You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
2197 lines
114 KiB
2197 lines
114 KiB
#!/usr/bin/perl |
|
# |
|
# This software was created by Alteeve's Niche! Inc. and has been released under the terms of the GNU GPL |
|
# version 2. |
|
# |
|
# ScanCore Scan Agent for 'ipmitool' to query IPMI data. |
|
# |
|
# https://alteeve.com |
|
# |
|
# Exit Codes: |
|
# 0 - Success |
|
# 1 - Passed in host name was not found in the database. |
|
# 2 - Bad number of scan_ipmitool_value_uuid's returned for the given |
|
# |
|
# 255 - The host's UUID isn't in the hosts table yet, ScanCore itself hasn't been run. |
|
# |
|
# TODO: |
|
# - Set a health score for over/under-temp events. |
|
# - Don't bother scanning other hosts.... ScanCore does direct calls to decide if/when to reboot an offline |
|
# node. |
|
# - Decide if we should parse 'ipmitool sel list' |
|
# - Detect a hung BMC by trying to talk to ourselves and, if that fails, send 'ipmitool bmc reset cold'. |
|
# Possibly try pinging the IPMI from the peer as it is not always possible to ping our own interface when |
|
# the IPMI and eth device share the same physical connector. |
|
# - Update the string processing from the '!!x!name=a,value=b,units=c!!' method to the new method here: |
|
# https://alteeve.com/w/ScanCore#Unit_Parsing |
|
# - Change 'scan_ipmitool_value_uuid' to 'scan_ipmitool_value_uuid'. |
|
# - Monitor / Alert on RPM, wattage, voltage, etc |
|
# |
|
# - A PSU wattage dropping to '0 Watts', in conjunction with it's fan dropping to '0' RPMs, is the sign that |
|
# input power was lost and should set a health score of ~5. |
|
# |
|
# NOTE: |
|
# - Health values |
|
# - IPMI BMC - Hung = 10 |
|
# - Temperature - Critical = 2 |
|
# - Temperature - Warning = 1 |
|
# - Fan - Failed = 5 |
|
# - PSU - Lost Input = 5 |
|
=pod |
|
|
|
A Hung/crashed BMC will fail to reset with this: |
|
==== |
|
[root@nr-c03n01 ~]# time ipmitool bmc reset cold |
|
Get Device ID command failed: 0xff Unspecified error |
|
Sent cold reset command to MC |
|
|
|
real 3m52.860s |
|
user 0m0.000s |
|
sys 0m0.002s |
|
==== |
|
|
|
Seeing this, we need to ask the peer to power-cycle us (/shared/status/.node.helpme -> 'task = power_cycle') |
|
and set the health to 'warning'. We will call anvil-safe-stop. |
|
|
|
The peer, on seeing (/shared/status/.node.helpme -> 'task = power_cycle'), will start pinging the peer on the |
|
BCN and SN. Once there is no response, we will start a 60 second counter, then cut power to the PDUs for 60 |
|
seconds, then restore power. We will then start pinging the IPMI interface. Once it responds, we will wait 60 |
|
seconds and then try to power it back on. |
|
|
|
--------- |
|
|
|
Change/set thresholds: |
|
|
|
From: https://forums.freenas.org/index.php?threads/how-to-change-sensor-thresholds-with-ipmi-using-ipmitool.23571/ |
|
|
|
Lower Non-Recoverable |
|
Lower Critical |
|
Lower Non-Critical |
|
|
|
Upper Non-Critical |
|
Upper Critical |
|
Upper Non-Recoverable |
|
|
|
ipmitool sensor thresh "*sensor name*" lower *lnr* *lcr* *lnc* |
|
|
|
ipmitool sensor thresh "*sensor name*" upper *unc* *ucr* *unr* |
|
=cut |
|
|
|
use strict; |
|
use warnings; |
|
use Anvil::Tools; |
|
use Data::Dumper; |
|
use Socket; |
|
no warnings 'recursion'; |
|
|
|
# Disable buffering |
|
$| = 1; |
|
|
|
# Prevent a discrepency between UID/GID and EUID/EGID from throwing an error. |
|
$< = $>; |
|
$( = $); |
|
|
|
my $THIS_FILE = ($0 =~ /^.*\/(.*)$/)[0]; |
|
my $running_directory = ($0 =~ /^(.*?)\/$THIS_FILE$/)[0]; |
|
if (($running_directory =~ /^\./) && ($ENV{PWD})) |
|
{ |
|
$running_directory =~ s/^\./$ENV{PWD}/; |
|
} |
|
|
|
my $anvil = Anvil::Tools->new({log_level => 2, log_secure => 1}); |
|
$anvil->Log->level({set => 2}); |
|
$anvil->Log->secure({set => 1}); |
|
|
|
# Make sure we're running as 'root' |
|
# $< == real UID, $> == effective UID |
|
if (($< != 0) && ($> != 0)) |
|
{ |
|
# Not root |
|
print $anvil->Words->string({key => "error_0005"})."\n"; |
|
$anvil->nice_exit({exit_code => 1}); |
|
} |
|
|
|
# Here we store data and variables for this agent. |
|
$anvil->data->{'scan-ipmitool'} = { |
|
disable => 0, |
|
# It will be marked as 'clear' when the temperature drops this many °C below the |
|
# critical temperature. |
|
host_name => {}, |
|
alert_sort => 2, |
|
# These are used when no other limits are set for a given sensor. |
|
thresholds => { |
|
'default' => { |
|
high_warning => 50, |
|
high_critical => 55, |
|
low_warning => 5, |
|
low_critical => 0, |
|
jump => 10, |
|
### TODO: Some sensors define their hysteresis which we can read using: |
|
### ipmitool ... sensor get "Ambient" |
|
buffer => 2, |
|
weight => 1, |
|
}, |
|
### TODO: Support wild-card sensor names. |
|
# If the user wants to assign manual values for a given sensor, they can do |
|
# so by creating an entry hear where the key is the IPMI-returned sensor |
|
# name. |
|
#ie: |
|
# =========================================================================== |
|
#'Ambient' => { |
|
# high_warning => 50, |
|
# high_critical => 55, |
|
# low_warning => 5, |
|
# low_critical => 0, |
|
# jump => 5, |
|
# buffer => 2, |
|
# weight => 1, |
|
#}, |
|
# =========================================================================== |
|
# CPUs tend to jump around wildly under sudden load, so we extend their jump |
|
# range so we don't get spurious warnings all the time. |
|
'CPU' => { |
|
jump => 25, |
|
}, |
|
'CPU1' => { |
|
jump => 25, |
|
}, |
|
'CPU2' => { |
|
jump => 25, |
|
}, |
|
'CPU3' => { |
|
jump => 25, |
|
}, |
|
'CPU4' => { |
|
jump => 25, |
|
}, |
|
'CPU5' => { |
|
jump => 25, |
|
}, |
|
'CPU6' => { |
|
jump => 25, |
|
}, |
|
'CPU7' => { |
|
jump => 25, |
|
}, |
|
'CPU8' => { |
|
jump => 25, |
|
}, |
|
# The ROC on LSI controllers can just dramatically |
|
'RAID Controller' => { |
|
jump => 15, |
|
}, |
|
# On Dells, 'Temp (xxh)' change a lot, so we bump the jump. |
|
'Temp' => { |
|
jump => 30, |
|
}, |
|
}, |
|
# TODO: Remove this and have Striker pull the list of thermal sensors read in the |
|
# last $timestamp. |
|
offline_sensor_list => "Ambient,Systemboard", |
|
local_lock_active => 0, |
|
scanning_myself => 0, |
|
queries => [], |
|
health => { |
|
old => {}, |
|
new => {}, |
|
}, |
|
}; |
|
|
|
$anvil->Storage->read_config(); |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, 'print' => 1 , key => "log_0115", variables => { program => $THIS_FILE }}); |
|
|
|
# Read switches |
|
$anvil->data->{switches}{force} = 0; |
|
$anvil->data->{switches}{purge} = 0; |
|
$anvil->Get->switches; |
|
|
|
# If we're disabled and '--force' wasn't used, exit. |
|
if (($anvil->data->{scancore}{'scan-ipmitool'}{disable}) && (not $anvil->data->{switches}{force})) |
|
{ |
|
# Exit. |
|
$anvil->nice_exit({exit_code => 0}); |
|
} |
|
|
|
# Handle start-up tasks |
|
my $problem = $anvil->ScanCore->agent_startup({agent => $THIS_FILE}); |
|
if ($problem) |
|
{ |
|
$anvil->nice_exit({exit_code => 1}); |
|
} |
|
|
|
if ($anvil->data->{switches}{purge}) |
|
{ |
|
# This can be called when doing bulk-database purges. |
|
my $schema_file = $anvil->data->{path}{directories}{scan_agents}."/".$THIS_FILE."/".$THIS_FILE.".sql"; |
|
$anvil->Database->purge_data({ |
|
debug => 2, |
|
tables => $anvil->Database->get_tables_from_schema({schema_file => $schema_file}), |
|
}); |
|
$anvil->nice_exit({exit_code => 0}); |
|
} |
|
|
|
# This calls anvil-report-ipmi-details to find IPMI devices to scan. It also handles any user-defined IPMI |
|
# devices set in striker.conf. |
|
if (not find_ipmi_targets($anvil)) |
|
{ |
|
# No targets found. |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => "scan_ipmitool_message_0001"}); |
|
$anvil->nice_exit({exit_code => 1}); |
|
} |
|
|
|
# Query IPMI targets. Unreachable targets will simply be ignored. |
|
query_ipmi_targets($anvil); |
|
|
|
# Look for changes. |
|
find_changes($anvil); |
|
|
|
# Finally, process health weights. |
|
process_health($anvil); |
|
|
|
# Update the database |
|
$anvil->Database->insert_or_update_updated({updated_by => $THIS_FILE}); |
|
|
|
# Clean up and go away. |
|
$anvil->nice_exit({exit_code => 0}); |
|
|
|
|
|
############################################################################################################# |
|
# Functions # |
|
############################################################################################################# |
|
|
|
# This reads in all health wieghts previously set, alters ones as needed, INSERTs new ones and DELETEs old |
|
# ones. |
|
sub process_health |
|
{ |
|
my ($anvil) = @_; |
|
|
|
# This will hold our updates. |
|
$anvil->data->{'scan-ipmitool'}{queries} = []; |
|
|
|
# Read in the new ones |
|
foreach my $health_source_name (sort {$a cmp $b} keys %{$anvil->data->{'scan-ipmitool'}{health}{new}}) |
|
{ |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"health::new::$health_source_name" => $anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name}, |
|
}}); |
|
|
|
my $health_uuid = $anvil->Database->insert_or_update_health({ |
|
debug => 2, |
|
cache => $anvil->data->{'scan-ipmitool'}{queries}, |
|
health_host_uuid => $anvil->Get->host_uuid, |
|
health_agent_name => $THIS_FILE, |
|
health_source_name => $health_source_name, |
|
health_source_weight => $anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name}, |
|
}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_uuid => $health_uuid }}); |
|
|
|
# Delete the new old key, if it existed |
|
if ($anvil->data->{'scan-ipmitool'}{health}{old}{$health_source_name}) |
|
{ |
|
delete $anvil->data->{'scan-ipmitool'}{health}{old}{$health_source_name}; |
|
} |
|
} |
|
|
|
# Delete any old entries that are left. |
|
foreach my $health_source_name (sort {$a cmp $b} keys %{$anvil->data->{'scan-ipmitool'}{health}{old}}) |
|
{ |
|
# Well set the source name to 'DELETED'. |
|
my $health_uuid = $anvil->Database->insert_or_update_health({ |
|
debug => 2, |
|
cache => $anvil->data->{'scan-ipmitool'}{queries}, |
|
health_uuid => $anvil->data->{'scan-ipmitool'}{health}{old}{$health_source_name}{uuid}, |
|
'delete' => 1, |
|
}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_uuid => $health_uuid }}); |
|
} |
|
|
|
# Now commit the changes. |
|
$anvil->Database->write({query => $anvil->data->{'scan-ipmitool'}{queries}, source => $THIS_FILE, line => __LINE__}); |
|
|
|
return(0); |
|
} |
|
|
|
# This reads in the last scan data from one of the databases and compares it against the just-read data. If |
|
# anything changed, register an alert. |
|
sub find_changes |
|
{ |
|
my ($anvil) = @_; |
|
|
|
# Loop through each host_name |
|
foreach my $host_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}}) |
|
{ |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { host_name => $host_name }}); |
|
|
|
# This returns the number of read sensors already in the DB for this host_name recorded by us |
|
# previously. |
|
if (read_last_scan($anvil, $host_name)) |
|
{ |
|
### Existing host_name, UPDATE or INSERT as needed. |
|
foreach my $scan_ipmitool_sensor_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}}) |
|
{ |
|
# Put the new values into variables |
|
my $new_scan_ipmitool_value_sensor_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $new_scan_ipmitool_sensor_units = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units}; |
|
my $new_scan_ipmitool_sensor_status = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status}; |
|
my $new_scan_ipmitool_sensor_high_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $new_scan_ipmitool_sensor_high_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $new_scan_ipmitool_sensor_low_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $new_scan_ipmitool_sensor_low_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
new_scan_ipmitool_sensor_units => $new_scan_ipmitool_sensor_units, |
|
new_scan_ipmitool_sensor_status => $new_scan_ipmitool_sensor_status, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_warning, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
# If the new value is 'na', we failed to read it. Skip. |
|
if ($new_scan_ipmitool_value_sensor_value eq "na") |
|
{ |
|
delete $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
next; |
|
} |
|
|
|
### NOTE: These were added to debug duplicate scan_ipmitool_values entries. |
|
if (not $new_scan_ipmitool_sensor_units) |
|
{ |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor => $scan_ipmitool_sensor_name, |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 1, key => "scan_ipmitool_message_0002", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "notice", message => "scan_ipmitool_message_0002", variables => $variables, set_by => $THIS_FILE, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
next; |
|
} |
|
if (not $new_scan_ipmitool_value_sensor_value) |
|
{ |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor => $scan_ipmitool_sensor_name, |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 1, key => "scan_ipmitool_message_0003", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "notice", message => "scan_ipmitool_message_0003", variables => $variables, set_by => $THIS_FILE, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
next; |
|
} |
|
|
|
# If the value is "" and it's a digit-based value, switch it to '0' |
|
if ((($new_scan_ipmitool_sensor_units eq "C") or ($new_scan_ipmitool_sensor_units eq "F") or ($new_scan_ipmitool_sensor_units eq "RPM")) && ($new_scan_ipmitool_value_sensor_value eq "")) |
|
{ |
|
$new_scan_ipmitool_value_sensor_value = 0; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value }}); |
|
} |
|
|
|
# Have I seen this sensor before? |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"ref(sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name})" => ref($anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}), |
|
}}); |
|
if (ref($anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name})) |
|
{ |
|
### Existing record, update it if needed. |
|
# Put the old values into variables |
|
my $scan_ipmitool_uuid = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_uuid}; |
|
my $old_scan_ipmitool_value_sensor_value = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $old_scan_ipmitool_sensor_units = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units}; |
|
my $old_scan_ipmitool_sensor_status = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status}; |
|
my $old_scan_ipmitool_sensor_high_critical = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $old_scan_ipmitool_sensor_high_warning = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $old_scan_ipmitool_sensor_low_critical = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $old_scan_ipmitool_sensor_low_warning = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
scan_ipmitool_uuid => $scan_ipmitool_uuid, |
|
old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value, |
|
old_scan_ipmitool_sensor_units => $old_scan_ipmitool_sensor_units, |
|
old_scan_ipmitool_sensor_status => $old_scan_ipmitool_sensor_status, |
|
old_scan_ipmitool_sensor_high_critical => $old_scan_ipmitool_sensor_high_critical, |
|
old_scan_ipmitool_sensor_high_warning => $old_scan_ipmitool_sensor_high_warning, |
|
old_scan_ipmitool_sensor_low_critical => $old_scan_ipmitool_sensor_low_critical, |
|
old_scan_ipmitool_sensor_low_warning => $old_scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
# If the value is "" and it's a digit-based value, switch it to '0' |
|
if ((($old_scan_ipmitool_sensor_units eq "C") or ($old_scan_ipmitool_sensor_units eq "F") or ($old_scan_ipmitool_sensor_units eq "RPM")) && ($old_scan_ipmitool_value_sensor_value eq "")) |
|
{ |
|
$old_scan_ipmitool_value_sensor_value = 0; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value }}); |
|
} |
|
|
|
# In some odd cases, there is no old sensor value |
|
$old_scan_ipmitool_value_sensor_value = "" if not defined $old_scan_ipmitool_value_sensor_value; |
|
|
|
# These will be used in alert messages, if needed. |
|
my $sensor_name = "name=$scan_ipmitool_sensor_name:units=$new_scan_ipmitool_sensor_units"; |
|
my $new_sensor_value = "value=$new_scan_ipmitool_value_sensor_value:units=$new_scan_ipmitool_sensor_units"; |
|
my $old_sensor_value = "value=$old_scan_ipmitool_value_sensor_value:units=$old_scan_ipmitool_sensor_units"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
sensor_name => $sensor_name, |
|
new_sensor_value => $new_sensor_value, |
|
old_sensor_value => $old_sensor_value, |
|
}}); |
|
|
|
### TODO: We can remove this, I think. |
|
### Look for changes |
|
# NOTE: If the new sensor has a state of 'na' and the old state |
|
# wasn't 'na', we ignore it. It happens not uncommonly and it's |
|
# never been an indication of a real problem before. |
|
# if ($new_scan_ipmitool_sensor_status eq "na") |
|
# { |
|
# # This is usually harmless, so we simple log this and move on |
|
# $anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 1, key => "scan_ipmitool_log_0004", variables => { sensor_name => $scan_ipmitool_sensor_name }}); |
|
# |
|
# # We loop out now because the rest of the values will look |
|
# # really bad (ie: temps down to 0c) and we don't want to |
|
# # trigger preventative actions on bad data. |
|
# delete $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
# next; |
|
# } |
|
# elsif (($new_scan_ipmitool_sensor_status ne "na") && ($old_scan_ipmitool_sensor_status eq "na")) |
|
# { |
|
# # It disappeared in a previous sweep, now it's back. We |
|
# # continue normal processing to handle those rare occassions |
|
# # where a sensor was lost back when we cared, and returned |
|
# # after updating to this version when we stopped caring. |
|
# $anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 1, key => "scan_ipmitool_log_0005", variables => { sensor_name => $scan_ipmitool_sensor_name }}); |
|
# } |
|
|
|
# Sensor value: |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value, |
|
}}); |
|
if ($new_scan_ipmitool_value_sensor_value ne $old_scan_ipmitool_value_sensor_value) |
|
{ |
|
# Update (no surprise ...) |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
sensor_name => $sensor_name, |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value, |
|
}}); |
|
my $query = " |
|
UPDATE |
|
scan_ipmitool_values |
|
SET |
|
scan_ipmitool_value_sensor_value = ".$anvil->Database->quote($new_scan_ipmitool_value_sensor_value).", |
|
modified_date = ".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
WHERE |
|
scan_ipmitool_value_scan_ipmitool_uuid = ".$anvil->Database->quote($scan_ipmitool_uuid)." |
|
; |
|
"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
### NOTE: These are set in 'process_temperature_change()' as |
|
### well, so change the values there if you change it |
|
### here, too. |
|
# This is an info-level alert, provided it is not gone above |
|
# or below tolerances. |
|
my $level = "info"; |
|
my $message_key = "scan_ipmitool_message_0004"; |
|
|
|
# If this is a temperature, see if we need to trigger an |
|
# alarm and set/clear the 'temperature' table entry. |
|
# TODO: For the rest of the sensors, we just log the changes. |
|
# If a sensor goes bad, for now we'll catch errors on |
|
# the sensor status change. We'll add better checks |
|
# later. |
|
if ($new_scan_ipmitool_sensor_units eq "C") |
|
{ |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
sensor_name => $sensor_name, |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value, |
|
}}); |
|
($level, $message_key) = process_temperature_change($anvil, $host_name, $scan_ipmitool_sensor_name); |
|
|
|
my $variables = { |
|
sensor_name => $sensor_name, |
|
new_sensor_value => $new_sensor_value, |
|
new_sensor_status => $new_scan_ipmitool_sensor_status, |
|
new_high_critical => $new_scan_ipmitool_sensor_high_critical eq "" ? "--" : $new_scan_ipmitool_sensor_high_critical, |
|
new_low_critical => $new_scan_ipmitool_sensor_low_critical eq "" ? "--" : $new_scan_ipmitool_sensor_low_critical, |
|
new_high_warning => $new_scan_ipmitool_sensor_high_warning eq "" ? "--" : $new_scan_ipmitool_sensor_high_warning, |
|
new_low_warning => $new_scan_ipmitool_sensor_low_warning eq "" ? "--" : $new_scan_ipmitool_sensor_low_warning, |
|
old_sensor_value => $old_sensor_value, |
|
old_sensor_status => $old_scan_ipmitool_sensor_status, |
|
old_high_critical => $old_scan_ipmitool_sensor_high_critical eq "" ? "--" : $old_scan_ipmitool_sensor_high_critical, |
|
old_low_critical => $old_scan_ipmitool_sensor_low_critical eq "" ? "--" : $old_scan_ipmitool_sensor_low_critical, |
|
old_high_warning => $old_scan_ipmitool_sensor_high_warning eq "" ? "--" : $old_scan_ipmitool_sensor_high_warning, |
|
old_low_warning => $old_scan_ipmitool_sensor_low_warning eq "" ? "--" : $old_scan_ipmitool_sensor_low_warning, |
|
}; |
|
my $sort_position = (($level eq "warning") or ($level eq "critical")) ? 1 : $anvil->data->{'scan-ipmitool'}{alert_sort}++; |
|
my $log_level = (($level eq "warning") or ($level eq "critical")) ? 1 : 2; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => $log_level, key => $message_key, variables => $variables}); |
|
$anvil->Alert->register({alert_level => $level, message => $message_key, variables => $variables, set_by => $THIS_FILE, sort_position => $sort_position}); |
|
} |
|
else |
|
{ |
|
# TODO: Add the checks of variables against the |
|
# high/low warning/critical thresholds here |
|
# (like RPM, wattage, voltage, etc). |
|
my $variables = { |
|
sensor_name => $sensor_name, |
|
new_sensor_value => $new_sensor_value, |
|
old_sensor_value => $old_sensor_value |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => $message_key, variables => $variables}); |
|
$anvil->Alert->register({alert_level => $level, message => $message_key, variables => $variables, set_by => $THIS_FILE, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
} |
|
} |
|
else |
|
{ |
|
# No change. |
|
$anvil->Log->entry({log_level => 2, message_key => "scancore_log_0047", file => $THIS_FILE, line => __LINE__}); |
|
} |
|
|
|
# Everything else |
|
if (($new_scan_ipmitool_sensor_units ne $old_scan_ipmitool_sensor_units) or |
|
($new_scan_ipmitool_sensor_status ne $old_scan_ipmitool_sensor_status) or |
|
($new_scan_ipmitool_sensor_high_critical ne $old_scan_ipmitool_sensor_high_critical) or |
|
($new_scan_ipmitool_sensor_high_warning ne $old_scan_ipmitool_sensor_high_warning) or |
|
($new_scan_ipmitool_sensor_low_critical ne $old_scan_ipmitool_sensor_low_critical) or |
|
($new_scan_ipmitool_sensor_low_warning ne $old_scan_ipmitool_sensor_low_warning)) |
|
{ |
|
# Huh, interesting. Well, update |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
new_scan_ipmitool_sensor_units => $new_scan_ipmitool_sensor_units, |
|
new_scan_ipmitool_sensor_status => $new_scan_ipmitool_sensor_status, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_warning, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
old_scan_ipmitool_sensor_units => $old_scan_ipmitool_sensor_units, |
|
old_scan_ipmitool_sensor_status => $old_scan_ipmitool_sensor_status, |
|
old_scan_ipmitool_sensor_high_critical => $old_scan_ipmitool_sensor_high_critical, |
|
old_scan_ipmitool_sensor_high_warning => $old_scan_ipmitool_sensor_high_warning, |
|
old_scan_ipmitool_sensor_low_critical => $old_scan_ipmitool_sensor_low_critical, |
|
old_scan_ipmitool_sensor_low_warning => $old_scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
### NOTE: These were added to debug duplicate scan_ipmitool_values entries. |
|
if (not $new_scan_ipmitool_sensor_units) |
|
{ |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor => $scan_ipmitool_sensor_name, |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => "scan_ipmitool_message_0015", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "notice", message => "scan_ipmitool_message_0015", variables => $variables, set_by => $THIS_FILE, show_header => 0, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
next; |
|
} |
|
|
|
my $query = " |
|
UPDATE |
|
scan_ipmitool |
|
SET |
|
scan_ipmitool_sensor_units = ".$anvil->Database->quote($new_scan_ipmitool_sensor_units).", |
|
scan_ipmitool_sensor_status = ".$anvil->Database->quote($new_scan_ipmitool_sensor_status).", |
|
scan_ipmitool_sensor_high_critical = ".$anvil->Database->quote($new_scan_ipmitool_sensor_high_critical).", |
|
scan_ipmitool_sensor_high_warning = ".$anvil->Database->quote($new_scan_ipmitool_sensor_high_warning).", |
|
scan_ipmitool_sensor_low_critical = ".$anvil->Database->quote($new_scan_ipmitool_sensor_low_critical).", |
|
scan_ipmitool_sensor_low_warning = ".$anvil->Database->quote($new_scan_ipmitool_sensor_low_warning).", |
|
modified_date = ".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
WHERE |
|
scan_ipmitool_sensor_host = ".$anvil->Database->quote($host_name)." |
|
AND |
|
scan_ipmitool_uuid = ".$anvil->Database->quote($scan_ipmitool_uuid)." |
|
;"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
# If this is a status change, set a 'warning' level alert |
|
# unless the change is to/from 'ns'. |
|
my $level = "notice"; |
|
my $message_key = "scan_ipmitool_message_0016"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
if (($new_scan_ipmitool_sensor_status ne $old_scan_ipmitool_sensor_status) && |
|
($new_scan_ipmitool_sensor_status ne "ns") && |
|
($old_scan_ipmitool_sensor_status ne "ns")) |
|
{ |
|
$level = "warning"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { level => $level }}); |
|
} |
|
my $variables = { |
|
sensor_name => $sensor_name, |
|
new_sensor_value => $new_sensor_value, |
|
old_sensor_value => $old_sensor_value, |
|
new_sensor_status => $new_scan_ipmitool_sensor_status, |
|
old_sensor_status => $old_scan_ipmitool_sensor_status, |
|
new_high_critical => $new_scan_ipmitool_sensor_high_critical eq "" ? "--" : $new_scan_ipmitool_sensor_high_critical." ".$new_scan_ipmitool_sensor_units, |
|
new_high_warning => $new_scan_ipmitool_sensor_high_warning eq "" ? "--" : $new_scan_ipmitool_sensor_high_warning." ".$new_scan_ipmitool_sensor_units, |
|
new_low_critical => $new_scan_ipmitool_sensor_low_critical eq "" ? "--" : $new_scan_ipmitool_sensor_low_critical." ".$new_scan_ipmitool_sensor_units, |
|
new_low_warning => $new_scan_ipmitool_sensor_low_warning eq "" ? "--" : $new_scan_ipmitool_sensor_low_warning." ".$new_scan_ipmitool_sensor_units, |
|
old_high_critical => $old_scan_ipmitool_sensor_high_critical eq "" ? "--" : $old_scan_ipmitool_sensor_high_critical." ".$old_scan_ipmitool_sensor_units, |
|
old_high_warning => $old_scan_ipmitool_sensor_high_warning eq "" ? "--" : $old_scan_ipmitool_sensor_high_warning." ".$old_scan_ipmitool_sensor_units, |
|
old_low_critical => $old_scan_ipmitool_sensor_low_critical eq "" ? "--" : $old_scan_ipmitool_sensor_low_critical." ".$old_scan_ipmitool_sensor_units, |
|
old_low_warning => $old_scan_ipmitool_sensor_low_warning eq "" ? "--" : $old_scan_ipmitool_sensor_low_warning." ".$old_scan_ipmitool_sensor_units, |
|
}; |
|
|
|
my $sort_position = (($level eq "warning") or ($level eq "critical")) ? 1 : $anvil->data->{'scan-ipmitool'}{alert_sort}++; |
|
my $log_level = (($level eq "warning") or ($level eq "critical")) ? 1 : 2; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => $log_level, key => $message_key, variables => $variables}); |
|
$anvil->Alert->register({alert_level => $level, message => $message_key, variables => $variables, set_by => $THIS_FILE, sort_position => $sort_position}); |
|
} |
|
|
|
# Delete the old key so that I can check to see what sensors |
|
# vanished. |
|
delete $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
} |
|
else |
|
{ |
|
### NOTE: If the new value is 'na', we ignore it as it is likely a |
|
### sensor that doesn't actually exist. |
|
if ($anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value} eq "") |
|
{ |
|
# Ignore it. |
|
$anvil->Log->entry({log_level => 3, message_key => "scan_ipmitool_log_0005", variables => { sensor_name => $scan_ipmitool_sensor_name }, file => $THIS_FILE, line => __LINE__}); |
|
delete $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
next; |
|
} |
|
|
|
### New record, INSERT it and sent an 'notice' level alert. |
|
# Generate a new UUID for this ipmi target. |
|
my $scan_ipmitool_uuid = $anvil->Get->uuid(); |
|
|
|
# Record the new UUID |
|
$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_uuid} = $scan_ipmitool_uuid; |
|
|
|
### NOTE: These were added to debug duplicate scan_ipmitool_values entries. |
|
if (not $new_scan_ipmitool_sensor_units) |
|
{ |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor => $scan_ipmitool_sensor_name, |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => "scan_ipmitool_message_0017", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "notice", message => "scan_ipmitool_message_0017", variables => $variables, set_by => $THIS_FILE, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
next; |
|
} |
|
if (not $new_scan_ipmitool_value_sensor_value) |
|
{ |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor => $scan_ipmitool_sensor_name, |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => "scan_ipmitool_message_0018", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "notice", message => "scan_ipmitool_message_0018", variables => $variables, set_by => $THIS_FILE, sort_position => $anvil->data->{'scan-ipmitool'}{alert_sort}++}); |
|
next; |
|
} |
|
|
|
# Save the new sensor. |
|
my $query = " |
|
INSERT INTO |
|
scan_ipmitool |
|
( |
|
scan_ipmitool_uuid, |
|
scan_ipmitool_host_uuid, |
|
scan_ipmitool_sensor_host, |
|
scan_ipmitool_sensor_name, |
|
scan_ipmitool_sensor_units, |
|
scan_ipmitool_sensor_status, |
|
scan_ipmitool_sensor_high_critical, |
|
scan_ipmitool_sensor_high_warning, |
|
scan_ipmitool_sensor_low_critical, |
|
scan_ipmitool_sensor_low_warning, |
|
modified_date |
|
) VALUES ( |
|
".$anvil->Database->quote($scan_ipmitool_uuid).", |
|
".$anvil->Database->quote($anvil->Get->host_uuid).", |
|
".$anvil->Database->quote($host_name).", |
|
".$anvil->Database->quote($scan_ipmitool_sensor_name).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_units).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_status).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_high_critical).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_high_warning).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_low_critical).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_low_warning).", |
|
".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
);"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
# Now INSERT the sensor value. |
|
my $scan_ipmitool_value_uuid = $anvil->Get->uuid(); |
|
$query = " |
|
INSERT INTO |
|
scan_ipmitool_values |
|
( |
|
scan_ipmitool_value_uuid, |
|
scan_ipmitool_value_host_uuid, |
|
scan_ipmitool_value_scan_ipmitool_uuid, |
|
scan_ipmitool_value_sensor_value, |
|
modified_date |
|
) VALUES ( |
|
".$anvil->Database->quote($scan_ipmitool_value_uuid).", |
|
".$anvil->Database->quote($anvil->Get->host_uuid).", |
|
".$anvil->Database->quote($scan_ipmitool_uuid).", |
|
".$anvil->Database->quote($new_scan_ipmitool_value_sensor_value).", |
|
".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
);"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
my $sensor_name = "name=".$scan_ipmitool_sensor_name.":units=".$new_scan_ipmitool_sensor_units; |
|
my $sensor_value = "value=".$new_scan_ipmitool_value_sensor_value.":units=".$new_scan_ipmitool_sensor_units; |
|
my $message_key = "scan_ipmitool_message_0019"; |
|
my $level = "notice"; |
|
my $variables = { |
|
host_name => $host_name, |
|
sensor_name => $sensor_name, |
|
sensor_value => $sensor_value, |
|
sensor_status => $new_scan_ipmitool_sensor_status, |
|
high_critical => $new_scan_ipmitool_sensor_high_critical eq "" ? "--" : $new_scan_ipmitool_sensor_high_critical." ".$new_scan_ipmitool_sensor_units, |
|
high_warning => $new_scan_ipmitool_sensor_high_warning eq "" ? "--" : $new_scan_ipmitool_sensor_high_warning." ".$new_scan_ipmitool_sensor_units, |
|
low_critical => $new_scan_ipmitool_sensor_low_critical eq "" ? "--" : $new_scan_ipmitool_sensor_low_critical." ".$new_scan_ipmitool_sensor_units, |
|
low_warning => $new_scan_ipmitool_sensor_low_warning eq "" ? "--" : $new_scan_ipmitool_sensor_low_warning." ".$new_scan_ipmitool_sensor_units, |
|
}; |
|
|
|
if ($new_scan_ipmitool_sensor_status ne "ok") |
|
{ |
|
# Alert cleared. |
|
$message_key = "scan_ipmitool_message_0020"; |
|
$level = "warning"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
message_key => $message_key, |
|
level => $level, |
|
}}); |
|
} |
|
|
|
my $sort_position = $level eq "warning" ? 1 : $anvil->data->{'scan-ipmitool'}{alert_sort}++; |
|
my $log_level = $level eq "warning" ? 1 : 2; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => $log_level, key => $message_key, variables => $variables}); |
|
$anvil->Alert->register({alert_level => $level, message => $message_key, variables => $variables, set_by => $THIS_FILE, sort_position => $sort_position}); |
|
} |
|
} |
|
} |
|
else |
|
{ |
|
# New host_name, INSERT everything. |
|
foreach my $scan_ipmitool_sensor_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}}) |
|
{ |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name }}); |
|
|
|
### NOTE: If the new value is 'na', we ignore it as it is likely a sensor |
|
### that doesn't actually exist. |
|
if ($anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value} eq "") |
|
{ |
|
# Ignore it. |
|
$anvil->Log->entry({log_level => 3, message_key => "scan_ipmitool_log_0005", variables => { sensor_name => $scan_ipmitool_sensor_name }, file => $THIS_FILE, line => __LINE__}); |
|
delete $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
next; |
|
} |
|
|
|
# Generate the UUID. |
|
my $scan_ipmitool_uuid = $anvil->Get->uuid() or $anvil->Alert->error({title_key => "error_title_0020", message_key => "error_message_0024", code => 2, file => $THIS_FILE, line => __LINE__}); |
|
|
|
# Record it. |
|
$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_uuid} = $scan_ipmitool_uuid; |
|
|
|
my $new_scan_ipmitool_value_sensor_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $new_scan_ipmitool_sensor_units = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units}; |
|
my $new_scan_ipmitool_sensor_status = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status}; |
|
my $new_scan_ipmitool_sensor_high_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $new_scan_ipmitool_sensor_high_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $new_scan_ipmitool_sensor_low_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $new_scan_ipmitool_sensor_low_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
scan_ipmitool_uuid => $scan_ipmitool_uuid, |
|
new_scan_ipmitool_sensor_units => $new_scan_ipmitool_sensor_units, |
|
new_scan_ipmitool_sensor_status => $new_scan_ipmitool_sensor_status, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_warning, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
# If the new value is 'na', we failed to read it. Skip. |
|
if ($new_scan_ipmitool_value_sensor_value eq "na") |
|
{ |
|
delete $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}; |
|
next; |
|
} |
|
|
|
### TODO: Make this ia log entry |
|
die "No IPMI units for sensor: [".$scan_ipmitool_sensor_name."]." if not $new_scan_ipmitool_sensor_units; |
|
die "No IPMI value for sensor: [".$new_scan_ipmitool_value_sensor_value."]." if not $new_scan_ipmitool_value_sensor_value; |
|
|
|
# If the value is "" and it's a digit-based value, switch it to '0' |
|
if ((($new_scan_ipmitool_sensor_units eq "C") or ($new_scan_ipmitool_sensor_units eq "F") or ($new_scan_ipmitool_sensor_units eq "RPM")) && ($new_scan_ipmitool_value_sensor_value eq "")) |
|
{ |
|
$new_scan_ipmitool_value_sensor_value = 0; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value }}); |
|
} |
|
|
|
my $query = " |
|
INSERT INTO |
|
scan_ipmitool |
|
( |
|
scan_ipmitool_uuid, |
|
scan_ipmitool_host_uuid, |
|
scan_ipmitool_sensor_name, |
|
scan_ipmitool_sensor_host, |
|
scan_ipmitool_sensor_units, |
|
scan_ipmitool_sensor_status, |
|
scan_ipmitool_sensor_high_critical, |
|
scan_ipmitool_sensor_high_warning, |
|
scan_ipmitool_sensor_low_critical, |
|
scan_ipmitool_sensor_low_warning, |
|
modified_date |
|
) VALUES ( |
|
".$anvil->Database->quote($scan_ipmitool_uuid).", |
|
".$anvil->Database->quote($anvil->Get->host_uuid).", |
|
".$anvil->Database->quote($scan_ipmitool_sensor_name).", |
|
".$anvil->Database->quote($host_name).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_units).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_status).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_high_critical).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_high_warning).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_low_critical).", |
|
".$anvil->Database->quote($new_scan_ipmitool_sensor_low_warning).", |
|
".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
);"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
# Now INSERT the sensor value. |
|
my $scan_ipmitool_value_uuid = $anvil->Get->uuid(); |
|
$query = " |
|
INSERT INTO |
|
scan_ipmitool_values |
|
( |
|
scan_ipmitool_value_uuid, |
|
scan_ipmitool_value_host_uuid, |
|
scan_ipmitool_value_scan_ipmitool_uuid, |
|
scan_ipmitool_value_sensor_value, |
|
modified_date |
|
) VALUES ( |
|
".$anvil->Database->quote($scan_ipmitool_value_uuid).", |
|
".$anvil->Database->quote($anvil->Get->host_uuid).", |
|
".$anvil->Database->quote($scan_ipmitool_uuid).", |
|
".$anvil->Database->quote($new_scan_ipmitool_value_sensor_value).", |
|
".$anvil->Database->quote($anvil->data->{sys}{database}{timestamp})." |
|
);"; |
|
$query =~ s/'NULL'/NULL/g; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
push @{$anvil->data->{'scan-ipmitool'}{queries}}, $query; |
|
|
|
# We need to let ScanCore translate the sensor data into a string for each |
|
# user and their prefered language and units. As such, we're going to use a |
|
# couple special variable strings for this. |
|
my $sensor_name = "name=".$scan_ipmitool_sensor_name.":units=".$new_scan_ipmitool_sensor_units; |
|
my $sensor_value = "value=".$new_scan_ipmitool_value_sensor_value.":units=".$new_scan_ipmitool_sensor_units; |
|
|
|
# If the sensor is not 'ok', set a warning level alert. |
|
my $level = "notice"; |
|
my $message_key = "scan_ipmitool_message_0019"; |
|
if ($new_scan_ipmitool_sensor_status ne "ok") |
|
{ |
|
$level = "warning"; |
|
$message_key = "scan_ipmitool_message_0020"; |
|
} |
|
|
|
my $variables = { |
|
host_name => $host_name, |
|
sensor_name => $scan_ipmitool_sensor_name, |
|
sensor_value => $sensor_value, |
|
sensor_status => $new_scan_ipmitool_sensor_status, |
|
high_critical => $new_scan_ipmitool_sensor_high_critical eq "" ? "--" : $new_scan_ipmitool_sensor_high_critical." ".$new_scan_ipmitool_sensor_units, |
|
high_warning => $new_scan_ipmitool_sensor_high_warning eq "" ? "--" : $new_scan_ipmitool_sensor_high_warning." ".$new_scan_ipmitool_sensor_units, |
|
low_critical => $new_scan_ipmitool_sensor_low_critical eq "" ? "--" : $new_scan_ipmitool_sensor_low_critical." ".$new_scan_ipmitool_sensor_units, |
|
low_warning => $new_scan_ipmitool_sensor_low_warning eq "" ? "--" : $new_scan_ipmitool_sensor_low_warning." ".$new_scan_ipmitool_sensor_units, |
|
}; |
|
my $sort_position = $level eq "warning" ? 1 : $anvil->data->{'scan-ipmitool'}{alert_sort}++; |
|
my $log_level = $level eq "warning" ? 1 : 2; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => $log_level, key => $message_key, variables => $variables}); |
|
$anvil->Alert->register({alert_level => $level, message => $message_key, variables => $variables, set_by => $THIS_FILE, sort_position => $sort_position}); |
|
} |
|
} |
|
|
|
# If I am scanning myself and if I see problems, I will set the health accordingly. |
|
if (($host_name eq $anvil->Get->host_name) or ($host_name eq $anvil->Get->short_host_name)) |
|
{ |
|
$anvil->data->{sys}{scanning_myself} = 1; |
|
} |
|
else |
|
{ |
|
$anvil->data->{sys}{scanning_myself} = 0; |
|
} |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { "sys::scanning_myself" => $anvil->data->{sys}{scanning_myself} }}); |
|
|
|
# Now commit the changes. |
|
$anvil->Database->write({debug => 2, query => $anvil->data->{'scan-ipmitool'}{queries}, source => $THIS_FILE, line => __LINE__}); |
|
$anvil->data->{'scan-ipmitool'}{queries} = []; |
|
|
|
### Now add, update and delete 'temperature' entries. |
|
process_temperature($anvil, $host_name); |
|
|
|
# Now look for any sensors that are in a bad state and set the health accordingly. |
|
check_sensor_health($anvil, $host_name); |
|
} |
|
|
|
return(0); |
|
} |
|
|
|
# This looks at various sensors, except temperature (handled in process_temperature() below) and sets the |
|
# health table as needed for sensors out of scope. |
|
sub check_sensor_health |
|
{ |
|
my ($anvil, $host_name) = @_; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { host_name => $host_name }}); |
|
|
|
foreach my $scan_ipmitool_sensor_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}}) |
|
{ |
|
# Put the new values into variables |
|
my $scan_ipmitool_value_sensor_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $scan_ipmitool_sensor_units = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units}; |
|
my $scan_ipmitool_sensor_status = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status}; |
|
my $scan_ipmitool_sensor_high_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $scan_ipmitool_sensor_high_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $scan_ipmitool_sensor_low_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $scan_ipmitool_sensor_low_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
scan_ipmitool_value_sensor_value => $scan_ipmitool_value_sensor_value, |
|
scan_ipmitool_sensor_units => $scan_ipmitool_sensor_units, |
|
scan_ipmitool_sensor_status => $scan_ipmitool_sensor_status, |
|
scan_ipmitool_sensor_high_critical => $scan_ipmitool_sensor_high_critical, |
|
scan_ipmitool_sensor_high_warning => $scan_ipmitool_sensor_high_warning, |
|
scan_ipmitool_sensor_low_critical => $scan_ipmitool_sensor_low_critical, |
|
scan_ipmitool_sensor_low_warning => $scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
if ((lc($scan_ipmitool_sensor_units) eq "c") or (lc($scan_ipmitool_sensor_units) eq "f")) |
|
{ |
|
# Temperatures will be handled in process_temperature(). |
|
next; |
|
} |
|
if ($scan_ipmitool_sensor_status ne "ok") |
|
{ |
|
my $health_source_name = $scan_ipmitool_sensor_units.":".$scan_ipmitool_sensor_name; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_source_name => $health_source_name }}); |
|
if (lc($scan_ipmitool_sensor_units) eq "v") |
|
{ |
|
$health_source_name = "voltage:".$scan_ipmitool_sensor_name; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_source_name => $health_source_name }}); |
|
} |
|
elsif (lc($scan_ipmitool_sensor_units) eq "w") |
|
{ |
|
$health_source_name = "wattage:".$scan_ipmitool_sensor_name; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_source_name => $health_source_name }}); |
|
} |
|
elsif (lc($scan_ipmitool_sensor_units) eq "rpm") |
|
{ |
|
$health_source_name = "fan:".$scan_ipmitool_sensor_name; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_source_name => $health_source_name }}); |
|
} |
|
elsif ($scan_ipmitool_sensor_units eq "%") |
|
{ |
|
$health_source_name = "percentage:".$scan_ipmitool_sensor_name; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { health_source_name => $health_source_name }}); |
|
} |
|
|
|
# Record it, if we're scanning ourselves. |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { "sys::scanning_myself" => $anvil->data->{sys}{scanning_myself} }}); |
|
if ($anvil->data->{sys}{scanning_myself}) |
|
{ |
|
# Set this to the user's requested weight, if set. Otherwise, use the default. |
|
my $weight = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{weight}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { weight => $weight }}); |
|
if (exists $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}) |
|
{ |
|
# If it a number? |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::weight" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}, |
|
}}); |
|
if (($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight} =~ /^\d+$/) or ($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight} =~ /^\d+\.\d+$/)) |
|
{ |
|
$weight = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { weight => $weight }}); |
|
} |
|
} |
|
|
|
# Default to '1' if not set. |
|
$weight = 1 if not $weight; |
|
|
|
$anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name} = $weight; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"health::new::$health_source_name" => $anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name}, |
|
}}); |
|
} |
|
} |
|
} |
|
|
|
return(0); |
|
} |
|
|
|
# This takes the temperature sensors and feeds them into the 'temperature' table, deleting stale entries as needed. |
|
sub process_temperature |
|
{ |
|
my ($anvil, $host_name) = @_; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { host_name => $host_name }}); |
|
|
|
$anvil->data->{'scan-ipmitool'}{queries} = []; |
|
|
|
# First, read in all existing entries. We'll compare and UPDATE or INSERT as needed and DELETE any |
|
# stale entries. |
|
my $query = " |
|
SELECT |
|
temperature_uuid, |
|
temperature_sensor_name, |
|
temperature_value_c, |
|
temperature_weight, |
|
temperature_state, |
|
temperature_is |
|
FROM |
|
temperature |
|
WHERE |
|
temperature_host_uuid = ".$anvil->Database->quote($anvil->Get->host_uuid)." |
|
AND |
|
temperature_agent_name = ".$anvil->Database->quote($THIS_FILE)." |
|
AND |
|
temperature_sensor_host = ".$anvil->Database->quote($host_name)." |
|
;"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
my $results = $anvil->Database->query({query => $query, source => $THIS_FILE, line => __LINE__}); |
|
|
|
# One or more records were found. |
|
foreach my $row (@{$results}) |
|
{ |
|
my $scan_ipmitool_sensor_name = $row->[1]; |
|
$anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid} = $row->[0]; |
|
$anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c} = $row->[2]; |
|
$anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_weight} = $row->[3]; |
|
$anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state} = $row->[4]; |
|
$anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is} = $row->[5]; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"old::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_uuid" => $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid}, |
|
"old::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"old::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_weight" => $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_weight}, |
|
"old::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"old::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
|
|
# Look at the new values. |
|
foreach my $scan_ipmitool_sensor_name (sort {$a cmp $b} keys %{$anvil->data->{new}{$host_name}{temperature}}) |
|
{ |
|
my $new_temperature_uuid = $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid}; |
|
my $new_temperature_value_c = $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}; |
|
my $new_temperature_state = $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}; |
|
my $new_temperature_is = $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
new_temperature_uuid => $new_temperature_uuid, |
|
new_temperature_value_c => $new_temperature_value_c, |
|
new_temperature_state => $new_temperature_state, |
|
new_temperature_is => $new_temperature_is, |
|
}}); |
|
|
|
if ($new_temperature_value_c eq "na") |
|
{ |
|
delete $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}; |
|
next; |
|
} |
|
|
|
# If the state is 'warning', set a health weight of 1 and set critical to 2. |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { "sys::scanning_myself" => $anvil->data->{sys}{scanning_myself} }}); |
|
my $new_temperature_weight = 1; |
|
if ($anvil->data->{sys}{scanning_myself}) |
|
{ |
|
# What weight will we apply to this sensor? |
|
$new_temperature_weight = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{weight}; |
|
if (exists $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_weight}) |
|
{ |
|
$new_temperature_weight = $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_weight}; |
|
} |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_temperature_weight => $new_temperature_weight }}); |
|
if (exists $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}) |
|
{ |
|
# If it a number? |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::weight" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}, |
|
}}); |
|
if (($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight} =~ /^\d+$/) or ($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight} =~ /^\d+\.\d+$/)) |
|
{ |
|
$new_temperature_weight = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{weight}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_temperature_weight => $new_temperature_weight }}); |
|
} |
|
} |
|
|
|
# Default to '1' if not set. |
|
$new_temperature_weight = 1 if not $new_temperature_weight; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_temperature_weight => $new_temperature_weight }}); |
|
|
|
# If it's not OK, set the weight |
|
if ($new_temperature_state ne "ok") |
|
{ |
|
my $health_source_name = "temperature:".$scan_ipmitool_sensor_name; |
|
$anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name} = $new_temperature_weight; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"health::new::$health_source_name" => $anvil->data->{'scan-ipmitool'}{health}{new}{$health_source_name}, |
|
}}); |
|
} |
|
} |
|
|
|
# Now see if the variable was seen before and, if so, if it changed. |
|
my $temperature_uuid = ""; |
|
if (ref($anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name})) |
|
{ |
|
# Update the existing entry, if needed. |
|
my $temperature_uuid = $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid}; |
|
} |
|
|
|
# Generate and store the UUID. |
|
my $sensor_host_uuid = $anvil->Get->host_uuid_from_name({host_name => $host_name}); |
|
if (not $sensor_host_uuid) |
|
{ |
|
$sensor_host_uuid = $host_name; |
|
} |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { sensor_host_uuid => $sensor_host_uuid }}); |
|
$temperature_uuid = $anvil->Database->insert_or_update_temperature({ |
|
cache => $anvil->data->{'scan-ipmitool'}{queries}, |
|
debug => 2, |
|
temperature_uuid => $temperature_uuid, |
|
temperature_host_uuid => $anvil->Get->host_uuid, |
|
temperature_agent_name => $THIS_FILE, |
|
temperature_sensor_host => $sensor_host_uuid, |
|
temperature_sensor_name => $scan_ipmitool_sensor_name, |
|
temperature_value_c => $new_temperature_value_c, |
|
temperature_state => $new_temperature_state, |
|
temperature_is => $new_temperature_is, |
|
temperature_weight => $new_temperature_weight, |
|
}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { temperature_uuid => $temperature_uuid }}); |
|
|
|
# We still want this value, so delete it from the hash. |
|
if (exists $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}) |
|
{ |
|
delete $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}; |
|
} |
|
|
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid} = $temperature_uuid; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_uuid" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid}, |
|
}}); |
|
} |
|
|
|
# Now, if any undeleted old entries remain, delete them from the database. |
|
foreach my $scan_ipmitool_sensor_name (sort {$a cmp $b} keys %{$anvil->data->{old}{$host_name}{temperature}}) |
|
{ |
|
my $temperature_uuid = $anvil->data->{old}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_uuid}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { temperature_uuid => $temperature_uuid }}); |
|
|
|
$temperature_uuid = $anvil->Database->insert_or_update_temperature({ |
|
cache => $anvil->data->{'scan-ipmitool'}{queries}, |
|
debug => 2, |
|
'delete' => 1, |
|
temperature_uuid => $temperature_uuid, |
|
}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { temperature_uuid => $temperature_uuid }}); |
|
} |
|
|
|
# Now commit the changes. |
|
$anvil->Database->write({query => $anvil->data->{'scan-ipmitool'}{queries}, source => $THIS_FILE, line => __LINE__}); |
|
|
|
return(0); |
|
} |
|
|
|
# This logs thermal sensor values that are outside nominal ranges |
|
sub log_abnormal_temperatures |
|
{ |
|
my ($anvil, $host_name, $scan_ipmitool_sensor_name) = @_; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
}}); |
|
|
|
my $new_scan_ipmitool_value_sensor_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $new_scan_ipmitool_sensor_high_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $new_scan_ipmitool_sensor_high_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $new_scan_ipmitool_sensor_low_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $new_scan_ipmitool_sensor_low_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
}}); |
|
|
|
# If the sensor value is 'na' or '', ignore it. |
|
if (($new_scan_ipmitool_value_sensor_value eq "") or ($new_scan_ipmitool_value_sensor_value eq "na")) |
|
{ |
|
return(0); |
|
} |
|
|
|
### High Warning |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::high_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_warning}, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::high_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}, |
|
}}); |
|
|
|
my $high_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_warning}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}) && |
|
( $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning} =~ /^\d/)) |
|
{ |
|
$high_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_warning => $high_warning }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_high_critical =~ /^\d/) |
|
{ |
|
$high_warning = $new_scan_ipmitool_sensor_high_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_warning => $high_warning }}); |
|
} |
|
|
|
### High Critical |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::high_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_critical}, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::high_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}, |
|
}}); |
|
|
|
my $high_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_critical}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}) && |
|
( $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical} =~ /^\d/)) |
|
{ |
|
$high_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_critical => $high_critical }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_high_critical =~ /^\d/) |
|
{ |
|
$high_critical = $new_scan_ipmitool_sensor_high_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_critical => $high_critical }}); |
|
} |
|
|
|
### Low Warning |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::low_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_warning}, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::low_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}, |
|
}}); |
|
|
|
my $low_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_warning}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}) && |
|
( $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning} =~ /^\d/)) |
|
{ |
|
$low_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_warning => $low_warning }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_low_critical =~ /^\d/) |
|
{ |
|
$low_warning = $new_scan_ipmitool_sensor_low_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_warning => $low_warning }}); |
|
} |
|
|
|
### Low Critical |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::low_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_critical}, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::low_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}, |
|
}}); |
|
my $low_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_critical}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}) && |
|
( $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical} =~ /^\d/)) |
|
{ |
|
$low_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_critical => $low_critical }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_low_critical =~ /^\d/) |
|
{ |
|
$low_critical = $new_scan_ipmitool_sensor_low_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_critical => $low_critical }}); |
|
} |
|
|
|
# Record the levels |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
high_warning => $high_warning, |
|
high_critical => $high_critical, |
|
low_warning => $low_warning, |
|
low_critical => $low_critical, |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
}}); |
|
|
|
# Record the temperatures. |
|
if ($new_scan_ipmitool_value_sensor_value < $low_critical) |
|
{ |
|
# Setup the 'temperature' entry. |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'critical', |
|
temperature_is => 'low', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value < $low_warning) |
|
{ |
|
# Setup the 'temperature' entry. |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'warning', |
|
temperature_is => 'low', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value > $high_critical) |
|
{ |
|
# Setup the 'temperature' entry. |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'critical', |
|
temperature_is => 'high', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value > $high_warning) |
|
{ |
|
# Setup the 'temperature' entry. |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'warning', |
|
temperature_is => 'high', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
else |
|
{ |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'ok', |
|
temperature_is => 'nominal', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
|
|
### NOTE: Recording all temps now, so this might not be needed |
|
# When the dashboard scans a node, it needs to know about the Ambient and Systemboard temperatures in |
|
# order to decide whether the node is safe too boot back up or not. So if this host_name is a |
|
# dashboard, log the 'Ambient' and 'Systemboard' temperatures (or whatever the user defined) as |
|
# 'good', if they're not already in the 'new::temperature::x' hash. |
|
my $host_type = $anvil->Get->host_type(); |
|
foreach my $sensor (split/,/, $anvil->data->{'scan-ipmitool'}{offline_sensor_list}) |
|
{ |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
sensor => $sensor, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
host_type => $host_type, |
|
}}); |
|
if (($scan_ipmitool_sensor_name eq $sensor) && |
|
($host_type eq "striker") && |
|
(not exists $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name})) |
|
{ |
|
$anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name} = { |
|
temperature_value_c => $new_scan_ipmitool_value_sensor_value, |
|
temperature_state => 'ok', |
|
temperature_is => 'nominal', |
|
}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_value_c" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_value_c}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_state" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_state}, |
|
"new::${host_name}::temperature::${scan_ipmitool_sensor_name}::temperature_is" => $anvil->data->{new}{$host_name}{temperature}{$scan_ipmitool_sensor_name}{temperature_is}, |
|
}}); |
|
} |
|
} |
|
|
|
return(0); |
|
} |
|
|
|
# This processes a temperature sensor, handling changes and recording values that are in a warning or |
|
# critical state. |
|
sub process_temperature_change |
|
{ |
|
my ($anvil, $host_name, $scan_ipmitool_sensor_name) = @_; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
}}); |
|
|
|
# This is a repeat of some variables set before this function was called, but setting them here again |
|
# saves passing in a pile of variables. |
|
my $level = "info"; |
|
my $message_key = "scan_ipmitool_message_0005"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
|
|
# New values |
|
my $new_scan_ipmitool_value_sensor_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}; |
|
my $new_scan_ipmitool_sensor_high_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}; |
|
my $new_scan_ipmitool_sensor_high_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}; |
|
my $new_scan_ipmitool_sensor_low_critical = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}; |
|
my $new_scan_ipmitool_sensor_low_warning = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_warning, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
}}); |
|
|
|
# If the value is "" and it's a digit-based value, switch it to '0' |
|
if ($new_scan_ipmitool_value_sensor_value eq "") |
|
{ |
|
$new_scan_ipmitool_value_sensor_value = 0; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { new_scan_ipmitool_value_sensor_value => $new_scan_ipmitool_value_sensor_value }}); |
|
} |
|
|
|
# Old value, if it exists. |
|
my $old_scan_ipmitool_value_sensor_value = $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value} ? $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value} : 0; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_value_sensor_value" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}, |
|
old_scan_ipmitool_value_sensor_value => $old_scan_ipmitool_value_sensor_value, |
|
}}); |
|
|
|
### Buffer, used for clearing all alerts. |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::buffer" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{buffer}, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::buffer" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{buffer}, |
|
}}); |
|
my $buffer = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{buffer} ? $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{buffer} : $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{buffer}; |
|
|
|
### High Warning |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::high_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_warning}, |
|
new_scan_ipmitool_sensor_high_warning => $new_scan_ipmitool_sensor_high_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::high_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}, |
|
}}); |
|
my $high_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_warning}; |
|
|
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}) && |
|
($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning} =~ /^\d/)) |
|
{ |
|
$high_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_warning => $high_warning }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_high_critical =~ /^\d/) |
|
{ |
|
$high_warning = $new_scan_ipmitool_sensor_high_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_warning => $high_warning }}); |
|
} |
|
|
|
### High Critical |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::high_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_critical}, |
|
new_scan_ipmitool_sensor_high_critical => $new_scan_ipmitool_sensor_high_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::high_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}, |
|
}}); |
|
my $high_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{high_critical}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}) && |
|
($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical} =~ /^\d/)) |
|
{ |
|
$high_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{high_critical}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_critical => $high_critical }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_high_critical =~ /^\d/) |
|
{ |
|
$high_critical = $new_scan_ipmitool_sensor_high_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { high_critical => $high_critical }}); |
|
} |
|
|
|
### Low Warning |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::low_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_warning}, |
|
new_scan_ipmitool_sensor_low_warning => $new_scan_ipmitool_sensor_low_warning, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::low_warning" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}, |
|
}}); |
|
my $low_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_warning}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}) && |
|
($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning} =~ /^\d/)) |
|
{ |
|
$low_warning = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_warning}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_warning => $low_warning }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_low_critical =~ /^\d/) |
|
{ |
|
$low_warning = $new_scan_ipmitool_sensor_low_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_warning => $low_warning }}); |
|
} |
|
|
|
### Low Critical |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::low_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_critical}, |
|
new_scan_ipmitool_sensor_low_critical => $new_scan_ipmitool_sensor_low_critical, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::low_critical" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}, |
|
}}); |
|
my $low_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{low_critical}; |
|
if ((defined $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}) && |
|
($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical} =~ /^\d/)) |
|
{ |
|
$low_critical = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{low_critical}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_critical => $low_critical }}); |
|
} |
|
elsif ($new_scan_ipmitool_sensor_low_critical =~ /^\d/) |
|
{ |
|
$low_critical = $new_scan_ipmitool_sensor_low_critical; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { low_critical => $low_critical }}); |
|
} |
|
|
|
### Jump delta |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::thresholds::defaults::jump" => $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{jump}, |
|
"scan-ipmitool::thresholds::${scan_ipmitool_sensor_name}::jump" => $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{jump}, |
|
}}); |
|
my $jump = $anvil->data->{'scan-ipmitool'}{thresholds}{'default'}{jump}; |
|
if ($anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{jump}) |
|
{ |
|
$jump = $anvil->data->{'scan-ipmitool'}{thresholds}{$scan_ipmitool_sensor_name}{jump}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { jump => $jump }}); |
|
} |
|
|
|
# We append the hex address some sensor names when there are duplicates. This deals with those. |
|
if ($scan_ipmitool_sensor_name =~ /^(.*?) \(.*?h\)$/) |
|
{ |
|
my $jump_name = $1; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { jump_name => $jump_name }}); |
|
if ((exists $anvil->data->{'scan-ipmitool'}{thresholds}{$jump_name}) && ($anvil->data->{'scan-ipmitool'}{thresholds}{$jump_name}{jump})) |
|
{ |
|
$jump = $anvil->data->{'scan-ipmitool'}{thresholds}{$jump_name}{jump}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { jump => $jump }}); |
|
} |
|
} |
|
|
|
# Final levels |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
scan_ipmitool_sensor_name => $scan_ipmitool_sensor_name, |
|
high_warning => $high_warning, |
|
high_critical => $high_critical, |
|
low_warning => $low_warning, |
|
low_critical => $low_critical, |
|
jump => $jump, |
|
buffer => $buffer, |
|
}}); |
|
|
|
# Now, has the value climbed, fallen or stayed the same? Pretend it is rising if it is a new sensor. |
|
if (($new_scan_ipmitool_value_sensor_value > $old_scan_ipmitool_value_sensor_value) || (not $old_scan_ipmitool_value_sensor_value)) |
|
{ |
|
### Rising. |
|
# |
|
# If it is over the high critical level, clear the 'warning', set the 'critical' and, if |
|
# needed, add the entry to 'temperature'. |
|
# |
|
# If it is over the high warning, check and set the warning. |
|
# |
|
# If it is over the low warning, check and clear both critical and warning, and clear the |
|
# 'temperature' entry, if needed. |
|
# |
|
# If it is over the low critical, but not low warning, clear the critical and set the warning. |
|
# Clear the 'temperature' entry, if it exists. |
|
# |
|
# If the temperature jumped above the set per-cycle change limit, trigger an alarm no matter |
|
# what. |
|
if ($new_scan_ipmitool_value_sensor_value > $high_critical) |
|
{ |
|
# We've gone critical. If it was previously 'warning', clear them. |
|
foreach my $type ("temperature_high_warning", "temperature_low_warning", "temperature_low_critical") |
|
{ |
|
my $record_locator = $host_name.":".$scan_ipmitool_sensor_name.":".$type; |
|
my $changed = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $record_locator, set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
record_locator => $record_locator, |
|
changed => $changed, |
|
}}); |
|
} |
|
|
|
# Set the critical warning. |
|
my $changed = $anvil->Alert->check_alert_sent({record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_high_critical", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { changed => $changed }}); |
|
|
|
# If set, alert the user and register with 'temperature'. |
|
if ($changed) |
|
{ |
|
# This is the first time we climbed. Send an alert and then register the |
|
# entry in the database's 'temperature' table. |
|
$level = "critical"; |
|
$message_key = "scan_ipmitool_message_0006"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value > $high_warning) |
|
{ |
|
# The temp is rising, so the 'high_critical' should not be set, but check/clear it |
|
# anyway to be safe. |
|
$anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_high_critical", set_by => $THIS_FILE}); |
|
my $changed = $anvil->Alert->check_alert_sent({clear => 0, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_high_warning", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { changed => $changed }}); |
|
if ($changed) |
|
{ |
|
# Tell the user that the temperature is rising. |
|
$level = "warning"; |
|
$message_key = "scan_ipmitool_message_0007"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value > ($low_warning + $buffer)) |
|
{ |
|
# If there was a 'low_warning' or 'low_critical', clear it and tell the user that |
|
# we're OK now. |
|
my $clear_critical = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_critical", set_by => $THIS_FILE}); |
|
my $clear_warning = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_warning", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
clear_critical => $clear_critical, |
|
clear_warning => $clear_warning, |
|
}}); |
|
if (($clear_critical) or ($clear_warning)) |
|
{ |
|
# Tell the user we're OK again. Whether this is a 'critical' or 'warning' |
|
# level alert depends on what it was before. We want people who only get |
|
# critical alerts to know we're OK if they got the critical alarm. |
|
$level = $clear_critical ? "critical" : "warning"; |
|
$message_key = "scan_ipmitool_message_0008"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value > ($low_critical + $buffer)) |
|
{ |
|
# It has risen above critically low levels. |
|
my $clear_critical = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_critical", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { clear_critical => $clear_critical }}); |
|
if ($clear_critical) |
|
{ |
|
# Tell the user we're getting better. |
|
$level = "critical"; |
|
$message_key = "scan_ipmitool_message_0009"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
else |
|
{ |
|
# it is floating in the safe area. |
|
} |
|
|
|
# Check for a jump now, if we have an old value. |
|
if ($old_scan_ipmitool_value_sensor_value) |
|
{ |
|
my $delta = ($new_scan_ipmitool_value_sensor_value - $old_scan_ipmitool_value_sensor_value); |
|
if ($delta > $jump) |
|
{ |
|
# Temperature jumped. This is a stand-alone 'warning' level alarm. |
|
my $sensor_name = "name=$scan_ipmitool_sensor_name:units=C"; |
|
my $new_sensor_value = "value=$new_scan_ipmitool_value_sensor_value:units=C"; |
|
my $old_sensor_value = "value=$old_scan_ipmitool_value_sensor_value:units=C"; |
|
my $variables = { |
|
sensor_name => $sensor_name, |
|
new_sensor_value => $new_sensor_value, |
|
old_sensor_value => $old_sensor_value |
|
}; |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 0, priority => "err", key => "scan_ipmitool_message_0010", variables => $variables}); |
|
$anvil->Alert->register({alert_level => "warning", message => "scan_ipmitool_message_0010", variables => $variables, sort_position => 1, set_by => $THIS_FILE}); |
|
} |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value < $old_scan_ipmitool_value_sensor_value) |
|
{ |
|
### Falling. |
|
# |
|
# If it is below the high critical, but not high warning, clear the critical and set the |
|
# warning. Clear the 'temperature' entry, if it exists. |
|
# |
|
# If it is below the high warning, check and clear both critical and warning, and clear the |
|
# 'temperature' entry, if needed. |
|
# |
|
# If it is below the low critical level, clear the 'warning', set the 'critical' and, if |
|
# needed, add the entry to 'temperature'. |
|
# |
|
# If it is below the low warning, check and set the warning. |
|
if ($new_scan_ipmitool_value_sensor_value < $low_critical) |
|
{ |
|
# We've gone critical. Clear previous alerts... |
|
foreach my $type ("temperature_high_critical", "temperature_high_warning", "temperature_low_warning") |
|
{ |
|
my $record_locator = $host_name.":".$scan_ipmitool_sensor_name.":".$type; |
|
my $changed = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $record_locator, set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
record_locator => $record_locator, |
|
changed => $changed, |
|
}}); |
|
} |
|
|
|
# Now set the critical warning. |
|
my $changed = $anvil->Alert->check_alert_sent({record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_critical", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { changed => $changed }}); |
|
if ($changed) |
|
{ |
|
# This is the first time we climbed. Send an alert and then register the |
|
# entry in the database's 'temperature' table. |
|
$level = "critical"; |
|
$message_key = "scan_ipmitool_message_0011"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value < $low_warning) |
|
{ |
|
# The temp is dropping, so the 'low_critical' should not be set, but check/clear it |
|
# anyway to be safe. |
|
$anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_critical", set_by => $THIS_FILE}); |
|
my $changed = $anvil->Alert->check_alert_sent({clear => 0, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_warning", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { changed => $changed }}); |
|
if ($changed) |
|
{ |
|
# Tell the user that the temperature is rising. |
|
$level = "warning"; |
|
$message_key = "scan_ipmitool_message_0012"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value < ($high_warning - $buffer)) |
|
{ |
|
# If there was a 'high_warning' or 'high_critical', clear it and tell the user that |
|
# we're OK now. |
|
my $clear_critical = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_high_critical", set_by => $THIS_FILE}); |
|
my $clear_warning = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_high_warning", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
clear_critical => $clear_critical, |
|
clear_warning => $clear_warning, |
|
}}); |
|
if (($clear_critical) or ($clear_warning)) |
|
{ |
|
# Tell the user we're OK again. Whether this is a 'critical' or 'warning' |
|
# level alert depends on what it was before. We want people who only get |
|
# critical alerts to know we're OK if they got the critical alarm. |
|
$level = $clear_critical ? "critical" : "warning"; |
|
$message_key = "scan_ipmitool_message_0013"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
elsif ($new_scan_ipmitool_value_sensor_value < ($high_critical - $buffer)) |
|
{ |
|
# It is below critically high levels. |
|
my $clear_critical = $anvil->Alert->check_alert_sent({clear => 1, record_locator => $host_name.":".$scan_ipmitool_sensor_name.":temperature_low_critical", set_by => $THIS_FILE}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { clear_critical => $clear_critical }}); |
|
if ($clear_critical) |
|
{ |
|
# Tell the user we're OK again. |
|
$level = "critical"; |
|
$message_key = "scan_ipmitool_message_0014"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
} |
|
} |
|
else |
|
{ |
|
# it is floating in the safe area. |
|
} |
|
} |
|
|
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
level => $level, |
|
message_key => $message_key, |
|
}}); |
|
return($level, $message_key); |
|
} |
|
|
|
# This reads in the last scan's data. |
|
sub read_last_scan |
|
{ |
|
my ($anvil, $host_name) = @_; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { host_name => $host_name }}); |
|
|
|
# Make sure I don't have any stray data for this host_name. |
|
if (exists $anvil->data->{sql}{$host_name}) |
|
{ |
|
delete $anvil->data->{sql}{$host_name}; |
|
} |
|
|
|
# Read in existing data, if any. |
|
my $query = " |
|
SELECT |
|
a.scan_ipmitool_uuid, |
|
a.scan_ipmitool_sensor_name, |
|
a.scan_ipmitool_sensor_units, |
|
a.scan_ipmitool_sensor_status, |
|
a.scan_ipmitool_sensor_high_critical, |
|
a.scan_ipmitool_sensor_high_warning, |
|
a.scan_ipmitool_sensor_low_critical, |
|
a.scan_ipmitool_sensor_low_warning, |
|
b.scan_ipmitool_value_sensor_value |
|
FROM |
|
scan_ipmitool a, |
|
scan_ipmitool_values b |
|
WHERE |
|
a.scan_ipmitool_uuid = b.scan_ipmitool_value_scan_ipmitool_uuid |
|
AND |
|
a.scan_ipmitool_sensor_host = ".$anvil->Database->quote($host_name)." |
|
AND |
|
a.scan_ipmitool_host_uuid = ".$anvil->Database->quote($anvil->Get->host_uuid)." |
|
;"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
my $results = $anvil->Database->query({query => $query, source => $THIS_FILE, line => __LINE__}); |
|
my $count = @{$results}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
results => $results, |
|
count => $count, |
|
}}); |
|
# One or more records were found. |
|
foreach my $row (@{$results}) |
|
{ |
|
my $scan_ipmitool_uuid = $row->[0]; |
|
my $scan_ipmitool_sensor_name = $row->[1]; |
|
my $scan_ipmitool_sensor_units = $row->[2]; |
|
my $scan_ipmitool_sensor_status = $row->[3]; |
|
my $scan_ipmitool_sensor_high_critical = $row->[4]; |
|
my $scan_ipmitool_sensor_high_warning = $row->[5]; |
|
my $scan_ipmitool_sensor_low_critical = $row->[6]; |
|
my $scan_ipmitool_sensor_low_warning = $row->[7]; |
|
my $scan_ipmitool_value_sensor_value = $row->[8]; |
|
|
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_uuid} = $scan_ipmitool_uuid; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units} = $scan_ipmitool_sensor_units; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status} = $scan_ipmitool_sensor_status; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical} = $scan_ipmitool_sensor_high_critical ? $scan_ipmitool_sensor_high_critical : ""; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning} = $scan_ipmitool_sensor_high_warning ? $scan_ipmitool_sensor_high_warning : ""; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical} = $scan_ipmitool_sensor_low_critical ? $scan_ipmitool_sensor_low_critical : ""; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning} = $scan_ipmitool_sensor_low_warning ? $scan_ipmitool_sensor_low_warning : ""; |
|
$anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value} = $scan_ipmitool_value_sensor_value; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_uuid" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_uuid}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_units" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_units}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_status" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_status}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_high_critical" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_critical}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_high_warning" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_high_warning}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_low_critical" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_critical}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_sensor_low_warning" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_sensor_low_warning}, |
|
"sql::${host_name}::scan_ipmitool_sensor_name::${scan_ipmitool_sensor_name}::scan_ipmitool_value_sensor_value" => $anvil->data->{sql}{$host_name}{scan_ipmitool_sensor_name}{$scan_ipmitool_sensor_name}{scan_ipmitool_value_sensor_value}, |
|
}}); |
|
} |
|
|
|
return($count); |
|
} |
|
|
|
# Query IPMI targets. Unreachable targets will simply be ignored. |
|
sub query_ipmi_targets |
|
{ |
|
my ($anvil) = @_; |
|
|
|
foreach my $host_name (sort {$a cmp $b} keys %{$anvil->data->{'scan-ipmitool'}{host_name}}) |
|
{ |
|
my $ipmitool_command = $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmitool_command}; |
|
my $ipmi_password = $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmi_password}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
ipmitool_command => $ipmitool_command, |
|
ipmi_password => $anvil->Log->is_secure($ipmi_password), |
|
}}); |
|
|
|
# Time the call. |
|
$anvil->Log->entry({source => $THIS_FILE, line => __LINE__, level => 2, key => "scan_ipmitool_log_0001", variables => { host_name => $host_name }}); |
|
|
|
# This will call, parse and store the information in (host_name == full host name; |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_value_sensor_value |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_units |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_status |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_high_critical |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_high_warning |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_low_critical |
|
# ipmi::<host_name>::scan_ipmitool_sensor_name::$sensor_name::scan_ipmitool_sensor_low_warning |
|
$anvil->System->collect_ipmi_data({ |
|
debug => 3, |
|
host_name => $host_name, |
|
ipmitool_command => $ipmitool_command, |
|
ipmi_password => $ipmi_password, |
|
}); |
|
|
|
# Analyze temperature sensors if this is our own data. |
|
if (($host_name eq $anvil->Get->host_name) or ($host_name eq $anvil->Get->short_host_name)) |
|
{ |
|
foreach my $sensor_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}}) |
|
{ |
|
my $units = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$sensor_name}{scan_ipmitool_sensor_units}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
sensor_name => $sensor_name, |
|
units => $units, |
|
}}); |
|
|
|
# If this is a temperature, check to see if it is outside its nominal range and, if |
|
# so, record it into a hash for loading into ScanCore's 'temperature' table. |
|
if ($units eq "C") |
|
{ |
|
log_abnormal_temperatures($anvil, $host_name, $sensor_name); |
|
} |
|
} |
|
} |
|
|
|
my $psu_count = 0; |
|
foreach my $sensor_name (sort {$a cmp $b} keys %{$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}}) |
|
{ |
|
if ($sensor_name =~ /^PSU(\d+)/) |
|
{ |
|
my $this_psu = $1; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { this_psu => $this_psu }}); |
|
if ($this_psu > $psu_count) |
|
{ |
|
$psu_count = $this_psu; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { psu_count => $psu_count }}); |
|
} |
|
} |
|
} |
|
|
|
# If a PSU is OK, but its wattage is 0, input power was lost. We'll switch the PSU state to |
|
# ensure this sets a health value. We'll check for five PSUs, though very very few should |
|
# have more than 2. |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { psu_count => $psu_count }}); |
|
foreach my $i (1..$psu_count) |
|
{ |
|
my $psu_key = "PSU".$i; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
i => $i, |
|
psu_key => $psu_key, |
|
}}); |
|
|
|
if (exists $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$psu_key}) |
|
{ |
|
# TODO: Is this the key for HP machines, too? |
|
my $wattage_key = $psu_key." Power"; |
|
my $psu_value = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$psu_key}{scan_ipmitool_value_sensor_value}; |
|
my $psu_status = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$psu_key}{scan_ipmitool_sensor_status}; |
|
my $psu_wattage = $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$wattage_key}{scan_ipmitool_value_sensor_value}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
wattage_key => $wattage_key, |
|
psu_value => $psu_value, |
|
psu_status => $psu_status, |
|
psu_wattage => $psu_wattage, |
|
}}); |
|
|
|
if ((lc($psu_status) eq "ok") && (lc($psu_wattage) eq "no reading")) |
|
{ |
|
# Change the status to 'no signal' |
|
$anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$psu_key}{scan_ipmitool_sensor_status} = "ns"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"ipmi::${host_name}::scan_ipmitool_sensor_name::${psu_key}::scan_ipmitool_sensor_status" => $anvil->data->{ipmi}{$host_name}{scan_ipmitool_sensor_name}{$psu_key}{scan_ipmitool_sensor_status}, |
|
}}); |
|
} |
|
} |
|
else |
|
{ |
|
# This PSU doesn't exist, we're done. |
|
last; |
|
} |
|
} |
|
} |
|
|
|
return(0); |
|
} |
|
|
|
# This looks for IPMI targets to scan. |
|
sub find_ipmi_targets |
|
{ |
|
my ($anvil) = @_; |
|
|
|
# This will keep track of how many IPMI targets we find. |
|
my $ipmi_targets = 0; |
|
|
|
# If I am a node, I will only scan myself. |
|
my $host_type = $anvil->Get->host_type(); |
|
my $host_name = $anvil->Get->host_name(); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_type => $host_type, |
|
host_name => $host_name, |
|
}}); |
|
|
|
# Do I have local IPMI access? |
|
if ((-e '/dev/ipmi0') or (-e '/dev/ipmi/0') or (-e '/dev/ipmidev/0')) |
|
{ |
|
my ($output, $return_code) = $anvil->System->call({timeout => 30, shell_call => $anvil->data->{path}{exe}{ipmitool}." chassis power status"}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
output => $output, |
|
return_code => $return_code, |
|
}}); |
|
if (not $return_code) |
|
{ |
|
# We're good. |
|
$ipmi_targets++; |
|
my $host_name = $anvil->Get->host_name(); |
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{host_ipmi} = ""; |
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmitool_command} = $anvil->data->{path}{exe}{ipmitool}; |
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmi_password} = ""; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::host_name::${host_name}::host_ipmi" => $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{host_ipmi}, |
|
"scan-ipmitool::host_name::${host_name}::ipmitool_command" => $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmitool_command}, |
|
"scan-ipmitool::host_name::${host_name}::ipmi_password" => $anvil->Log->is_secure($anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmi_password}), |
|
}}); |
|
} |
|
} |
|
|
|
### NOTE: This is changed. Now that striker's directly call the targets to check temperature when |
|
### evaluating thermal boot conditions, we don't need to store this data. |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { ipmi_targets => $ipmi_targets }}); |
|
return($ipmi_targets); |
|
|
|
# Which hosts we scan depends on if we're a Striker dashboard or not. If we are, we'll try to scan |
|
# all machines in all Anvil! systems. Otherwise, we only scan ourselves. |
|
=cut |
|
if ($host_type ne "striker") |
|
{ |
|
# We're not a dashboard, so we don't scan others. |
|
return($ipmi_targets); |
|
} |
|
|
|
# Loop through Anvil! systems. |
|
my $query = " |
|
SELECT |
|
anvil_name, |
|
anvil_node1_host_uuid, |
|
anvil_node2_host_uuid, |
|
anvil_dr1_host_uuid |
|
FROM |
|
anvils |
|
WHERE |
|
anvil_description != 'DELETED' |
|
;"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
|
|
my $results = $anvil->Database->query({query => $query, source => $THIS_FILE, line => __LINE__}); |
|
my $count = @{$results}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
results => $results, |
|
count => $count, |
|
}}); |
|
foreach my $row (@{$results}) |
|
{ |
|
# For each host_uuid, get the IPMI info. |
|
my $anvil_name = $row->[0]; |
|
my $anvil_node1_host_uuid = $row->[1]; |
|
my $anvil_node2_host_uuid = $row->[2]; |
|
my $anvil_dr1_host_uuid = defined $row->[3] ? $row->[3] : ""; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
's1:anvil_name' => $anvil_name, |
|
's2:anvil_node1_host_uuid' => $anvil_node1_host_uuid, |
|
's3:anvil_node2_host_uuid' => $anvil_node2_host_uuid, |
|
's4:anvil_dr1_host_uuid' => $anvil_dr1_host_uuid, |
|
}}); |
|
|
|
my $query = " |
|
SELECT |
|
host_name, |
|
host_uuid, |
|
host_ipmi |
|
FROM |
|
hosts |
|
WHERE |
|
host_ipmi != '' |
|
AND |
|
( |
|
host_uuid = ".$anvil->Database->quote($anvil_node1_host_uuid)." |
|
OR |
|
host_uuid = ".$anvil->Database->quote($anvil_node2_host_uuid); |
|
if ($anvil_dr1_host_uuid) |
|
{ |
|
$query .= " |
|
OR |
|
host_uuid = ".$anvil->Database->quote($anvil_dr1_host_uuid); |
|
} |
|
$query .= " |
|
) |
|
;"; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { query => $query }}); |
|
|
|
my $results = $anvil->Database->query({query => $query, source => $THIS_FILE, line => __LINE__}); |
|
my $count = @{$results}; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
results => $results, |
|
count => $count, |
|
}}); |
|
foreach my $row (@{$results}) |
|
{ |
|
# We've got an entry in the 'scan_hardware' table, so now we'll look for data in the node and |
|
# services tables. |
|
my $host_name = $row->[0]; |
|
my $host_uuid = $row->[1]; |
|
my $host_ipmi = $row->[2]; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
host_name => $host_name, |
|
host_uuid => $host_uuid, |
|
host_ipmi => $anvil->Log->is_secure($host_ipmi), |
|
}}); |
|
|
|
# Get the ipaddress and see if I can ping the target. If I can't, there is no sense in |
|
# recording this entry. |
|
my $access = 0; |
|
my $target = ""; |
|
if (($host_ipmi =~ /-a (.*?) /) or ($host_ipmi =~ /-ip (.*?) /)) |
|
{ |
|
$target = $1; |
|
} |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { target => $target }}); |
|
if ($target) |
|
{ |
|
($access, my $average_time) = $anvil->Network->ping({ping => $target}); |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
access => $access, |
|
average_time => $average_time, |
|
}}); |
|
} |
|
next if not $access; |
|
$ipmi_targets++; |
|
|
|
# Convert to an 'ipmitool' call. |
|
my ($ipmitool_command, $ipmi_password) = $anvil->Convert->fence_ipmilan_to_ipmitool({fence_ipmilan_command => $host_ipmi}); |
|
|
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{host_ipmi} = $host_ipmi; |
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmitool_command} = $ipmitool_command; |
|
$anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmi_password} = $ipmi_password; |
|
$anvil->Log->variables({source => $THIS_FILE, line => __LINE__, level => 2, list => { |
|
"scan-ipmitool::host_name::${host_name}::host_ipmi" => $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{host_ipmi}, |
|
"scan-ipmitool::host_name::${host_name}::ipmitool_command" => $anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmitool_command}, |
|
"scan-ipmitool::host_name::${host_name}::ipmi_password" => $anvil->Log->is_secure($anvil->data->{'scan-ipmitool'}{host_name}{$host_name}{ipmi_password}), |
|
}}); |
|
} |
|
} |
|
=cut |
|
return($ipmi_targets); |
|
}
|
|
|