Hi,
The ganglia test fails with the following output:
> Client nodes: oscarnode1 oscarnode3 oscarnode4 oscarnode6
> Match pattern:
> is005760.intra.cea.Fr|oscarnode1|oscarnode3|oscarnode4|oscarnode6
> Number of hosts matched: 4
> Gstat output:
> CLUSTER INFORMATION
> Name: SSTM Cluster
> Hosts: 5
> Gexec Hosts: 0
> Dead Hosts: 0
> Localtime: Mon Dec 14 15:24:42 2009
>
> CLUSTER HOSTS
> Hostname LOAD CPU Gexec
> CPUs (Procs/Total) [ 1, 5, 15min] [ User, Nice, System, Idle, Wio]
>
> head
> 16 ( 1/ 396) [ 1.29, 1.15, 1.10] [ 0.3, 0.0, 6.3, 93.1,
> 0.3] OFF
> oscarnode6
> 12 ( 0/ 170) [ 0.00, 0.00, 0.00] [ 0.1, 0.0, 0.0, 99.8,
> 0.1] OFF
> oscarnode1
> 12 ( 0/ 169) [ 0.00, 0.04, 0.01] [ 0.0, 0.0, 0.0, 100.0,
> 0.0] OFF
> oscarnode4
> 12 ( 0/ 170) [ 0.06, 0.03, 0.01] [ 0.0, 0.0, 0.0, 99.9,
> 0.1] OFF
> oscarnode3
> 12 ( 0/ 170) [ 0.07, 0.02, 0.00] [ 0.1, 0.0, 0.1, 99.7,
> 0.2] OFF
>
> The number of nodes expected is different from the number of nodes detected.
> Check to see if gmond is running on all your nodes and make sure that you
> are not having any network issues.
1st thought that the fault belonged to me when fixing the Nodes entry name vs
fqdn vs hostname (hostname does now contains the non fqdn hostname)
but it seems that the problem is from elsewhere:
Indeed, the Match pattern contains the FQDN, but the listed nodes does not
contains either basic hostname of head or fqdn of head. Instead it contains
"head".
And it looks like it tries to compare "head" with "the fqdn hostname" which
fails.
mysql> select * from Nodes;
+------------+---------+-----------+--------------+----------------------+---------------+------------+----+----------+-----------+--------------+------+------+-------+---------+
| cluster_id | cpu_num | cpu_speed | dns_domain | fqdn |
group_name | hostname | id | image_id | installer | name | ram |
swap | units | virtual |
+------------+---------+-----------+--------------+----------------------+---------------+------------+----+----------+-----------+--------------+------+------+-------+---------+
| 1 | NULL | NULL | intra.cea.fr | is005760intra.cea.fr |
oscar_server | is005760 | 1 | 0 | NULL | oscar_server | NULL |
NULL | NULL | NULL |
| 1 | NULL | NULL | NULL | NULL |
oscar_clients | oscarnode1 | 9 | 2 | sis | oscarnode1 | NULL |
NULL | NULL | NULL |
| 1 | NULL | NULL | NULL | NULL |
oscar_clients | oscarnode3 | 11 | 2 | sis | oscarnode3 | NULL |
NULL | NULL | NULL |
| 1 | NULL | NULL | NULL | NULL |
oscar_clients | oscarnode4 | 12 | 2 | sis | oscarnode4 | NULL |
NULL | NULL | NULL |
| 1 | NULL | NULL | NULL | NULL |
oscar_clients | oscarnode6 | 14 | 2 | sis | oscarnode6 | NULL |
NULL | NULL | NULL |
+------------+---------+-----------+--------------+----------------------+---------------+------------+----+----------+-----------+--------------+------+------+-------+---------+
5 rows in set (0.00 sec)
I'll give a look at that tomorrow.
Best regards,
Olivier.
--
Olivier LAHAYE
CEA Saclay
DRT-LIST-DETECS-SSTM
------------------------------------------------------------------------------
Return on Information:
Google Enterprise Search pays you back
Get the facts.
http://p.sf.net/sfu/google-dev2dev
_______________________________________________
Oscar-devel mailing list
Oscar-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/oscar-devel
