[gelöst] USV an Proxmox in LXC durchreichen

David G.

Ich hab die usb am Server stecken und dort auch den Nut Server installiert.
So fährt das System sauber runter. Proxmox fährt dann sauber alle VMs sauber runter.
Der iobroker kann sich per nut auch verbinden und alle Daten abrufen für vis etc.

wendy2702

Hast du auch einen NUT client auf dem Server installiert?

Und du hast nichts in die IOB CT oder VM durchgereicht wenn ich das richtig verstehe.

David G.

@wendy2702

Ja, am Host nur den Server laufen. An nichts durchgereicht.
Der Nut Adapter kann sich zum nut Server verbinden.

wendy2702

Magst du bei Gelegenheit mal deine Konfig files zeigen?

Hat aber keine Eile.

David G.

@wendy2702

# Network UPS Tools: example nut.conf
#
##############################################################################
# General section
##############################################################################
# The MODE determines which part of the NUT is to be started, and which
# configuration files must be modified.
#
# This file try to standardize the various files being found in the field, like
# /etc/default/nut on Debian based systems, /etc/sysconfig/ups on RedHat based
# systems, ... Distribution's init script should source this file to see which
# component(s) has to be started.
#
# The values of MODE can be:
# - none: NUT is not configured, or use the Integrated Power Management, or use
#   some external system to startup NUT components. So nothing is to be started.
# - standalone: This mode address a local only configuration, with 1 UPS
#   protecting the local system. This implies to start the 3 NUT layers (driver,
#   upsd and upsmon) and the matching configuration files. This mode can also
#   address UPS redundancy.
# - netserver: same as for the standalone configuration, but also need
#   some more network access controls (firewall, tcp-wrappers) and possibly a
#   specific LISTEN directive in upsd.conf.
#   Since this MODE is opened to the network, a special care should be applied
#   to security concerns.
# - netclient: this mode only requires upsmon.
#
# IMPORTANT NOTE:
#  This file is intended to be sourced by standard POSIX shell scripts (so
#  there is no guaranteed `export VAR=VAL` syntax) and by systemd on Linux.
#  You MUST NOT use spaces around the equal sign!

MODE=netserver

# Uncomment this to allow starting the service even if ups.conf has no device
# sections at the moment. This environment variable overrides the built-in
# "false" and an optional same-named default flag that can be set in upsd.conf:
#ALLOW_NO_DEVICE=true
#export ALLOW_NO_DEVICE

# Network UPS Tools: example ups.conf
#
# --- SECURITY NOTE ---
#
# If you use snmp-ups and set a community string in here, you
# will have to secure this file to keep other users from obtaining
# that string.  It needs to be readable by upsdrvctl and any drivers,
# and by upsd.
#
# ---
#
# This is where you configure all the UPSes that this system will be
# monitoring directly.  These are usually attached to serial ports, but
# USB devices and SNMP devices are also supported.
#
# This file is used by upsdrvctl to start and stop your driver(s), and
# is also used by upsd to determine which drivers to monitor.  The
# drivers themselves also read this file for configuration directives.
#
# The general form is:
#
# [upsname]
#       driver = <drivername>
#         port = <portname>
#       < any other directives here >
#
# The section header ([upsname]) can be just about anything as long as
# it is a single word inside brackets.  upsd uses this to uniquely
# identify a UPS on this system.
#
# If you have a UPS called snoopy, your section header would be "[snoopy]".
# On a system called "doghouse", the line in your upsmon.conf to monitor
# and manage it would look something like this:
#
#   MONITOR snoopy@doghouse 1 upsmonuser mypassword primary
#
# It might look like this if monitoring in "secondary" mode (without any
# ability to directly manage the UPS) from a different system:
#
#   MONITOR snoopy@doghouse 1 upsmonuser mypassword secondary
#
# Configuration directives
# ------------------------
#
# These directives are used by upsdrvctl only and should be specified outside
# of a driver definition:
#
#    maxretry: OPTIONAL.  Specify the number of attempts to start the driver(s),
#              in case of failure, before giving up. A delay of 'retrydelay' is
#              inserted between each attempt. Caution should be taken when using
#              this option, since it can impact the time taken by your system to
#              start.
#
#              The built-in default is 1 attempt.
#
#  retrydelay: OPTIONAL.  Specify the delay between each restart attempt of the
#              driver(s), as specified by 'maxretry'. Caution should be taken
#              when using this option, since it can impact the time taken by your
#              system to start.
#
#              The default is 5 seconds.
#
#      chroot: OPTIONAL. Used for securing. See man page for details.
#
#  driverpath: OPTIONAL. Used for custom setups. See man page for details.
#
#      nowait: OPTIONAL. Tell upsdrvctl to not wait at all for the driver(s)
#              to execute the requested command. Fire and forget.
#
# pollinterval: OPTIONAL. The status of the UPS will be refreshed after a
#              maximum delay which is controlled by this setting (default
#              2 seconds). This may be useful if the driver is creating too
#              much of a load on your system or network.
#              Note that some drivers also have an option called *pollfreq*
#              which controls how frequently some of the less critical
#              parameters are polled. See respective driver man pages.
#

# Set maxretry to 3 by default, this should mitigate race with slow devices:
maxretry = 3

# These directives can be set outside and inside a driver definition, with
# slightly different meanings per context:
#
# maxstartdelay: OPTIONAL.  This can be set as a global variable
#                above your first UPS definition and it can also be
#                set in a UPS section.  This value controls how long
#                upsdrvctl will wait for the driver to finish starting.
#                This keeps your system from getting stuck due to a
#                broken driver or UPS.
#                The default is 45 seconds.
#
#   debug_min: OPTIONAL.  Specify a minimum debug level for all driver daemons
#              (when specified at global level), or for this driver daemon
#              (when specified in a driver section), e.g. for troubleshooting
#              a deployment. This does not directly impact the foreground or
#              background running mode. If both the global and driver level
#              `debug_min` are set, the driver-level setting takes precedence.
#              Command-line option `-D` can only increase this verbosity level.
#
# user, group: OPTIONAL. Overrides the compiled-in (also global-section,
#                when used in driver section) default unprivileged user/group
#                name for NUT device driver. Impacts access rights used for
#                the socket file access (group) and communication ports (user).
#
# synchronous: OPTIONAL.  The driver work by default in asynchronous
#              mode (like *no*) with fallback to synchronous if sending
#              fails (i.e *synchronous=auto*).  This means that all data
#              are pushed by the driver on the communication socket to
#              upsd (Unix socket on Unix, Named pipe on Windows) without
#              waiting for these data to be actually consumed.  With
#              some HW, such as ePDUs, that can produce a lot of data,
#              asynchronous mode may cause some congestion, resulting in
#              the socket to be full, and the driver to appear as not
#              connected.  By enabling the 'synchronous' flag
#              (value = 'yes'), the driver will wait for data to be
#              consumed by upsd, prior to publishing more.  This can be
#              enabled either globally or per driver.
#
#              The default is 'no' (i.e. asynchronous mode) for backward
#              compatibility of the driver behavior.
#

# These directives are common to all drivers that support ups.conf:
#
#  driver: REQUIRED.  Specify the program to run to talk to this UPS.
#          apcsmart, bestups, and sec are some examples.
#
#    port: REQUIRED.  The serial port where your UPS is connecte#    desc: optional, to keep a note of the UPS purpose, location, etc.
#
#  nolock: optional, and not recommended for use in this file.
#
#          If you put nolock in here, the driver will not lock the
#          serial port every time it starts.  This may allow other
#          processes to seize the port if you start more than one by
#          mistake.
#
#          This is only intended to be used on systems where locking
#          absolutely must be disabled for the software to work.
#
# ignorelb: OPTIONAL. Ignore low battery condition reported by device,
#           and evaluate remaining battery charge or runtime instead.
#           See man page for details.
#
# usb_set_altinterface(=num): OPTIONAL. Require that NUT calls this method
#           to set the interface, even if 0 (default). Some devices require
#           the call to initialize; others however can get stuck due to it -
#           so it is not called by default. Yet others can be composite
#           devices which use a non-zero interface to represent the UPS.
#
# default.<variable>: OPTIONAL. Set a default value for <variable> which is
#           used in case the UPS doesn't provide a value, but which will be
#           overwritten if a value is available from the UPS, e.g.:
#               default.input.voltage.nominal = 230
#           will report the nominal input voltage to be 230, unless the UPS
#           eventually tells us differently.
#
# override.<variable>: OPTIONAL. Set a value for <value> that overrides
#           (for NUT) any value that may be read from the UPS.
#           Used for overriding values from the UPS that are clearly wrong
#           (e.g. some devices report wrong values for battery voltage):
#               override.battery.voltage.nominal = 12
#           Use with caution!  This will only change the appearance of the
#           variable to the outside world (and NUT calculations), internally
#           in the UPS the original value is used.
#
# Anything else is passed through to the hardware-specific part of
# the driver.
#
# Examples
# --------
#
# A simple example for a UPS called "powerpal" that uses the blazer_ser
# driver on /dev/ttyS0 is:
#
# [powerpal]
#   driver = blazer_ser
#   port = /dev/ttyS0
#   desc = "Web server"
#
# If your UPS driver requires additional settings, you can specify them
# here.  For example, if it supports a setting of "1234" for the
# variable "cable", it would look like this:
#
# [myups]
#   driver = mydriver
#   port = /dev/ttyS1
#   cable = 1234
#   desc = "Something descriptive"
#
# To find out if your driver supports any extra settings, start it with
# the -h option and/or read the driver's documentation.
[ups]
        driver = "usbhid-ups"
        port = "auto"
        desc = "ups"
        pollinterval = 10
        override.battery.charge.low = 35
        override.battery.runtime.low = 600

# Network UPS Tools: example upsd configuration file
#
# This file contains access control data, you should keep it secure.
#
# It should only be readable by the user that upsd becomes.  See the FAQ.
#
# Each entry below provides usage and default value.
#
# For more information, refer to upsd.conf manual page.

# =======================================================================
# MAXAGE <seconds>
# MAXAGE 15
#
# This defaults to 15 seconds.  After a UPS driver has stopped updating
# the data for this many seconds, upsd marks it stale and stops making
# that information available to clients.  After all, the only thing worse
# than no data is bad data.
#
# You should only use this if your driver has difficulties keeping
# the data fresh within the normal 15 second interval.  Watch the syslog
# for notifications from upsd about staleness.

# =======================================================================
# TRACKINGDELAY <seconds>
# TRACKINGDELAY 3600
#
# This defaults to 1 hour. When instant commands and variables setting status
# tracking is enabled, status execution information are kept during this
# amount of time, and then cleaned up.

# =======================================================================
# ALLOW_NO_DEVICE <Boolean>
# ALLOW_NO_DEVICE true
#
# Normally upsd requires that at least one device section is defined in ups.conf
# when the daemon starts, to serve its data.  For automatically managed services
# it may be preferred to have upsd always running, and reload the configuration
# when power devices become defined.
#
# Boolean values 'true', 'yes', 'on' and '1' mean that the server would not
# refuse to start with zero device sections found in ups.conf.
#
# Boolean values 'false', 'no', 'off' and '0' mean that the server should refuse
# to start if zero device sections were found in ups.conf. This is the default.

# =======================================================================
# STATEPATH <path>
# STATEPATH /var/run/nut
#
# Tell upsd to look for the driver state sockets in 'path' rather
# than the default that was compiled into the program.

# =======================================================================
# LISTEN <IP address or name> [<port>]
# LISTEN 127.0.0.1 3493
# LISTEN ::1 3493
# LISTEN myhostname 83493
# LISTEN myhostname.mydomain
#
# This defaults to the localhost listening addresses and port 3493.
# In case of IP v4 or v6 disabled kernel, only the available one will be used.
#
# You may specify each interface IP address or name that you want upsd to
# listen on for connections, optionally with a port number.
#
# You may need this if you have multiple interfaces on your machine and
# you don't want upsd to listen to all interfaces (for instance on a
# firewall, you may not want to listen to the external interface).
#
# This will only be read at startup of upsd.  If you make changes here,
# you'll need to restart upsd, reload will have no effect.

# =======================================================================
# MAXCONN <connections>
# MAXCONN 1024
#
# This defaults to maximum number allowed on your system.  Each UPS, each
# LISTEN address and each client count as one connection.  If the server
# runs out of connections, it will no longer accept new incoming client
# connections.  Only set this if you know exactly what you're doing.

# =======================================================================
# CERTFILE <certificate file>
# CERTFILE /usr/local/ups/etc/upsd.pem
#
# When compiled with SSL support with OpenSSL backend,
# you can enter the certificate file here.
# The certificates must be in PEM format and must be sorted starting with
# the subject's certificate (server certificate), followed by intermediate
# CA certificates (if applicable_ and the highest level (root) CA. It should
# end with the server key. See 'docs/security.txt' or the Security chapter of
# NUT user manual for more information on the SSL support in NUT.
#
# See 'docs/security.txt' or the Security chapter of NUT user manual
# for more information on the SSL support in NUT.

# =======================================================================
# CERTPATH <certificate file or directory>
# CERTPATH /usr/local/ups/etc/cert/upsd
#
# When compiled with SSL support with NSS backend,
# you can enter the certificate path here.
# Certificates are stored in a dedicated database (split into 3 files).
# Specify the path of the database directory.
#
# See 'docs/security.txt' or the Security chapter of NUT user manual
# for more information on the SSL support in NUT.

# =======================================================================
# CERTIDENT <certificate name> <database password>
# CERTIDENT "my nut server" "MyPasSw0rD"
#
# When compiled with SSL support with NSS backend,
# you can specify the certificate name to retrieve from database to
# authenticate itself and the password
# required to access certificate related private key.
#
# See 'docs/security.txt' or the Security chapter of NUT user manual
# for more information on the SSL support in NUT.

# =======================================================================
# CERTREQUEST <certificate request level>
# CERTREQUEST REQUIRE
#
# When compiled with SSL support with NSS backend and client certificate
# validation (disabled by default, see 'docs/security.txt'),
# you can specify if upsd requests or requires client's' certificates.
# Possible values are :
#  - 0 to not request to clients to provide any certificate
#  - 1 to require to all clients a certificate
#  - 2 to require to all clients a valid certificate
#
# See 'docs/security.txt' or the Security chapter of NUT user manual
# for more information on the SSL support in NUT.

# =======================================================================
# DISABLE_WEAK_SSL <Boolean>
# DISABLE_WEAK_SSL true
#
# Tell upsd to disable older/weak SSL/TLS protocols and ciphers.
#
# With relatively recent versions of OpenSSL or NSS it will be restricted
# to TLSv1.2 or better.
#
# Unless you have really ancient clients, you probably want to enable this.
# Currently disabled by default to ensure compatibility with existing setups.

# =======================================================================
# DEBUG_MIN <Integer>
# DEBUG_MIN 2
#.
# Optionally specify a minimum debug level for `upsd` data daemon, e.g. for
# troubleshooting a deployment, without impacting foreground or background
# running mode directly, and without need to edit init-scripts or service
# unit definitions. Note that command-line option `-D` can only increase
# this verbosity level.
#
# NOTE: if the running daemon receives a `reload` command, presence of the
# `DEBUG_MIN NUMBER` value in the configuration file can be used to tune
# debugging verbosity in the running service daemon (it is recommended to
# comment it away or set the minimum to explicit zero when done, to avoid
# huge journals and I/O system abuse). Keep in mind that for this run-time
# tuning, the `DEBUG_MIN` value *present* in *reloaded* configuration files
# is applied instantly and overrides any previously set value, from file
# or CLI options, regardless of older logging level being higher or lower
# than the newly found number; a missing (or commented away) value however
# does not change the previously active logging verbosity.
LISTEN 0.0.0.0 3493
LISTEN 192.168.99.33 3493
LISTEN 192.168.99.58 3493

# Network UPS Tools: Example upsd.users
#
# This file sets the permissions for upsd - the UPS network daemon.
# Users are defined here, are given passwords, and their privileges are
# controlled here too.  Since this file will contain passwords, keep it
# secure, with only enough permissions for upsd to read it.

# --------------------------------------------------------------------------

# Each user gets a section.  To start a section, put the username in
# brackets on a line by itself.  To set something for that user, specify
# it under that section heading.  The username is case-sensitive, so
# admin and AdMiN are two different users.
#
# Possible settings:
#
# password: The user's password.  This is case-sensitive.
#
# --------------------------------------------------------------------------
#
# actions: Let the user do certain things with upsd.
#
# Valid actions are:
#
# SET   - change the value of certain variables in the UPS
# FSD   - set the "forced shutdown" flag in the UPS
#
# --------------------------------------------------------------------------
#
# instcmds: Let the user initiate specific instant commands.  Use "ALL"
# to grant all commands automatically.  There are many possible
# commands, so use 'upscmd -l' to see what your hardware supports.  Here
# are a few examples:
#
# test.panel.start      - Start a front panel test
# test.battery.start    - Start battery test
# test.battery.stop     - Stop battery test
# calibrate.start       - Start calibration
# calibrate.stop        - Stop calibration
#
# --------------------------------------------------------------------------
#
# Example:
#
#	[admin]
#		password = mypass
#		actions = SET
#		instcmds = ALL
#

#
# --- Configuring for a user who can execute tests only
#
#	[testuser]
#		password  = pass
#		instcmds  = test.battery.start
#		instcmds  = test.battery.stop

#
# --- Configuring for upsmon
#
# To add a user for your upsmon, use this example:
#
#   [upsmon]
#       password  = pass
#       upsmon primary
# or
#       upsmon secondary
#
# The matching MONITOR line in your upsmon.conf would look like this:
#
# MONITOR myups@localhost 1 upsmon pass primary	(or secondary)
#
# See comments in the upsmon.conf(.sample) file for details about this
# keyword and the difference of NUT secondary and primary systems.
[usv]
       password = xxxxx
       actions = SET
       instcmds = ALL
       upsmon master

wendy2702

@David-G. Mega, Vielen Dank!

David G.

@wendy2702

Bei deiner USV musst du natürlich recherchieren, welchen Treiber man angeben muss.

wendy2702

@David-G. Ja.

Das weiß ich noch. Hatte das vor x Jahren mal laufen aber damals nicht unter Proxmox

wendy2702

@david-g. Danke nochmal für deine CONF Daten. USV läuft jetzt am ersten Server. Jetzt noch was mit Blockly häkeln damit alles irgenwann runterfährt.

Negalein

muss mich auch kurz einklinken.

ChatGPT schlägt mir folgendes vor. Passt da vorallem das wegen Proxmox?

peterfido

ChatGPT sagt dauernd "Super" "sauber", etc.

Meine einfache Regel: Die großen Stromfresser zuerst. Also NAS mit vielen Festplatten, Windows PC und so halt. Proxmox beendet alles automatisch in der umgekehrten Reihenfolge des Startens. Da braucht man nicht manuell eingreifen.

Windows macht gelegentlich Ärger, wenn da was nicht gespeichert wurde. Da muss der Befehl zum Herunterfahren Forcieren.

David G.

Hab dein ChatGPT Kram nur ganz grob im Ansatz überflogen (Hier im Forum lese ich nur, was Menschen schreiben, keine 10 Seiten aus ChatGPT).

Ich würde sagen, es ist Geschmackssache. Außer beide Standorte wären an verschiedenen Sicherungen im Haus.

Community Forum

NEWS

[gelöst] USV an Proxmox in LXC durchreichen

LXCs sauber stoppen

Support us

485

32.7k

82.3k

1.3m