[GE users] Gaussian doesn't parallel under Linux and AIX

schummer at rhrk.uni-kl.de schummer at rhrk.uni-kl.de
Mon Jul 12 14:45:03 BST 2004


    [ The following text is in the "iso-8859-15" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]


On 12-Jul-2004 John Hearns wrote:
> On Mon, 2004-07-12 at 11:12, schummer at rhrk.uni-kl.de wrote:
>> I have the following problem: 
>> 
>> Gaussian doesn't run parallel in Batchjobs (SGE 5.3p6) on our Linux-Cluster
>> (amd64) 
> I support a computational chemistry cluster,
> which runs SGE on amd64
> 
>> and under AIX5.2.L. Gaussian hangs in link 0.
> Apologies, but I don't understand this.
> Can you send some output?

Input:

%mem=500MB
%nosave
%chk=v.chk
! Naechste Zeile aktiviert 2 Proz.
%nprocshared=2
 
 
#p hf/6-31+G(2df,p) Integral(FineGrid) gfinput sp
 
HNVCl3
 
 0 1
 n
 v   1 vn2
cl   2 clv3       1 clvn3
cl   2 clv4       3 clvcl4       1 dih4
cl   2 clv5       3 clvcl5       4 dih5
 h   1 hn6        2 hnv6         4 dih6
  
vn2         1.597805
clv3        2.151202
clvn3       107.289
clv4        2.151243
clvcl4      111.556
dih4       -117.239
clv5        2.151258
clvcl5      111.569
dih5       -125.508
hn6         1.020612
hnv6        179.995
dih6         91.257

1. Run in dialog:

Top (show threads on):

 15:13:04  up 11 days, 22:15,  1 user,  load average: 0.88, 0.23, 0.14
54 processes: 50 sleeping, 4 running, 0 zombie, 0 stopped
CPU states:  cpu    user    nice  system    irq  softirq  iowait    idle
           total   99.9%    0.0%    0.1%   0.0%     0.0%    0.0%    0.0%
           cpu00  100.0%    0.0%    0.0%   0.0%     0.0%    0.0%    0.0%
           cpu01   99.8%    0.0%    0.2%   0.0%     0.0%    0.0%    0.0%
Mem:  4016892k av, 1525104k used, 2491788k free,       0k shrd,   61640k buff
                    815704k actv,  472056k in_d,       8k in_c
Swap: 4194296k av,   19540k used, 4174756k free                  695340k cached
                                                                               
                                                                             
  PID USER     PRI  NI  SIZE  RSS SHARE STAT %CPU %MEM   TIME CPU COMMAND
14665 schummer  25   0  517M 517M  2496 R    49.9 13.1   0:28   0 l502.exe
14574 schummer  25   0  517M 517M  2496 R    49.7 13.1   0:37   1 l502.exe
    1 root      15   0   520  476   452 S     0.0  0.0   0:07   0 init
    2 root      RT   0     0    0     0 SW    0.0  0.0   0:00   0 migration/0
    3 root      RT   0     0    0     0 SW    0.0  0.0   0:00   1 migration/1
 
2. Batch:

Top-output:

 15:30:10  up 11 days, 22:32,  1 user,  load average: 2.91, 1.75, 0.76
54 processes: 52 sleeping, 2 running, 0 zombie, 0 stopped
CPU states:  cpu    user    nice  system    irq  softirq  iowait    idle
           total   18.4%    0.1%   33.0%   0.6%     1.2%   39.7%    7.0%
           cpu00   36.6%    0.0%   59.8%   1.2%     2.4%    0.0%    0.0%
           cpu01    0.2%    0.2%    6.2%   0.0%     0.0%   79.4%   14.0%
Mem:  4016892k av, 4007392k used,    9500k free,       0k shrd,  214764k buff
                    696520k actv, 2905120k in_d,   63224k in_c
Swap: 4194296k av,       0k used, 4194296k free                 3492280k cached
                                                                               
                                                                             
  PID USER     PRI  NI  SIZE  RSS SHARE STAT %CPU %MEM   TIME CPU COMMAND
30784 schummer  25   0 10732  10M  2240 R    48.1  0.2   6:00   1 l1.exe
30942 root      18   2  1456 1456   384 D N   2.7  0.0   0:26   1 cp
    7 root      15   0     0    0     0 SW    0.2  0.0   1:19   1 kswapd

ps:

UID        PID  PPID  C STIME TTY          TIME CMD
schummer 30782 30780  0 15:23 ?        00:00:00 bash
/opt/sge/default/spool/lc35/job_scripts/5863
schummer 30783 30782  0 15:23 ?        00:00:00 /opt/g03/g03
schummer 30784 30783 97 15:23 ?        00:15:25 /opt/g03/l1.exe
/usr/people/schummer/sge/gaussian/weber/Gau-30783.inp
-scrdir=/usr/people/schummer/sge/gaussi
  
> 
> Also, could you try some simple parallel examples and see if they run?
> 
> 
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail: users-help at gridengine.sunsource.net
> 

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list