smartd, dma config

ansible/README.md

@@ -1,9 +1,10 @@
 Assumes:
 
-- ALl:
+- All:
   - OS (Debian) has been installed and IPs have been configured in hosts.cfg
   - Host is already trusted via ssh and can be ssh'd into using keys
   - Passwordless sudo is enabled for the user ansible uses
+  - Root and user pw is something memorable
 
 - Wireguard hosts:
   - Secure boot is disabled (wireguard is an unsigned module)

ansible/files/dma.conf

@@ -0,0 +1,68 @@
+# $DragonFly: src/etc/dma/dma.conf,v 1.2 2008/02/04 10:11:41 matthias Exp $
+#
+# Your smarthost (also called relayhost).  Leave blank if you don't want
+# smarthost support.
+# NOTE: on Debian systems this is handled via debconf!
+# Please use dpkg-reconfigure dma to change this value.
+SMARTHOST smtp.gmail.com
+
+# Use this SMTP port.  Most users will be fine with the default (25)
+PORT 587
+
+# Path to your alias file.  Just stay with the default.
+#ALIASES /etc/aliases
+
+# Path to your spooldir.  Just stay with the default.
+#SPOOLDIR /var/spool/dma
+
+# SMTP authentication
+AUTHPATH /etc/dma/auth.conf
+
+# Uncomment if yout want TLS/SSL support
+SECURETRANSFER
+
+# Uncomment if you want STARTTLS support (only used in combination with
+# SECURETRANSFER)
+STARTTLS
+
+# Uncomment if you have specified STARTTLS above and it should be allowed
+# to fail ("opportunistic TLS", use an encrypted connection when available
+# but allow an unencrypted one to servers that do not support it)
+#OPPORTUNISTIC_TLS
+
+# Path to your local SSL certificate
+#CERTFILE
+
+# If you want to use plain text SMTP login without using encryption, change
+# the SECURE entry below to INSECURE.  Otherwise plain login will only work
+# over a secure connection.  Use this option with caution.
+#SECURE
+
+# Uncomment if you want to defer your mails.  This is useful if you are
+# behind a dialup line.  You have to submit your mails manually with dma -q
+#DEFER
+
+# Uncomment if you want the bounce message to include the complete original
+# message, not just the headers.
+#FULLBOUNCE
+
+# The internet hostname dma uses to identify the host.
+# If not set or empty, the result of gethostname(2) is used.
+# If MAILNAME is an absolute path to a file, the first line of this file
+# will be used as the hostname.
+# NOTE: on Debian systems this is handled via debconf!
+# Please use dpkg-reconfigure dma to change this value.
+MAILNAME /etc/mailname
+
+# Masquerade envelope from addresses with this address/hostname.
+# Use this if mails are not accepted by destination mail servers because
+# your sender domain is invalid.
+# By default, MASQUERADE is not set.
+# Format: MASQUERADE [user@][host]
+# Examples:
+# MASQUERADE john@  on host "hamlet" will send all mails as john@hamlet
+# MASQUERADE percolator  will send mails as $username@percolator, e.g. fish@percolator
+# MASQUERADE herb@ert  will send all mails as herb@ert
+
+# Directly forward the mail to the SMARTHOST bypassing aliases and local delivery
+#NULLCLIENT

ansible/files/smartd.conf

@@ -0,0 +1,150 @@
+# Sample configuration file for smartd.  See man smartd.conf.
+
+# Home page is: http://www.smartmontools.org
+
+# smartd will re-read the configuration file if it receives a HUP
+# signal
+
+# The file gives a list of devices to monitor using smartd, with one
+# device per line. Text after a hash (#) is ignored, and you may use
+# spaces and tabs for white space. You may use '\' to continue lines.
+
+# You can usually identify which hard disks are on your system by
+# looking in /proc/ide and in /proc/scsi.
+
+# The word DEVICESCAN will cause any remaining lines in this
+# configuration file to be ignored: it tells smartd to scan for all
+# ATA and SCSI devices.  DEVICESCAN may be followed by any of the
+# Directives listed below, which will be applied to all devices that
+# are found.  Most users should comment out DEVICESCAN and explicitly
+# list the devices that they wish to monitor.
+#DEVICESCAN -d removable -n standby -m root -M exec /usr/share/smartmontools/smartd-runner
+DEVICESCAN -m alerts@seaturtle.pw -M test
+
+# Alternative setting to ignore temperature and power-on hours reports
+# in syslog.
+#DEVICESCAN -I 194 -I 231 -I 9
+
+# Alternative setting to report more useful raw temperature in syslog.
+#DEVICESCAN -R 194 -R 231 -I 9
+
+# Alternative setting to report raw temperature changes >= 5 Celsius
+# and min/max temperatures.
+#DEVICESCAN -I 194 -I 231 -I 9 -W 5
+
+# First ATA/SATA or SCSI/SAS disk.  Monitor all attributes, enable
+# automatic online data collection, automatic Attribute autosave, and
+# start a short self-test every day between 2-3am, and a long self test
+# Saturdays between 3-4am.
+#/dev/sda -a -o on -S on -s (S/../.././02|L/../../6/03)
+
+# Monitor SMART status, ATA Error Log, Self-test log, and track
+# changes in all attributes except for attribute 194
+#/dev/sdb -H -l error -l selftest -t -I 194
+
+# Monitor all attributes except normalized Temperature (usually 194),
+# but track Temperature changes >= 4 Celsius, report Temperatures
+# >= 45 Celsius and changes in Raw value of Reallocated_Sector_Ct (5).
+# Send mail on SMART failures or when Temperature is >= 55 Celsius.
+#/dev/sdc -a -I 194 -W 4,45,55 -R 5 -m admin@example.com
+
+# An ATA disk may appear as a SCSI device to the OS. If a SCSI to
+# ATA Translation (SAT) layer is between the OS and the device then
+# this can be flagged with the '-d sat' option. This situation may
+# become common with SATA disks in SAS and FC environments.
+# /dev/sda -a -d sat
+
+# A very silent check.  Only report SMART health status if it fails
+# But send an email in this case
+#/dev/sdc -H -C 0 -U 0 -m admin@example.com
+
+# First two SCSI disks.  This will monitor everything that smartd can
+# monitor.  Start extended self-tests Wednesdays between 6-7pm and
+# Sundays between 1-2 am
+#/dev/sda -d scsi -s L/../../3/18
+#/dev/sdb -d scsi -s L/../../7/01
+
+# Monitor 4 ATA disks connected to a 3ware 6/7/8000 controller which uses
+# the 3w-xxxx driver. Start long self-tests Sundays between 1-2, 2-3, 3-4, 
+# and 4-5 am.
+# NOTE: starting with the Linux 2.6 kernel series, the /dev/sdX interface
+# is DEPRECATED.  Use the /dev/tweN character device interface instead.
+# For example /dev/twe0, /dev/twe1, and so on.
+#/dev/sdc -d 3ware,0 -a -s L/../../7/01
+#/dev/sdc -d 3ware,1 -a -s L/../../7/02
+#/dev/sdc -d 3ware,2 -a -s L/../../7/03
+#/dev/sdc -d 3ware,3 -a -s L/../../7/04
+
+# Monitor 2 ATA disks connected to a 3ware 9000 controller which
+# uses the 3w-9xxx driver (Linux, FreeBSD). Start long self-tests Tuesdays
+# between 1-2 and 3-4 am.
+#/dev/twa0 -d 3ware,0 -a -s L/../../2/01
+#/dev/twa0 -d 3ware,1 -a -s L/../../2/03
+
+# Monitor 2 SATA (not SAS) disks connected to a 3ware 9000 controller which
+# uses the 3w-sas driver (Linux). Start long self-tests Tuesdays
+# between 1-2 and 3-4 am.
+# On FreeBSD /dev/tws0 should be used instead
+#/dev/twl0 -d 3ware,0 -a -s L/../../2/01
+#/dev/twl0 -d 3ware,1 -a -s L/../../2/03
+
+# Same as above for Windows. Option '-d 3ware,N' is not necessary,
+# disk (port) number is specified in device name.
+# NOTE: On Windows, DEVICESCAN works also for 3ware controllers.
+#/dev/hdc,0 -a -s L/../../2/01
+#/dev/hdc,1 -a -s L/../../2/03
+#
+# Monitor 2 disks connected to the first HP SmartArray controller which
+# uses the cciss driver. Start long tests on Sunday nights and short
+# self-tests every night and send errors to root
+#/dev/cciss/c0d0 -d cciss,0 -a -s (L/../../7/02|S/../.././02) -m root
+#/dev/cciss/c0d0 -d cciss,1 -a -s (L/../../7/03|S/../.././03) -m root
+
+# Monitor 3 ATA disks directly connected to a HighPoint RocketRAID. Start long
+# self-tests Sundays between 1-2, 2-3, and 3-4 am. 
+#/dev/sdd -d hpt,1/1 -a -s L/../../7/01
+#/dev/sdd -d hpt,1/2 -a -s L/../../7/02
+#/dev/sdd -d hpt,1/3 -a -s L/../../7/03
+
+# Monitor 2 ATA disks connected to the same PMPort which connected to the
+# HighPoint RocketRAID. Start long self-tests Tuesdays between 1-2 and 3-4 am
+#/dev/sdd -d hpt,1/4/1 -a -s L/../../2/01
+#/dev/sdd -d hpt,1/4/2 -a -s L/../../2/03
+
+# HERE IS A LIST OF DIRECTIVES FOR THIS CONFIGURATION FILE.
+# PLEASE SEE THE smartd.conf MAN PAGE FOR DETAILS
+#
+#   -d TYPE Set the device type: ata, scsi, marvell, removable, 3ware,N, hpt,L/M/N
+#   -T TYPE set the tolerance to one of: normal, permissive
+#   -o VAL  Enable/disable automatic offline tests (on/off)
+#   -S VAL  Enable/disable attribute autosave (on/off)
+#   -n MODE No check. MODE is one of: never, sleep, standby, idle
+#   -H      Monitor SMART Health Status, report if failed
+#   -l TYPE Monitor SMART log.  Type is one of: error, selftest
+#   -f      Monitor for failure of any 'Usage' Attributes
+#   -m ADD  Send warning email to ADD for -H, -l error, -l selftest, and -f
+#   -M TYPE Modify email warning behavior (see man page)
+#   -s REGE Start self-test when type/date matches regular expression (see man page)
+#   -p      Report changes in 'Prefailure' Normalized Attributes
+#   -u      Report changes in 'Usage' Normalized Attributes
+#   -t      Equivalent to -p and -u Directives
+#   -r ID   Also report Raw values of Attribute ID with -p, -u or -t
+#   -R ID   Track changes in Attribute ID Raw value with -p, -u or -t
+#   -i ID   Ignore Attribute ID for -f Directive
+#   -I ID   Ignore Attribute ID for -p, -u or -t Directive
+#   -C ID   Report if Current Pending Sector count non-zero
+#   -U ID   Report if Offline Uncorrectable count non-zero
+#   -W D,I,C Monitor Temperature D)ifference, I)nformal limit, C)ritical limit
+#   -v N,ST Modifies labeling of Attribute N (see man page)
+#   -a      Default: equivalent to -H -f -t -l error -l selftest -C 197 -U 198
+#   -F TYPE Use firmware bug workaround. Type is one of: none, samsung
+#   -P TYPE Drive-specific presets: use, ignore, show, showall
+#    #      Comment: text after a hash sign is ignored
+#    \      Line continuation character
+# Attribute ID is a decimal integer 1 <= ID <= 255
+# except for -C and -U, where ID = 0 turns them off.
+# All but -d, -m and -M Directives are only implemented for ATA devices
+#
+# If the test string DEVICESCAN is the first uncommented text
+# then smartd will scan for devices.
+# DEVICESCAN may be followed by any desired Directives.

ansible/handlers.yml

@@ -1,4 +1,18 @@
 ---
+- name: Enable weechat service
+  service:
+    name: weechat
+    enabled: yes
+
+- name: Re-export exportfs
+  command: exportfs -arv
+
+- name: Restart and enable smartd
+  service:
+    name: smartd
+    enabled: yes
+    state: restarted
+
 - name: Restart chrony service
   service:
     name: chrony
@@ -24,10 +38,3 @@
     name: zfs-zed
     state: restarted
 
-- name: Enable weechat service
-  service:
-    name: weechat
-    enabled: yes
-
-- name: Re-export exportfs
-  command: exportfs -arv

ansible/main.yml

@@ -13,6 +13,7 @@
           - apt-listchanges
           - chrony
           - curl
+          - dma
           - git
           - htop
           - iperf3
@@ -20,6 +21,7 @@
           - nmap
           - oidentd
           - rsync
+          - smartmontools
           - speedtest-cli
           - tmux
           - unattended-upgrades
@@ -95,6 +97,26 @@
         group: root
         mode: '0644'
 
+    - name: Configure dma
+      copy:
+        src: files/dma.conf
+        dest: /etc/dma/dma.conf
+        owner: root
+        group: mail
+        mode: '0640'
+
+    - debug:
+        msg: 'Manually configure /etc/dma/auth.conf'
+
+    - name: Configure smartd
+      copy:
+        src: files/smartd.conf
+        dest: /etc/smartd.conf
+        owner: root
+        group: root
+        mode: '0644'
+      notify: Restart and enable smartd
+
 ### Router
 ##- hosts: router
 ##  become: yes
@@ -124,8 +146,10 @@
         force_apt_get: yes
         update_cache: yes
 
-    # Manually do wireguard config https://wiki.debian.org/Wireguard
+    - debug:
-    # Manuall do beets config https://wiki.archlinux.org/index.php/Beets
+        msg:
+          - Manually do wireguard config https://wiki.debian.org/Wireguard
+          - Manuall do beets config https://wiki.archlinux.org/index.php/Beets
 
 # NFS core config
 # ASSUMES /bigdata IS CONFIGURED (make sure dir is 755)
@@ -134,26 +158,15 @@
   handlers:
     - import_tasks: handlers.yml
   tasks:
-    - name: Install zfs-zed, postfix, nfs-kernel-server
+    - name: Install zfs-zed, dma, and nfs-kernel-server
       apt:
         name:
+          - dma
           - nfs-kernel-server
-          - postfix
           - zfs-zed
         force_apt_get: yes
         update_cache: yes
 
-    - name: Configure postfix
-      copy:
-        src: files/bigdummy-main.cf
-        dest: /etc/postfix/main.cf
-        owner: root
-        group: root
-        mode: '0644'
-      notify: Restart postfix
-
-    # Manually set postfix password
-
     - name: Configure zfs-zed
       copy:
         src: files/zed.rc
@@ -163,12 +176,20 @@
         mode: '0644'
       notify: Restart zfs-zed
 
+    - name: Install weekly bigdata scrub cron job
+      cron:
+        name: 'Scrub bigdata zfs pool'
+        special_time: weekly
+        job: 'zpool scrub bigdata'
+        user: root
+
     - name: Install rclone
       apt:
         deb: https://github.com/rclone/rclone/releases/download/v1.49.2/rclone-v1.49.2-linux-amd64.deb
         force_apt_get: yes
 
-    # Manually configure rclone remote drive
+    - debug:
+        msg: Manually configure rclone remote drive
 
     - name: Export /bigdata
       copy:
@@ -233,5 +254,6 @@
         name: paul
         groups: docker
         append: yes
-    
+
-    # Clone docker repo to start services
+    - debug:
+        msg: Clone docker repo to start services