This commit adds a table 'device_skip' that is used to restrict job queue searches to avoid jobs that are not permitted on this backend via *_no ACLs, or jobs on devices that have previously encountered multiple SNMP timeouts. When the backend loads or a device is added, a row is added to the table if that device should not be polled on this backend (together with the job actions which are to be skipped/denied). When a device SNMP connect fails a counter in the same row (or a new row) is incremented. There is also a new report 'SNMP Connect Failures' to show the devices with non-zero SNMP connect failure counters. A configurable limit in the setting 'max_deferrals' is used to set the threshold of no longer polling the device. To reset the deferrals/failures count, restart the Netdisco backend (which regenerates 'device_skip' cache entries). Squashed commit of the following: commitb5e32c219dAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 20:55:14 2017 +0100 show all failed connections in report commitffce3cee84Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 20:12:39 2017 +0100 only resolve fqdn once commitcc4f680f01Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 20:10:20 2017 +0100 Revert "only resolve fqdn once" This reverts commit3d136a54de. commitd8d082b30eAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 20:09:05 2017 +0100 a report to show SNMP failures commit3d136a54deAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 19:37:58 2017 +0100 only resolve fqdn once commit4550b8a84cAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 17:27:43 2017 +0100 skipover now implicit from deferrals/actionset; fix sql where logic with better correlation commitb51edbccd2Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 16:11:29 2017 +0100 only abort lock if action matches badactions commit415559b24fAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 13:56:42 2017 +0100 set skipover true when adding to actionset commit1086f2c467Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 13:50:56 2017 +0100 fix empty actionset commit31962580b8Merge:9b2e993e6808133bAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 13:25:08 2017 +0100 Merge branch 'og-device_skip' of github.com:netdisco/netdisco into og-device_skip commit6808133bdbAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 13:19:54 2017 +0100 in-job checks for acls are required for netdisco-do foreground actions commit3944dd7813Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 13:18:30 2017 +0100 avoid extra device lookup commit9b2e993e0fAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 12:31:36 2017 +0100 also delete device_skip rows when deleting device commitb55854e91dAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 11:34:27 2017 +0100 actions in device_skip table are now an array/set commit5e126eef07Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 09:36:33 2017 +0100 typo commit44266f2767Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 09:14:25 2017 +0100 *able checks within jobs should not be necessary with skiplist commite7c22e7d11Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 08:58:57 2017 +0100 increment deferrals field when job is deferred commit88ae9c00baAuthor: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 08:40:27 2017 +0100 turn connect fail into defer commiteac1857043Author: Oliver Gorwits <oliver@cpan.org> Date: Tue May 23 08:26:59 2017 +0100 rename failures column to be deferrals commit96ed444bbbAuthor: Oliver Gorwits <oliver@cpan.org> Date: Mon May 22 22:52:51 2017 +0100 set up list of jobs the backend instance should skip commit3a0019296dAuthor: Oliver Gorwits <oliver@cpan.org> Date: Mon May 22 22:01:50 2017 +0100 separate out is_*able last_* checks commitcf8589aba2Author: Oliver Gorwits <oliver@cpan.org> Date: Sun May 21 22:35:38 2017 +0100 change from ignore to skip name commited193356f8Author: Oliver Gorwits <oliver@cpan.org> Date: Sun May 21 14:52:33 2017 +0100 device_ignore table to track devices to skip in polling
		
			
				
	
	
		
			160 lines
		
	
	
		
			4.6 KiB
		
	
	
	
		
			Perl
		
	
	
	
	
	
			
		
		
	
	
			160 lines
		
	
	
		
			4.6 KiB
		
	
	
	
		
			Perl
		
	
	
	
	
	
| package App::Netdisco::Backend::Worker::Interactive::PortActions;
 | |
| 
 | |
| use App::Netdisco::Util::Port ':all';
 | |
| use App::Netdisco::Util::SNMP 'snmp_connect_rw';
 | |
| use App::Netdisco::Util::Device 'get_device';
 | |
| use App::Netdisco::Backend::Util ':all';
 | |
| 
 | |
| use Role::Tiny;
 | |
| use namespace::clean;
 | |
| 
 | |
| sub portname {
 | |
|   my ($self, $job) = @_;
 | |
|   return _set_port_generic($job, 'alias', 'name');
 | |
| }
 | |
| 
 | |
| sub portcontrol {
 | |
|   my ($self, $job) = @_;
 | |
| 
 | |
|   my $port = get_port($job->device, $job->port)
 | |
|     or return job_error(sprintf "Unknown port name [%s] on device [%s]",
 | |
|       $job->port, $job->device);
 | |
| 
 | |
|   my $reconfig_check = port_reconfig_check($port);
 | |
|   return job_error("Cannot alter port: $reconfig_check")
 | |
|     if $reconfig_check;
 | |
| 
 | |
|   # need to remove "-other" which appears for power/portcontrol
 | |
|   (my $sa = $job->subaction) =~ s/-\w+//;
 | |
|   $job->subaction($sa);
 | |
| 
 | |
|   if ($sa eq 'bounce') {
 | |
|       $job->subaction('down');
 | |
|       my @stat = _set_port_generic($job, 'up_admin');
 | |
|       return @stat if $stat[0] ne 'done';
 | |
|       $job->subaction('up');
 | |
|       return _set_port_generic($job, 'up_admin');
 | |
|   }
 | |
|   else {
 | |
|       return _set_port_generic($job, 'up_admin');
 | |
|   }
 | |
| }
 | |
| 
 | |
| sub vlan {
 | |
|   my ($self, $job) = @_;
 | |
| 
 | |
|   my $port = get_port($job->device, $job->port)
 | |
|     or return job_error(sprintf "Unknown port name [%s] on device [%s]",
 | |
|       $job->port, $job->device);
 | |
| 
 | |
|   my $port_reconfig_check = port_reconfig_check($port);
 | |
|   return job_error("Cannot alter port: $port_reconfig_check")
 | |
|     if $port_reconfig_check;
 | |
| 
 | |
|   my $vlan_reconfig_check = vlan_reconfig_check($port);
 | |
|   return job_error("Cannot alter vlan: $vlan_reconfig_check")
 | |
|     if $vlan_reconfig_check;
 | |
| 
 | |
|   my @stat = _set_port_generic($job, 'pvid'); # for Cisco trunk
 | |
|   return @stat if $stat[0] eq 'done';
 | |
|   return _set_port_generic($job, 'vlan');
 | |
| }
 | |
| 
 | |
| sub _set_port_generic {
 | |
|   my ($job, $slot, $column) = @_;
 | |
|   $column ||= $slot;
 | |
| 
 | |
|   my $device = get_device($job->device);
 | |
|   my $ip = $device->ip;
 | |
|   my $pn = $job->port;
 | |
|   my $data = $job->subaction;
 | |
| 
 | |
|   my $port = get_port($ip, $pn)
 | |
|     or return job_error("Unknown port name [$pn] on device [$ip]");
 | |
| 
 | |
|   if ($device->vendor ne 'netdisco') {
 | |
|       # snmp connect using rw community
 | |
|       my $info = snmp_connect_rw($ip)
 | |
|         or return job_defer("Failed to connect to device [$ip] to control port");
 | |
| 
 | |
|       my $iid = get_iid($info, $port)
 | |
|         or return job_error("Failed to get port ID for [$pn] from [$ip]");
 | |
| 
 | |
|       my $method = 'set_i_'. $slot;
 | |
|       my $rv = $info->$method($data, $iid);
 | |
| 
 | |
|       if (!defined $rv) {
 | |
|           return job_error(sprintf 'Failed to set [%s] %s to [%s] on [%s]: %s',
 | |
|                         $pn, $slot, $data, $ip, ($info->error || ''));
 | |
|       }
 | |
| 
 | |
|       # confirm the set happened
 | |
|       $info->clear_cache;
 | |
|       my $check_method = 'i_'. $slot;
 | |
|       my $state = ($info->$check_method($iid) || '');
 | |
|       if (ref {} ne ref $state or $state->{$iid} ne $data) {
 | |
|           return job_error("Verify of [$pn] $slot failed on [$ip]");
 | |
|       }
 | |
|   }
 | |
| 
 | |
|   # update netdisco DB
 | |
|   $port->update({$column => $data});
 | |
| 
 | |
|   return job_done("Updated [$pn] $slot status on [$ip] to [$data]");
 | |
| }
 | |
| 
 | |
| sub power {
 | |
|   my ($self, $job) = @_;
 | |
| 
 | |
|   my $port = get_port($job->device, $job->port)
 | |
|     or return job_error(sprintf "Unknown port name [%s] on device [%s]",
 | |
|       $job->port, $job->device);
 | |
| 
 | |
|   return job_error("No PoE service on port [%s] on device [%s]")
 | |
|     unless $port->power;
 | |
| 
 | |
|   my $reconfig_check = port_reconfig_check($port);
 | |
|   return job_error("Cannot alter port: $reconfig_check")
 | |
|     if $reconfig_check;
 | |
| 
 | |
|   my $device = get_device($job->device);
 | |
|   my $ip = $device->ip;
 | |
|   my $pn = $job->port;
 | |
| 
 | |
|   # munge data
 | |
|   (my $data = $job->subaction) =~ s/-\w+//; # remove -other
 | |
|   $data = 'true'  if $data =~ m/^(on|yes|up)$/;
 | |
|   $data = 'false' if $data =~ m/^(off|no|down)$/;
 | |
| 
 | |
|   # snmp connect using rw community
 | |
|   my $info = snmp_connect_rw($ip)
 | |
|     or return job_defer("Failed to connect to device [$ip] to control power");
 | |
| 
 | |
|   my $powerid = get_powerid($info, $port)
 | |
|     or return job_error("Failed to get power ID for [$pn] from [$ip]");
 | |
| 
 | |
|   my $rv = $info->set_peth_port_admin($data, $powerid);
 | |
| 
 | |
|   if (!defined $rv) {
 | |
|       return job_error(sprintf 'Failed to set [%s] power to [%s] on [%s]: %s',
 | |
|                     $pn, $data, $ip, ($info->error || ''));
 | |
|   }
 | |
| 
 | |
|   # confirm the set happened
 | |
|   $info->clear_cache;
 | |
|   my $state = ($info->peth_port_admin($powerid) || '');
 | |
|   if (ref {} ne ref $state or $state->{$powerid} ne $data) {
 | |
|       return job_error("Verify of [$pn] power failed on [$ip]");
 | |
|   }
 | |
| 
 | |
|   # update netdisco DB
 | |
|   $port->power->update({
 | |
|     admin => $data,
 | |
|     status => ($data eq 'false' ? 'disabled' : 'searching'),
 | |
|   });
 | |
| 
 | |
|   return job_done("Updated [$pn] power status on [$ip] to [$data]");
 | |
| }
 | |
| 
 | |
| 1;
 |