[OMPI devel] Strange schema error

2007-05-23 Thread George Bosilca 

Folks,

Starting from yesterday I'm unable to run any Open MPI application. I  
get an error in the schema URM component, which complain about a  
missing something ...


[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../ 
ompi-trunk/orte/mca/schema/base/schema_base_fns.c at line 163
[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../ 
ompi-trunk/orte/mca/rds/base/rds_base_registry_fns.c at line 81
[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in  
file ../../../../../ompi-trunk/orte/mca/rmgr/urm/rmgr_urm.c at line 398


The only thing I'm doing which is not completely default is that I  
specify the rds_hostfile_path in my Open MPI configuration file. I  
trim down the host file as well as the config file to their bare  
minimum but the errors is still popping up. I tried to reinstall  
everything cleanly from the beginning but it didn't solve any issue.


I'm the only one having issues right now ? Any idea on how to solve it ?

  Thanks,
george.

Re: [OMPI devel] Strange schema error

2007-05-23 Thread Ralph H Castain 
Just a quick glance (running out door) - it looks like Josh commented out a
critical piece of code in the rds hostfile component at line 442. It loads
the cell info into the name service so it can correctly respond to the query
you cite below.

You might try restoring that code - if you do, check to be sure you still
get a local_cellid=0 to be safe. If not, I'll have to fix it later today for
you.

I'm unaware of any recent changes, though, that would have caused that
behavior to suddenly surface - unless this got changed recently? Certainly,
nothing I installed in the last few days would have caused it to appear.

I've been running the trunk on both my Mac and odin for the last several
days without incident.

Ralph


On 5/23/07 8:41 AM, "George Bosilca"  wrote:

> Folks,
> 
> Starting from yesterday I'm unable to run any Open MPI application. I
> get an error in the schema URM component, which complain about a
> missing something ...
> 
> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
> ompi-trunk/orte/mca/schema/base/schema_base_fns.c at line 163
> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
> ompi-trunk/orte/mca/rds/base/rds_base_registry_fns.c at line 81
> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in
> file ../../../../../ompi-trunk/orte/mca/rmgr/urm/rmgr_urm.c at line 398
> 
> The only thing I'm doing which is not completely default is that I
> specify the rds_hostfile_path in my Open MPI configuration file. I
> trim down the host file as well as the config file to their bare
> minimum but the errors is still popping up. I tried to reinstall
> everything cleanly from the beginning but it didn't solve any issue.
> 
> I'm the only one having issues right now ? Any idea on how to solve it ?
> 
>Thanks,
>  george.
> 
> ___
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel

Re: [OMPI devel] Strange schema error

2007-05-23 Thread Ralph H Castain 
Actually, I think that is true (got back earlier than expected). The problem
really is that we had multiple compensating errors combined with an error
return that wasn't being checked.

I'll try to fix the basic problem(s).


On 5/23/07 9:31 AM, "Josh Hursey"  wrote:

> I haven't looked at this at all, but that line changed in r6813 which
> was Aug. 2005 so I would guess the problem is elsewhere. However with
> the recent ORTE changes maybe this is a side effect.
> 
> -- Josh
> 
> 
> On May 23, 2007, at 11:11 AM, Ralph H Castain wrote:
> 
>> Just a quick glance (running out door) - it looks like Josh
>> commented out a
>> critical piece of code in the rds hostfile component at line 442.
>> It loads
>> the cell info into the name service so it can correctly respond to
>> the query
>> you cite below.
>> 
>> You might try restoring that code - if you do, check to be sure you
>> still
>> get a local_cellid=0 to be safe. If not, I'll have to fix it later
>> today for
>> you.
>> 
>> I'm unaware of any recent changes, though, that would have caused that
>> behavior to suddenly surface - unless this got changed recently?
>> Certainly,
>> nothing I installed in the last few days would have caused it to
>> appear.
>> 
>> I've been running the trunk on both my Mac and odin for the last
>> several
>> days without incident.
>> 
>> Ralph
>> 
>> 
>> On 5/23/07 8:41 AM, "George Bosilca"  wrote:
>> 
>>> Folks,
>>> 
>>> Starting from yesterday I'm unable to run any Open MPI application. I
>>> get an error in the schema URM component, which complain about a
>>> missing something ...
>>> 
>>> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
>>> ompi-trunk/orte/mca/schema/base/schema_base_fns.c at line 163
>>> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
>>> ompi-trunk/orte/mca/rds/base/rds_base_registry_fns.c at line 81
>>> [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in
>>> file ../../../../../ompi-trunk/orte/mca/rmgr/urm/rmgr_urm.c at
>>> line 398
>>> 
>>> The only thing I'm doing which is not completely default is that I
>>> specify the rds_hostfile_path in my Open MPI configuration file. I
>>> trim down the host file as well as the config file to their bare
>>> minimum but the errors is still popping up. I tried to reinstall
>>> everything cleanly from the beginning but it didn't solve any issue.
>>> 
>>> I'm the only one having issues right now ? Any idea on how to
>>> solve it ?
>>> 
>>>Thanks,
>>>  george.
>>> 
>>> ___
>>> devel mailing list
>>> de...@open-mpi.org
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>> 
>> 
>> ___
>> devel mailing list
>> de...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
> 
> ___
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel

Re: [OMPI devel] Strange schema error

2007-05-23 Thread Ralph H Castain 
Okay, this is now fixed as of r14732.

Thanks (and apologies) to George for spotting it.

Ralph



On 5/23/07 9:57 AM, "Ralph H Castain"  wrote:

> Actually, I think that is true (got back earlier than expected). The problem
> really is that we had multiple compensating errors combined with an error
> return that wasn't being checked.
> 
> I'll try to fix the basic problem(s).
> 
> 
> On 5/23/07 9:31 AM, "Josh Hursey"  wrote:
> 
>> I haven't looked at this at all, but that line changed in r6813 which
>> was Aug. 2005 so I would guess the problem is elsewhere. However with
>> the recent ORTE changes maybe this is a side effect.
>> 
>> -- Josh
>> 
>> 
>> On May 23, 2007, at 11:11 AM, Ralph H Castain wrote:
>> 
>>> Just a quick glance (running out door) - it looks like Josh
>>> commented out a
>>> critical piece of code in the rds hostfile component at line 442.
>>> It loads
>>> the cell info into the name service so it can correctly respond to
>>> the query
>>> you cite below.
>>> 
>>> You might try restoring that code - if you do, check to be sure you
>>> still
>>> get a local_cellid=0 to be safe. If not, I'll have to fix it later
>>> today for
>>> you.
>>> 
>>> I'm unaware of any recent changes, though, that would have caused that
>>> behavior to suddenly surface - unless this got changed recently?
>>> Certainly,
>>> nothing I installed in the last few days would have caused it to
>>> appear.
>>> 
>>> I've been running the trunk on both my Mac and odin for the last
>>> several
>>> days without incident.
>>> 
>>> Ralph
>>> 
>>> 
>>> On 5/23/07 8:41 AM, "George Bosilca"  wrote:
>>> 
 Folks,
 
 Starting from yesterday I'm unable to run any Open MPI application. I
 get an error in the schema URM component, which complain about a
 missing something ...
 
 [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
 ompi-trunk/orte/mca/schema/base/schema_base_fns.c at line 163
 [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in file ../../../../
 ompi-trunk/orte/mca/rds/base/rds_base_registry_fns.c at line 81
 [dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in
 file ../../../../../ompi-trunk/orte/mca/rmgr/urm/rmgr_urm.c at
 line 398
 
 The only thing I'm doing which is not completely default is that I
 specify the rds_hostfile_path in my Open MPI configuration file. I
 trim down the host file as well as the config file to their bare
 minimum but the errors is still popping up. I tried to reinstall
 everything cleanly from the beginning but it didn't solve any issue.
 
 I'm the only one having issues right now ? Any idea on how to
 solve it ?
 
Thanks,
  george.
 
 ___
 devel mailing list
 de...@open-mpi.org
 http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>> 
>>> 
>>> ___
>>> devel mailing list
>>> de...@open-mpi.org
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>> 
>> ___
>> devel mailing list
>> de...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
> 
> 
> ___
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel

Re: [OMPI devel] Strange schema error

2007-05-23 Thread George Bosilca 
Thanks Ralph. I confirm, the problem seems to be fixed by your last  
commit.


Thanks,
  george.

On May 23, 2007, at 12:32 PM, Ralph H Castain wrote:


Okay, this is now fixed as of r14732.

Thanks (and apologies) to George for spotting it.

Ralph



On 5/23/07 9:57 AM, "Ralph H Castain"  wrote:

Actually, I think that is true (got back earlier than expected).  
The problem
really is that we had multiple compensating errors combined with  
an error

return that wasn't being checked.

I'll try to fix the basic problem(s).


On 5/23/07 9:31 AM, "Josh Hursey"  wrote:

I haven't looked at this at all, but that line changed in r6813  
which
was Aug. 2005 so I would guess the problem is elsewhere. However  
with

the recent ORTE changes maybe this is a side effect.

-- Josh


On May 23, 2007, at 11:11 AM, Ralph H Castain wrote:


Just a quick glance (running out door) - it looks like Josh
commented out a
critical piece of code in the rds hostfile component at line 442.
It loads
the cell info into the name service so it can correctly respond to
the query
you cite below.

You might try restoring that code - if you do, check to be sure you
still
get a local_cellid=0 to be safe. If not, I'll have to fix it later
today for
you.

I'm unaware of any recent changes, though, that would have  
caused that

behavior to suddenly surface - unless this got changed recently?
Certainly,
nothing I installed in the last few days would have caused it to
appear.

I've been running the trunk on both my Mac and odin for the last
several
days without incident.

Ralph


On 5/23/07 8:41 AM, "George Bosilca"  wrote:


Folks,

Starting from yesterday I'm unable to run any Open MPI  
application. I

get an error in the schema URM component, which complain about a
missing something ...

[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in  
file ../../../../

ompi-trunk/orte/mca/schema/base/schema_base_fns.c at line 163
[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in  
file ../../../../

ompi-trunk/orte/mca/rds/base/rds_base_registry_fns.c at line 81
[dancer:01083] [0,0,0] ORTE_ERROR_LOG: Not found in
file ../../../../../ompi-trunk/orte/mca/rmgr/urm/rmgr_urm.c at
line 398

The only thing I'm doing which is not completely default is that I
specify the rds_hostfile_path in my Open MPI configuration file. I
trim down the host file as well as the config file to their bare
minimum but the errors is still popping up. I tried to reinstall
everything cleanly from the beginning but it didn't solve any  
issue.


I'm the only one having issues right now ? Any idea on how to
solve it ?

   Thanks,
 george.

___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel



___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel


___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel



___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel



___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel




smime.p7s
Description: S/MIME cryptographic signature