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE=$(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 # if [ "$THIRD_PARTY_PCIE_CARD_COOLING_RESPONSE" == "16 05 00 00 00 05 00 01 00 00" ]; then
# return 0 # return 0
@ -41,18 +45,20 @@ function disable_third_party_PCIe_card_Dell_default_cooling_response () {
# Prepare traps in case of container exit # Prepare traps in case of container exit
function gracefull_exit () { function gracefull_exit () {
apply_Dell_profile apply_Dell_fan_control_profile
enable_third_party_PCIe_card_Dell_default_cooling_response enable_third_party_PCIe_card_Dell_default_cooling_response
echo "/!\ WARNING /!\ Container stopped, Dell default dynamic fan control profile applied for safety." echo "/!\ WARNING /!\ Container stopped, Dell default dynamic fan control profile applied for safety."
exit 0 exit 0
} }
# Trap the signals for container exit and run gracefull_exit function
trap 'gracefull_exit' SIGQUIT SIGKILL SIGTERM trap 'gracefull_exit' SIGQUIT SIGKILL SIGTERM
# Prepare, format and define initial variables # Prepare, format and define initial variables
# readonly DELL_FRESH_AIR_COMPLIANCE=45 # 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* ]] if [[ $FAN_SPEED == 0x* ]]
then then
DECIMAL_FAN_SPEED=$(printf '%d' $FAN_SPEED) DECIMAL_FAN_SPEED=$(printf '%d' $FAN_SPEED)
@ -63,72 +69,85 @@ else
fi fi
# Log main informations given to the container # Log main informations given to the container
echo "Idrac/IPMI host: $IDRAC_HOST" echo "iDRAC/IPMI host: $IDRAC_HOST"
# Check if the iDRAC host is set to 'local' or not then set the IDRAC_LOGIN_STRING accordingly
if [[ $IDRAC_HOST == "local" ]] if [[ $IDRAC_HOST == "local" ]]
then then
LOGIN_STRING='open' IDRAC_LOGIN_STRING='open'
else else
echo "Idrac/IPMI username: $IDRAC_USERNAME" echo "iDRAC/IPMI username: $IDRAC_USERNAME"
echo "Idrac/IPMI password: $IDRAC_PASSWORD" echo "iDRAC/IPMI password: $IDRAC_PASSWORD"
LOGIN_STRING="lanplus -H $IDRAC_HOST -U $IDRAC_USERNAME -P $IDRAC_PASSWORD" IDRAC_LOGIN_STRING="lanplus -H $IDRAC_HOST -U $IDRAC_USERNAME -P $IDRAC_PASSWORD"
fi fi
# Log the fan speed objective, CPU temperature threshold and check interval
echo "Fan speed objective: $DECIMAL_FAN_SPEED%" echo "Fan speed objective: $DECIMAL_FAN_SPEED%"
echo "CPU temperature treshold: $CPU_TEMPERATURE_TRESHOLD°C" echo "CPU temperature treshold: $CPU_TEMPERATURE_TRESHOLD°C"
echo "Check interval: ${CHECK_INTERVAL}s" echo "Check interval: ${CHECK_INTERVAL}s"
echo "" echo ""
# Prepare required variables and constants # Define the interval for printing
readonly TABLE_HEADER_PRINT_INTERVAL=10 readonly TABLE_HEADER_PRINT_INTERVAL=10
i=$TABLE_HEADER_PRINT_INTERVAL i=$TABLE_HEADER_PRINT_INTERVAL
IS_DELL_PROFILE_APPLIED=true # Set the flag used to check if the active fan control profile has changed
IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# Start monitoring # Start monitoring
while true; do while true; do
# Sleep for the specified interval before taking another reading
sleep $CHECK_INTERVAL & sleep $CHECK_INTERVAL &
SLEEP_PROCESS_PID=$! SLEEP_PROCESS_PID=$!
DATA=$(ipmitool -I $LOGIN_STRING sdr type temperature | grep degrees) # Retrieve sensor data using ipmitool
DATA=$(ipmitool -I $IDRAC_LOGIN_STRING sdr type temperature | grep degrees)
INLET_TEMPERATURE=$(echo "$DATA" | grep Inlet | grep -Po '\d{2}' | tail -1) INLET_TEMPERATURE=$(echo "$DATA" | grep Inlet | grep -Po '\d{2}' | tail -1)
EXHAUST_TEMPERATURE=$(echo "$DATA" | grep Exhaust | grep -Po '\d{2}' | tail -1) EXHAUST_TEMPERATURE=$(echo "$DATA" | grep Exhaust | grep -Po '\d{2}' | tail -1)
CPU_DATA=$(echo "$DATA" | grep "3\." | grep -Po '\d{2}') CPU_DATA=$(echo "$DATA" | grep "3\." | grep -Po '\d{2}')
CPU1_TEMPERATURE=$(echo $CPU_DATA | awk '{print $1;}') CPU1_TEMPERATURE=$(echo $CPU_DATA | awk '{print $1;}')
CPU2_TEMPERATURE=$(echo $CPU_DATA | awk '{print $2;}') CPU2_TEMPERATURE=$(echo $CPU_DATA | awk '{print $2;}')
CPU1_OVERHEAT () { [ $CPU1_TEMPERATURE -gt $CPU_TEMPERATURE_TRESHOLD ]; } # Define functions to check if CPU 1 and CPU 2 temperatures are above the threshold
CPU2_OVERHEAT () { [ $CPU2_TEMPERATURE -gt $CPU_TEMPERATURE_TRESHOLD ]; } function CPU1_OVERHEAT () { [ $CPU1_TEMPERATURE -gt $CPU_TEMPERATURE_TRESHOLD ]; }
function CPU2_OVERHEAT () { [ $CPU2_TEMPERATURE -gt $CPU_TEMPERATURE_TRESHOLD ]; }
# Initialize a variable to store the comments displayed when the fan control profile changed
COMMENT=" -" COMMENT=" -"
# Check if CPU 1 is overheating then apply Dell default dynamic fan control profile if true
if CPU1_OVERHEAT if CPU1_OVERHEAT
then then
apply_Dell_profile apply_Dell_fan_control_profile
if ! $IS_DELL_PROFILE_APPLIED if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then then
IS_DELL_PROFILE_APPLIED=true IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
# Check if CPU 2 is overheating too, Dell default dynamic fan control profile already applied before
if CPU2_OVERHEAT if CPU2_OVERHEAT
then then
COMMENT="CPU 1 and CPU 2 temperatures are too high. Dell default dynamic fan control profile applied." COMMENT="CPU 1 and CPU 2 temperatures are too high, Dell default dynamic fan control profile applied for safety"
else else
COMMENT="CPU 1 temperature is too high. Dell default dynamic fan control profile applied." COMMENT="CPU 1 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi fi
fi fi
# Check if CPU 2 is overheating then apply Dell default dynamic fan control profile if true
elif CPU2_OVERHEAT elif CPU2_OVERHEAT
then then
apply_Dell_profile apply_Dell_fan_control_profile
if ! $IS_DELL_PROFILE_APPLIED if ! $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then then
IS_DELL_PROFILE_APPLIED=true IS_DELL_FAN_CONTROL_PROFILE_APPLIED=true
COMMENT="CPU 2 temperature is too high. Dell default dynamic fan control profile applied." COMMENT="CPU 2 temperature is too high, Dell default dynamic fan control profile applied for safety"
fi fi
else else
apply_user_profile apply_user_fan_control_profile
if $IS_DELL_PROFILE_APPLIED # Check if user fan control profile is applied then apply it if not
if $IS_DELL_FAN_CONTROL_PROFILE_APPLIED
then then
COMMENT="CPU temperature decreased and is now OK (<= $CPU_TEMPERATURE_TRESHOLD°C). User's fan control profile applied." IS_DELL_FAN_CONTROL_PROFILE_APPLIED=false
IS_DELL_PROFILE_APPLIED=false COMMENT="CPU temperature decreased and is now OK (<= $CPU_TEMPERATURE_TRESHOLD°C), user's fan control profile applied."
fi fi
fi fi
@ -143,15 +162,14 @@ while true; do
THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Enabled" THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS="Enabled"
fi fi
# Print temperatures array # Print temperatures, active fan control profile and comment if any change happened during last time interval
if [ $i -ge $TABLE_HEADER_PRINT_INTERVAL ] if [ $i -eq $TABLE_HEADER_PRINT_INTERVAL ]
then then
echo " ------- Temperatures -------" echo " ------- Temperatures -------"
echo " Date & time Inlet CPU 1 CPU 2 Exhaust Active fan speed profile Third-party PCIe card Dell default cooling response Comment" echo " Date & time Inlet CPU 1 CPU 2 Exhaust Active fan speed profile Third-party PCIe card Dell default cooling response Comment"
i=0 i=0
fi fi
printf "%12s %3d°C %3d°C %3d°C %5d°C %40s %51s %s\n" "$(date +"%d-%m-%y %H:%M:%S")" $INLET_TEMPERATURE $CPU1_TEMPERATURE $CPU2_TEMPERATURE $EXHAUST_TEMPERATURE "$CURRENT_FAN_CONTROL_PROFILE" "$THIRD_PARTY_PCIE_CARD_DELL_DEFAULT_COOLING_RESPONSE_STATUS" "$COMMENT" printf "%19s %3d°C %3d°C %3d°C %5d°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++)) ((i++))
wait $SLEEP_PROCESS_PID wait $SLEEP_PROCESS_PID
done done