Nagios Support Forum

Code: Select all

[10-24-2017 11:56:12] NPCD: ERROR: Executed command exits with return code '7'
[10-24-2017 11:56:12] NPCD: ERROR: Command line was '/usr/local/nagios/libexec/process_perfdata.pl -n -b /var/nagiosramdisk/spool/perfdata//1508838959.perfdata.service'
[10-24-2017 11:57:24] NPCD: WARN: MAX load reached: load 10.640000/10.000000 at i=0
[10-24-2017 11:57:39] NPCD: WARN: MAX load reached: load 10.260000/10.000000 at i=1
[10-24-2017 12:00:11] NPCD: ERROR: Executed command exits with return code '7'
[10-24-2017 12:00:11] NPCD: ERROR: Command line was '/usr/local/nagios/libexec/process_perfdata.pl -n -b /var/nagiosramdisk/spool/perfdata//1508839199.perfdata.service'
[10-24-2017 12:00:31] NPCD: ERROR: Executed command exits with return code '7'
[10-24-2017 12:00:31] NPCD: ERROR: Command line was '/usr/local/nagios/libexec/process_perfdata.pl -n -b /var/nagiosramdisk/spool/perfdata//1508839215.perfdata.service'

Code: Select all

2017-10-24 12:09:18 [14134] [0] *** TIMEOUT: Timeout after 5 secs. ***
2017-10-24 12:09:18 [14134] [0] *** TIMEOUT: Deleting current file to avoid NPCD loops
2017-10-24 12:09:18 [14134] [0] *** TIMEOUT: Please check your npcd.cfg
2017-10-24 12:09:18 [14134] [0] *** TIMEOUT: /var/nagiosramdisk/spool/perfdata//1508839749.perfdata.service-PID-14134 deleted
2017-10-24 12:09:18 [14134] [0] *** Timeout while processing Host: "<hostname>" Service: "System_-_Network_bandwidth"
2017-10-24 12:09:18 [14134] [0] *** process_perfdata.pl terminated on signal ALRM

Code: Select all

# grep -i time /usr/local/nagios/etc/pnp/process_perfdata.cfg
TIMEOUT = 5
[root@hq-nagios-xi01 var]# grep -ri time /usr/local/nagios/etc/pnp/npcd.cfg
# sleep_time - how many seconds should npcd wait between dirscans
# sleep_time = 15 (default)
sleep_time = 15

Code: Select all

MariaDB [(none)]> SELECT count(*) from nagios.nagios_logentries;
+----------+
| count(*) |
+----------+
| 10168443 |
+----------+
1 row in set (0.00 sec)

Code: Select all

MariaDB [(none)]> SELECT table_name AS table_name, round(((data_length + index_length) / 1024 / 1024), 2) Size_in_MB FROM information_schema.TABLES WHERE table_schema = 'nagios' AND table_name = 'nagios_logentries';
+-------------------+------------+
| table_name        | Size_in_MB |
+-------------------+------------+
| nagios_logentries |    2465.89 |
+-------------------+------------+
1 row in set (0.00 sec)

Code: Select all

MariaDB [nagios]> select logentry_time from nagios_logentries order by logentry_time ASC limit 1;
+---------------------+
| logentry_time       |
+---------------------+
| 2017-07-26 15:10:01 |
+---------------------+
1 row in set (0.00 sec)

Code: Select all

MariaDB [nagios]> SELECT count(*) from nagios.nagios_notifications;
+----------+
| count(*) |
+----------+
|  6077202 |
+----------+
1 row in set (0.00 sec)

Code: Select all

MariaDB [nagios]> select start_time from nagios_notifications ORDER BY notification_id  ASC limit 1;
+---------------------+
| start_time          |
+---------------------+
| 2017-07-26 15:10:01 |
+---------------------+
1 row in set (0.01 sec)

Code: Select all

/usr/local/nagios/etc/pnp/process_perfdata.cfg
/usr/local/nagios/etc/pnp/npcd.cfg

Code: Select all

Oct 25 00:32:12 hq-nagios-xi01 ndo2db: Warning: Retrying message send. This can occur because you have too few messages allowed or too few total bytes allowed in message queues. You are currently using 384000 of 512000 messages and 393216000 of 393216000 bytes in the queue. See README for kernel tuning options.

Code: Select all

Oct 25 00:40:54 hq-nagios-xi01 nagios: Warning: The check of host 'XXXX' looks like it was orphaned (results never came back).  I'm scheduling an immediate che
ck of the host...

Code: Select all

kernel.msgmnb = 786432000
kernel.msgmax = 262144000
kernel.shmmax = 4294967295
kernel.shmall = 268435456
kernel.msgmni = 512000

Code: Select all

=======================
nagios offloaded database repair succeeded
nagiosql offloaded database repair succeeded
nagiosxi offloaded database repair succeeded

Code: Select all

30539305 - 56 - REPAIR TABLE `nagios_statehistory`
30539363 - 57 - OPTIMIZE TABLE nagios_logentries

Code: Select all

Every 2.0s: ipcs -q                          Wed Oct 25 10:40:46 2017


------ Message Queues --------
key        msqid      owner      perms      used-bytes   messages
0xba000002 0          nagios     600        786432000    768000
0x9f000002 32769      nagios     600        175332352    171223

Code: Select all

    <p><pre>SQL Error [nagiosxi] : MySQL server has gone away</pre></p>

Code: Select all

# mysqladmin status
Uptime: 15129774  Threads: 95  Questions: 23546418316  Slow queries: 1808  Opens: 739472  Flush tables: 10  Open tables: 251  Queries per second avg: 1556.296

Code: Select all

MariaDB [mysql]> SELECT table_name AS table_name, engine, table_rows, round(((data_length + index_length) / 1024 / 1024), 2) Size_in_MB FROM information_schema.TABLES WHERE table_rows > 1000000;
+----------------------+--------+------------+------------+
| table_name           | engine | table_rows | Size_in_MB |
+----------------------+--------+------------+------------+
| nagios_logentries    | MyISAM |    5942113 |    1496.32 |
| nagios_notifications | MyISAM |    3402418 |    1205.06 |
| nagios_statehistory  | MyISAM |    5707759 |     937.75 |
+----------------------+--------+------------+------------+
3 rows in set (0.35 sec)