enh(rubrik): add --check-retention option to track disappeared jobs and fix an issue in long output (#5171)
This option has been added to track disappeared jobs and fix a concatenation issue in long output. Refs: CTOR-775
This commit is contained in:
itoussies
GitHub
parent
591981bf37
commit
88be153235
|
|
@ -1,4 +1,7 @@
|
|||
{
|
||||
"dependencies": [
|
||||
"libdatetime-perl",
|
||||
"libdigest-md5-perl",
|
||||
"libjson-perl"
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,4 +1,7 @@
|
|||
{
|
||||
"dependencies": [
|
||||
"perl(DateTime)",
|
||||
"perl(Digest::MD5)",
|
||||
"perl(JSON::XS)"
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -221,7 +221,8 @@ sub new {
|
|||
'filter-location-name:s' => { name => 'filter_location_name' },
|
||||
'filter-object-type:s' => { name => 'filter_object_type' },
|
||||
'unit:s' => { name => 'unit', default => 's' },
|
||||
'limit:s' => { name => 'limit' }
|
||||
'limit:s' => { name => 'limit' },
|
||||
'check-retention' => { name => 'check_retention' }
|
||||
});
|
||||
|
||||
$self->{cache_exec} = centreon::plugins::statefile->new(%options);
|
||||
|
|
@ -247,7 +248,11 @@ sub check_options {
|
|||
sub manage_selection {
|
||||
my ($self, %options) = @_;
|
||||
|
||||
my $jobs_exec = $options{custom}->get_jobs_monitoring(get_param => [ 'limit=' . $self->{option_results}->{limit} ]);
|
||||
my $get_param = [ 'limit=' . $self->{option_results}->{limit} ];
|
||||
if (defined($self->{option_results}->{filter_job_type}) && $self->{option_results}->{filter_job_type} ne '') {
|
||||
push @{$get_param}, 'job_type=' . $self->{option_results}->{filter_job_type};
|
||||
}
|
||||
my $jobs_exec = $options{custom}->get_jobs_monitoring(get_param => $get_param);
|
||||
|
||||
$self->{cache_exec}->read(statefile => 'rubrik_' . $self->{mode} . '_' .
|
||||
Digest::MD5::md5_hex(
|
||||
|
|
@ -260,7 +265,8 @@ sub manage_selection {
|
|||
);
|
||||
my $ctime = time();
|
||||
my $last_exec_times = $self->{cache_exec}->get(name => 'jobs');
|
||||
$last_exec_times = {} if (!defined($last_exec_times));
|
||||
$last_exec_times = {} if (!defined($last_exec_times));
|
||||
my %jobs_detected = ();
|
||||
|
||||
$self->{global} = { detected => 0 };
|
||||
$self->{jobs} = {};
|
||||
|
|
@ -269,13 +275,13 @@ sub manage_selection {
|
|||
$job_exec->{objectId} !~ /$self->{option_results}->{filter_job_id}/);
|
||||
next if (defined($self->{option_results}->{filter_job_name}) && $self->{option_results}->{filter_job_name} ne '' &&
|
||||
$job_exec->{objectName} !~ /$self->{option_results}->{filter_job_name}/);
|
||||
next if (defined($self->{option_results}->{filter_job_type}) && $self->{option_results}->{filter_job_type} ne '' &&
|
||||
$job_exec->{jobType} !~ /$self->{option_results}->{filter_job_type}/i);
|
||||
next if (defined($self->{option_results}->{filter_object_type}) && $self->{option_results}->{filter_object_type} ne '' &&
|
||||
$job_exec->{objectType} !~ /$self->{option_results}->{filter_object_type}/i);
|
||||
next if (defined($self->{option_results}->{filter_location_name}) && $self->{option_results}->{filter_location_name} ne '' &&
|
||||
$job_exec->{locationName} !~ /$self->{option_results}->{filter_location_name}/);
|
||||
|
||||
$self->{global}->{detected}++;
|
||||
$jobs_detected{$job_exec->{objectName}} = 1;
|
||||
$job_exec->{jobType} = lc($job_exec->{jobType});
|
||||
|
||||
if (!defined($self->{jobs}->{ $job_exec->{objectId} })) {
|
||||
|
|
@ -302,7 +308,6 @@ sub manage_selection {
|
|||
$last_exec = $_;
|
||||
}
|
||||
|
||||
$self->{global}->{detected}++;
|
||||
# Failure, Scheduled, Success, SuccessfulWithWarnings, Active, Canceled
|
||||
$failed++ if ($_->{jobStatus} =~ /Failure/i);
|
||||
$total++;
|
||||
|
|
@ -326,7 +331,9 @@ sub manage_selection {
|
|||
$last_exec_times->{ $job_exec->{objectId} } = {
|
||||
jobName => $job_exec->{objectName},
|
||||
jobType => $job_exec->{jobType},
|
||||
epoch => $dt->epoch()
|
||||
epoch => $dt->epoch(),
|
||||
objectType => $job_exec->{objectType},
|
||||
locationName => $job_exec->{locationName}
|
||||
};
|
||||
}
|
||||
|
||||
|
|
@ -355,6 +362,8 @@ sub manage_selection {
|
|||
$self->{jobs}->{$objectId} = {
|
||||
name => $last_exec_times->{$objectId}->{jobName},
|
||||
jobType => $last_exec_times->{$objectId}->{jobType},
|
||||
objectType => $last_exec_times->{$objectId}->{objectType},
|
||||
locationName => $last_exec_times->{$objectId}->{locationName},
|
||||
timers => {
|
||||
jobName => $last_exec_times->{$objectId}->{jobName},
|
||||
jobType => $last_exec_times->{$objectId}->{jobType},
|
||||
|
|
@ -364,6 +373,15 @@ sub manage_selection {
|
|||
};
|
||||
}
|
||||
|
||||
if ($self->{global}->{detected} == 0 && defined($self->{option_results}->{check_retention})) {
|
||||
my $jobs_last_detected = $self->{cache_exec}->get(name => 'jobs');
|
||||
foreach my $job_id (keys %{$jobs_last_detected}) {
|
||||
if (!defined($jobs_detected{$jobs_last_detected->{$job_id}->{jobName}})) {
|
||||
$self->{global}->{detected}++;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
$self->{cache_exec}->write(data => {
|
||||
jobs => $last_exec_times
|
||||
});
|
||||
|
|
@ -407,6 +425,10 @@ Select the time unit for last execution time thresholds. May be 's' for seconds,
|
|||
|
||||
Define the number of entries to retrieve for the pagination (default: 500).
|
||||
|
||||
=item B<--check-retention>
|
||||
|
||||
Use the retention file to check if a job has been detected once but does not appear in the API response.
|
||||
|
||||
=item B<--unknown-execution-status>
|
||||
|
||||
Set unknown threshold for last job execution status.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,92 @@
|
|||
{
|
||||
"uuid": "c8fba1bd-af32-4acd-83a2-5b26a0152183",
|
||||
"lastMigration": 32,
|
||||
"name": "Rubrik2",
|
||||
"endpointPrefix": "api/v1",
|
||||
"latency": 0,
|
||||
"port": 3000,
|
||||
"hostname": "",
|
||||
"folders": [],
|
||||
"routes": [
|
||||
{
|
||||
"uuid": "b9fdb329-671b-48d0-a906-d58e45a70527",
|
||||
"type": "http",
|
||||
"documentation": "",
|
||||
"method": "get",
|
||||
"endpoint": "job_monitoring",
|
||||
"responses": [
|
||||
{
|
||||
"uuid": "4aac7b2c-2947-4e6b-83a4-094da73ecc5a",
|
||||
"body": "{\r\n \"jobMonitoringInfoList\": [\r\n {\r\n \"jobMonitoringState\": \"Success\",\r\n \"jobStatus\": \"Success\",\r\n \"jobType\": \"Backup\",\r\n \"objectId\": \"VolumeGroup:::123a456-123a-456b-789c-123456789\",\r\n \"objectType\": \"WindowsVolumeGroup\",\r\n \"objectName\": \"centreon.groupe.active volumes\",\r\n \"locationId\": \"Host:::123c456-a123-b456-c789-123a456\",\r\n \"locationName\": \"centreon.groupe.active\",\r\n \"slaDomainId\": \"1234a456-123a-456b-aaaa-12345\",\r\n \"slaDomainName\": \"CENTREON-DOMAIN\",\r\n \"startTime\": \"2024-07-18T20:00:01.382Z\",\r\n \"endTime\": \"2024-07-19T06:42:16.355Z\",\r\n \"lastSuccessfulJobTime\": \"2024-07-16T20:00:01.382Z\",\r\n \"nextJobTime\": \"2023-11-07T20:00:00.000Z\",\r\n \"isFirstFullSnapshot\": false,\r\n \"sourceClusterName\": \"LOCAL\",\r\n \"sourceClusterId\": \"aaaaaa-123a-456b-aaaa-12345\",\r\n \"retryCount\": 0,\r\n \"maximumAttemptsForJob\": 3,\r\n \"dataTransferred\": 571231961088,\r\n \"objectLogicalSize\": 193955119497216,\r\n \"eventSeriesId\": \"Zaaaaaa-123a-456b-123a-12345abcd\",\r\n \"duration\": 38534973,\r\n \"nodeId\": \"AAAABBBBCCCCDDD\",\r\n \"warningCount\": 0,\r\n \"lastUpdatedTime\": \"2024-07-19T06:42:16.721Z\",\r\n \"isLogTask\": false,\r\n \"isOnDemand\": false,\r\n \"retryStatus\": \"NotRetried\"\r\n },\r\n {\r\n \"jobMonitoringState\": \"Scheduled\",\r\n \"jobStatus\": \"Scheduled\",\r\n \"jobType\": \"Backup\",\r\n \"objectId\": \"VolumeGroup:::123a456-123a-456b-789c-123456789\",\r\n \"objectType\": \"WindowsVolumeGroup\",\r\n \"objectName\": \"centreon.groupe.active volumes\",\r\n \"locationId\": \"Host:::123c456-a123-b456-c789-123a456\",\r\n \"locationName\": \"centreon.groupe.active\",\r\n \"slaDomainId\": \"1234a456-123a-456b-aaaa-12345\",\r\n \"slaDomainName\": \"CENTREON-DOMAIN\",\r\n \"startTime\": \"2024-07-18T20:00:00.000Z\",\r\n \"lastSuccessfulJobTime\": \"2024-07-18T20:00:01.382Z\",\r\n \"isFirstFullSnapshot\": false,\r\n \"sourceClusterName\": \"LOCAL\",\r\n \"sourceClusterId\": \"aaaaaa-123a-456b-aaaa-12345\",\r\n \"retryCount\": 0,\r\n \"maximumAttemptsForJob\": 3,\r\n \"objectLogicalSize\": 193955119497216,\r\n \"eventSeriesId\": \"afba57d8-efb3-452e-892b-157acc6b6069\",\r\n \"nodeId\": \"AAAABBBBCCCCDDD\",\r\n \"warningCount\": 0,\r\n \"lastUpdatedTime\": \"2024-07-18T06:42:16.894Z\",\r\n \"isLogTask\": false,\r\n \"isOnDemand\": false,\r\n \"retryStatus\": \"NotRetried\"\r\n }\r\n ],\r\n \"jobType\": \"Backup\",\r\n \"shouldIncludeLogRelatedJob\": false,\r\n \"objectName\": \"CENTREON\",\r\n \"hasMore\": false\r\n}",
|
||||
"latency": 0,
|
||||
"statusCode": 200,
|
||||
"label": "",
|
||||
"headers": [],
|
||||
"bodyType": "INLINE",
|
||||
"filePath": "",
|
||||
"databucketID": "",
|
||||
"sendFileAsBody": false,
|
||||
"rules": [],
|
||||
"rulesOperator": "OR",
|
||||
"disableTemplating": false,
|
||||
"fallbackTo404": false,
|
||||
"default": true,
|
||||
"crudKey": "id",
|
||||
"callbacks": []
|
||||
}
|
||||
],
|
||||
"responseMode": null
|
||||
}
|
||||
],
|
||||
"rootChildren": [
|
||||
{
|
||||
"type": "route",
|
||||
"uuid": "b9fdb329-671b-48d0-a906-d58e45a70527"
|
||||
}
|
||||
],
|
||||
"proxyMode": false,
|
||||
"proxyHost": "",
|
||||
"proxyRemovePrefix": false,
|
||||
"tlsOptions": {
|
||||
"enabled": false,
|
||||
"type": "CERT",
|
||||
"pfxPath": "",
|
||||
"certPath": "",
|
||||
"keyPath": "",
|
||||
"caPath": "",
|
||||
"passphrase": ""
|
||||
},
|
||||
"cors": true,
|
||||
"headers": [
|
||||
{
|
||||
"key": "Content-Type",
|
||||
"value": "application/json"
|
||||
},
|
||||
{
|
||||
"key": "Access-Control-Allow-Origin",
|
||||
"value": "*"
|
||||
},
|
||||
{
|
||||
"key": "Access-Control-Allow-Methods",
|
||||
"value": "GET,POST,PUT,PATCH,DELETE,HEAD,OPTIONS"
|
||||
},
|
||||
{
|
||||
"key": "Access-Control-Allow-Headers",
|
||||
"value": "Content-Type, Origin, Accept, Authorization, Content-Length, X-Requested-With"
|
||||
}
|
||||
],
|
||||
"proxyReqHeaders": [
|
||||
{
|
||||
"key": "",
|
||||
"value": ""
|
||||
}
|
||||
],
|
||||
"proxyResHeaders": [
|
||||
{
|
||||
"key": "",
|
||||
"value": ""
|
||||
}
|
||||
],
|
||||
"data": [],
|
||||
"callbacks": []
|
||||
}
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
*** Settings ***
|
||||
Documentation Check Rubrik REST API jobs cache file creation
|
||||
|
||||
Resource ${CURDIR}${/}..${/}..${/}..${/}..${/}resources/import.resource
|
||||
|
||||
Suite Setup Start Mockoon ${MOCKOON_JSON}
|
||||
Suite Teardown Stop Mockoon
|
||||
Test Timeout 120s
|
||||
|
||||
|
||||
*** Variables ***
|
||||
${MOCKOON_JSON} ${CURDIR}${/}applications-rubrik-restapi.json
|
||||
${cmd} ${CENTREON_PLUGINS}
|
||||
... --plugin=apps::backup::rubrik::restapi::plugin
|
||||
... --hostname=${HOSTNAME}
|
||||
... --api-username='username'
|
||||
... --api-password='password'
|
||||
... --proto='http'
|
||||
... --port=${APIPORT}
|
||||
|
||||
|
||||
*** Test Cases ***
|
||||
cache ${tc}/1
|
||||
[Tags] apps backup rubrik restapi cache
|
||||
|
||||
${command} Catenate
|
||||
... ${cmd}
|
||||
... --mode=cache
|
||||
|
||||
${output} Run ${command}
|
||||
${output} Strip String ${output}
|
||||
Should Be Equal As Strings
|
||||
... ${output}
|
||||
... ${expected_result}
|
||||
... \nWrong output result for command:\n${command}\n\nExpected:\n${expected_result}\nCommand output:\n${output}\n
|
||||
|
||||
Examples: tc extra_options expected_result --
|
||||
... 1 ${EMPTY} OK: Cache files created successfully
|
||||
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
*** Settings ***
|
||||
Documentation Check Rubrik REST API jobs
|
||||
|
||||
Resource ${CURDIR}${/}..${/}..${/}..${/}..${/}resources/import.resource
|
||||
|
||||
Suite Setup Start Mockoon ${MOCKOON_JSON}
|
||||
Suite Teardown Stop Mockoon
|
||||
Test Timeout 120s
|
||||
|
||||
|
||||
*** Variables ***
|
||||
${MOCKOON_JSON} ${CURDIR}${/}applications-rubrik-restapi.json
|
||||
${cmd} ${CENTREON_PLUGINS}
|
||||
... --plugin=apps::backup::rubrik::restapi::plugin
|
||||
... --hostname=${HOSTNAME}
|
||||
... --api-username='username'
|
||||
... --api-password='password'
|
||||
... --proto='http'
|
||||
... --port=${APIPORT}
|
||||
|
||||
*** Test Cases ***
|
||||
jobs ${tc}/11
|
||||
[Tags] apps backup rubrik restapi jobs
|
||||
|
||||
${command} Catenate
|
||||
... ${cmd}
|
||||
... --mode=jobs
|
||||
... ${extraoptions}
|
||||
|
||||
Log ${command}
|
||||
|
||||
${output} Run ${command}
|
||||
|
||||
Should Match Regexp ${output} ${expected_result}
|
||||
|
||||
Examples: tc extraoptions expected_result --
|
||||
... 1 ${EMPTY} OK: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % - last execution .* - last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*s;;;0;
|
||||
... 2 --unknown-execution-status='\\%\{status\} eq "Success"' UNKNOWN: job 'centreon.groupe.active volumes' \[type: backup\] last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*s;;;0;
|
||||
... 3 --warning-execution-status='\\%\{status\} eq "Success"' WARNING: job 'centreon.groupe.active volumes' \[type: backup\] last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*s;;;0;
|
||||
... 4 --critical-execution-status='\\%\{status\} eq "Success"' CRITICAL: job 'centreon.groupe.active volumes' \[type: backup\] last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*s;;;0;
|
||||
... 5 --warning-jobs-executions-detected=1 --critical-jobs-executions-detected=3 WARNING: Number of jobs executions detected: 2 \| 'jobs.executions.detected.count'=2;0:2;0:5;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;;;0;
|
||||
... 6 --warning-jobs-executions-detected=1 --critical-jobs-executions-detected=1 CRITICAL: Number of jobs executions detected: 2 \| 'jobs.executions.detected.count'=2;0:2;0:3;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;;;0;
|
||||
... 7 --warning-job-executions-failed-prct=1:1 --critical-job-executions-failed-prct=1 WARNING: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;1:1;0:1;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;;;0;
|
||||
... 8 --warning-job-executions-failed-prct=1 --critical-job-executions-failed-prct=1:1 CRITICAL: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;0:1;1:1;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;;;0;
|
||||
... 9 --warning-job-execution-last=315360000 --critical-job-execution-last=315360000 OK: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % - last execution .* - last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;0:315360000;0:315360000;0;
|
||||
... 10 --warning-job-execution-last=1 --critical-job-execution-last=315360000 WARNING: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % - last execution .* - last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;0:1;0:315360000;0;
|
||||
... 11 --warning-job-execution-last=315360000 --critical-job-execution-last=315360000 CRITICAL: job 'centreon.groupe.active volumes' \[type: backup\] number of failed executions: 0.00 % - last execution .* - last execution started: 2024-07-18T20:00:01.382Z status: Success \| 'jobs.executions.detected.count'=2;;;0; 'centreon.groupe.active volumes~backup#job.executions.failed.percentage'=0.00%;;;0;100 'centreon.groupe.active volumes~backup#job.execution.last.seconds'=.*;0:315360000;0:315360000;0;
|
||||
Loading…
Reference in New Issue