Re: [OMPI devel] Switching away from SVN?

[Jeff Squyres]

Cool -- thanks Roland!

For anyone who wants to play with the entire history of OMPI in git  
(as of last night or so -- this git repository is *not* being kept in  
sync with SVN), I cloned the tree that Roland created and put it here:


http://www.open-mpi.org/~jsquyres/unofficial/ompi.git

So you can:

git clone http://www.open-mpi.org/~jsquyres/unofficial/ompi.git

And then work with local git operations from there.



On Mar 20, 2008, at 8:53 PM, Roland Dreier wrote:

 has some interesting
info about svn->git conversions (and svn vs. next-gen distibuted
systems in general).

Also, out of curiousity I tried doing

   git-svn clone --stdlayout http://svn.open-mpi.org/svn/ompi/

and it seemed to work fine (git-svn is part of the main git
distribution).  The only obvious thing missing is that you would
probably want to set up an author file for a real conversion, so that
you get real names instead of just "jsquyres".  It took a while to
run, mostly because it has to grab each svn changeset one by one.

The interesting thing is that a checkout of the current ompi tree
seems to be about 37 MB, while .git directory of my repository, which
has the entire history of all branches of the svn repository plus
1.6MB of svn metadata is 36 MB.  And git can do fun stuff like

   git diff v1.1..v1.2

in half a second (it generates a 274858 line diff).  It can generate
the full 116320 line (11164 commit) log of the trunk in .3 seconds.

Jeff, if you want to see the repository, it is in

   /data/home/roland/ompi.git

Feel free to make it available however you want (it's your data of  
course).


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



--
Jeff Squyres
Cisco Systems

[OMPI devel] IRIX autoconf failure.

[Regan Russell]

Hello,

I am having problems with the Assembler section of the  GNU autoconf stuff on 
OpenMPI.
Is anyone willing to work with me to get this up and running...?

*** Assembler
checking dependency style of gcc... gcc3
checking for BSD- or MS-compatible name lister (nm)... /usr/bin/nm -B
checking the name lister (/usr/bin/nm -B) interface... BSD nm
checking for fgrep... /sbin/grep -F
checking if need to remove -g from CCASFLAGS... no
checking whether to enable smp locks... yes
checking if .proc/endp is needed... no
checking directive for setting text section... .text
checking directive for exporting symbols... .globl
checking for objdump... no
checking if .note.GNU-stack is needed... no
checking suffix for labels... :
checking prefix for global symbol labels... none
configure: error: Could not determine global symbol label prefix
minnie:openmpi-1.2.6rc3r17884> 
minnie:openmpi-1.2.6rc3r17884> hinv
CPU: MIPS R14000 Processor Chip Revision: 2.4
FPU: MIPS R14010 Floating Point Chip Revision: 2.4
Processor 0: 600 MHZ IP35 
Processor 1: 600 MHZ IP35 
Processor 2: 600 MHZ IP35 
Processor 3: 600 MHZ IP35 
Processor 4: 500 MHZ IP35 
Processor 5: 500 MHZ IP35 
Processor 6: 500 MHZ IP35 
Processor 7: 500 MHZ IP35 
Main memory size: 8192 Mbytes
Instruction cache size: 32 Kbytes
Data cache size: 32 Kbytes
...

minnie:openmpi-1.2.6rc3r17884> uname -aR
IRIX64 minnie 6.5 6.5.25m 07080049 IP35

cc -v
MIPSpro Compilers: Version 7.4.4m


Thanks,


Regan Russell BSc.


_
Are you paid what you're worth? Find out: SEEK Salary Centre
http://a.ninemsn.com.au/b.aspx?URL=http%3A%2F%2Fninemsn%2Eseek%2Ecom%2Eau%2Fcareer%2Dresources%2Fsalary%2Dcentre%2F%3Ftracking%3Dsk%3Ahet%3Asc%3Anine%3A0%3Ahot%3Atext&_t=764565661&_r=OCT07_endtext_salary&_m=EXT

Re: [OMPI devel] Switching away from SVN?

[Ralph H Castain]

Great!

I don't have a religious preference between the options (hg vs git vs ??),
but think we should definitely move away from svn.

Someone mentioned discussing this at some upcoming meeting? Could you send
around some info on this, since (ahem) some of us at least are -not-
involved in the wonderful MPI Forum, and have no idea when this might be
taking place???

Thanks
Ralph



On 3/21/08 6:52 AM, "Jeff Squyres"  wrote:

> Cool -- thanks Roland!
> 
> For anyone who wants to play with the entire history of OMPI in git
> (as of last night or so -- this git repository is *not* being kept in
> sync with SVN), I cloned the tree that Roland created and put it here:
> 
>  http://www.open-mpi.org/~jsquyres/unofficial/ompi.git
> 
> So you can:
> 
>  git clone http://www.open-mpi.org/~jsquyres/unofficial/ompi.git
> 
> And then work with local git operations from there.
> 
> 
> 
> On Mar 20, 2008, at 8:53 PM, Roland Dreier wrote:
>>  has some interesting
>> info about svn->git conversions (and svn vs. next-gen distibuted
>> systems in general).
>> 
>> Also, out of curiousity I tried doing
>> 
>>git-svn clone --stdlayout http://svn.open-mpi.org/svn/ompi/
>> 
>> and it seemed to work fine (git-svn is part of the main git
>> distribution).  The only obvious thing missing is that you would
>> probably want to set up an author file for a real conversion, so that
>> you get real names instead of just "jsquyres".  It took a while to
>> run, mostly because it has to grab each svn changeset one by one.
>> 
>> The interesting thing is that a checkout of the current ompi tree
>> seems to be about 37 MB, while .git directory of my repository, which
>> has the entire history of all branches of the svn repository plus
>> 1.6MB of svn metadata is 36 MB.  And git can do fun stuff like
>> 
>>git diff v1.1..v1.2
>> 
>> in half a second (it generates a 274858 line diff).  It can generate
>> the full 116320 line (11164 commit) log of the trunk in .3 seconds.
>> 
>> Jeff, if you want to see the repository, it is in
>> 
>>/data/home/roland/ompi.git
>> 
>> Feel free to make it available however you want (it's your data of
>> course).
>> 
>> - R.
>> ___
>> devel mailing list
>> de...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
> 

Re: [OMPI devel] Switching away from SVN?

[Jeff Squyres]

The next MPI Forum meeting is April 28-30 in Chicago, IL.  Following  
what we have been doing for the past 2 meetings, this means that the  
OMPI meeting will be 1-5pm US Central time on Wednesday, 30 April.


We could probably have a teleconf portion for this, because I would  
imagine that this kind of discussion (perhaps with some hands-on and/ 
or some brief slides) could translate well to a remote audience for  
those who don't want to travel just for a 1 afternoon meeting.




On Mar 21, 2008, at 9:26 AM, Ralph H Castain wrote:

Great!

I don't have a religious preference between the options (hg vs git  
vs ??),

but think we should definitely move away from svn.

Someone mentioned discussing this at some upcoming meeting? Could  
you send

around some info on this, since (ahem) some of us at least are -not-
involved in the wonderful MPI Forum, and have no idea when this  
might be

taking place???

Thanks
Ralph



On 3/21/08 6:52 AM, "Jeff Squyres"  wrote:


Cool -- thanks Roland!

For anyone who wants to play with the entire history of OMPI in git
(as of last night or so -- this git repository is *not* being kept in
sync with SVN), I cloned the tree that Roland created and put it  
here:


http://www.open-mpi.org/~jsquyres/unofficial/ompi.git

So you can:

git clone http://www.open-mpi.org/~jsquyres/unofficial/ompi.git

And then work with local git operations from there.



On Mar 20, 2008, at 8:53 PM, Roland Dreier wrote:

 has some interesting
info about svn->git conversions (and svn vs. next-gen distibuted
systems in general).

Also, out of curiousity I tried doing

  git-svn clone --stdlayout http://svn.open-mpi.org/svn/ompi/

and it seemed to work fine (git-svn is part of the main git
distribution).  The only obvious thing missing is that you would
probably want to set up an author file for a real conversion, so  
that

you get real names instead of just "jsquyres".  It took a while to
run, mostly because it has to grab each svn changeset one by one.

The interesting thing is that a checkout of the current ompi tree
seems to be about 37 MB, while .git directory of my repository,  
which

has the entire history of all branches of the svn repository plus
1.6MB of svn metadata is 36 MB.  And git can do fun stuff like

  git diff v1.1..v1.2

in half a second (it generates a 274858 line diff).  It can generate
the full 116320 line (11164 commit) log of the trunk in .3 seconds.

Jeff, if you want to see the repository, it is in

  /data/home/roland/ompi.git

Feel free to make it available however you want (it's your data of
course).

- R.
___
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



--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] Switching away from SVN?

[Ralph H Castain]

On 3/21/08 7:41 AM, "Jeff Squyres"  wrote:

> The next MPI Forum meeting is April 28-30 in Chicago, IL.  Following
> what we have been doing for the past 2 meetings, this means that the
> OMPI meeting will be 1-5pm US Central time on Wednesday, 30 April.
> 
> We could probably have a teleconf portion for this, because I would
> imagine that this kind of discussion (perhaps with some hands-on and/
> or some brief slides) could translate well to a remote audience for
> those who don't want to travel just for a 1 afternoon meeting.

That would really help...thanks!

> 
> 
> 
> On Mar 21, 2008, at 9:26 AM, Ralph H Castain wrote:
>> Great!
>> 
>> I don't have a religious preference between the options (hg vs git
>> vs ??),
>> but think we should definitely move away from svn.
>> 
>> Someone mentioned discussing this at some upcoming meeting? Could
>> you send
>> around some info on this, since (ahem) some of us at least are -not-
>> involved in the wonderful MPI Forum, and have no idea when this
>> might be
>> taking place???
>> 
>> Thanks
>> Ralph
>> 
>> 
>> 
>> On 3/21/08 6:52 AM, "Jeff Squyres"  wrote:
>> 
>>> Cool -- thanks Roland!
>>> 
>>> For anyone who wants to play with the entire history of OMPI in git
>>> (as of last night or so -- this git repository is *not* being kept in
>>> sync with SVN), I cloned the tree that Roland created and put it
>>> here:
>>> 
>>> http://www.open-mpi.org/~jsquyres/unofficial/ompi.git
>>> 
>>> So you can:
>>> 
>>> git clone http://www.open-mpi.org/~jsquyres/unofficial/ompi.git
>>> 
>>> And then work with local git operations from there.
>>> 
>>> 
>>> 
>>> On Mar 20, 2008, at 8:53 PM, Roland Dreier wrote:
  has some interesting
 info about svn->git conversions (and svn vs. next-gen distibuted
 systems in general).
 
 Also, out of curiousity I tried doing
 
   git-svn clone --stdlayout http://svn.open-mpi.org/svn/ompi/
 
 and it seemed to work fine (git-svn is part of the main git
 distribution).  The only obvious thing missing is that you would
 probably want to set up an author file for a real conversion, so
 that
 you get real names instead of just "jsquyres".  It took a while to
 run, mostly because it has to grab each svn changeset one by one.
 
 The interesting thing is that a checkout of the current ompi tree
 seems to be about 37 MB, while .git directory of my repository,
 which
 has the entire history of all branches of the svn repository plus
 1.6MB of svn metadata is 36 MB.  And git can do fun stuff like
 
   git diff v1.1..v1.2
 
 in half a second (it generates a 274858 line diff).  It can generate
 the full 116320 line (11164 commit) log of the trunk in .3 seconds.
 
 Jeff, if you want to see the repository, it is in
 
   /data/home/roland/ompi.git
 
 Feel free to make it available however you want (it's your data of
 course).
 
 - R.
 ___
 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
> 

[OMPI devel] op changes reverted

[Jeff Squyres]

The op changes from last night were still resulting in broken builds  
this morning, so I have backed them out.


Please see the details here:

https://svn.open-mpi.org/trac/ompi/changeset/17908

--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] IRIX autoconf failure.

[Brian W. Barrett]

On Fri, 21 Mar 2008, Regan Russell wrote:


I am having problems with the Assembler section of the  GNU autoconf stuff on 
OpenMPI.
Is anyone willing to work with me to get this up and running...?


As a warning, MIPS / IRIX is not currently on the list of Open MPI 
supported platforms, so there may be some issues that we can't overcome. 
But this is usually a pretty simple thing -- can you send the config.log 
file generated by configure?


Thanks,

Brian

[OMPI devel] New libevent to trunk?

[Jeff Squyres]

Josh --

Where do we stand on bringing in the new libevent to the trunk this  
weekend?  Is it ok to import, or do you need more time to work with  
the ramifications to the FT stuff?


--
Jeff Squyres
Cisco Systems

[OMPI devel] Fwd: [all-osl-users] Short outage of the OSL web/mail servers

[Jeff Squyres]

FYI (this affects all services of www.open-mpi.org and open-mpi.org,  
but not svn.open-mpi.org).



Begin forwarded message:

Date: March 21, 2008 12:01:09 PM EDT
Subject: [all-osl-users] Short outage of the OSL web/mail servers

Hi,

The OSL web/mail servers need to reboot on Mar 24, 2008. There will  
be a short outage of the following services:

- web services
- send/receive mails via mail.osl.iu.edu
- jabber
- postgresql
- mailman
- hypermail

The reboot time on Mar 24, 2008 :
- 5:00am-5:30am Pacific US time
- 6:00am-6:30am Mountain US time
- 7:00am-7:30am Central US time
- 8:00am-8:30am Eastern US time
- 12:00pm-12:30pm GMT

Please let me know if you have any issues or questions about this  
outage.


Regards,

--
- DongInn



--
Jeff Squyres
Cisco Systems

[OMPI devel] Makefile.am updates

[Jeff Squyres]

Just wanted to give a heads-up to developers on two changes that will  
be coming in in the [hopefully] not-distant future:


1. Per recent off-list discussions about the build system, I have done  
some cleanups and standardizations in the various */tools/*/ 
Makefile.am files.  A commit is coming soon that will:

  - Somewhat simplify these Makefile.am's
  - Make them consistent with each other (do similar actions in  
similar ways)
  - Update to remove old kruft that was required by older versions of  
AM


This work is nearly done; barring any problems from a code review,  
it'll likely be committed soon.


2. Per discussions on the GNU libtool list and some advice from the  
ever-helpful Ralf W., I now know how to remove much of the code  
duplication in nearly every OMPI component Makefile.am.  The resulting  
Makefile.am's are much smaller and simpler.


This work is barely started; I'll likely do this with low frequency  
over time (when I'm bored/brain-fried/procrastinating real work/etc.)  
and make a big commit when it's all done.


--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] New libevent to trunk?

[Josh Hursey]

Go ahead and bring it in. I have c/r working with forcing poll for  
the event engine via the amca file. Supporting the other mechanisms  
will take a while and should not prevent this from being merged into  
the trunk.


Thanks for checking though.
Josh

On Mar 21, 2008, at 11:53 AM, Jeff Squyres wrote:

Josh --

Where do we stand on bringing in the new libevent to the trunk this
weekend?  Is it ok to import, or do you need more time to work with
the ramifications to the FT stuff?

--
Jeff Squyres
Cisco Systems

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

Re: [OMPI devel] New libevent to trunk?

[Jeff Squyres]

Thanks.  Since I haven't heard any other objections, I'll bring it in  
sometime over the weekend (Brian promised to test on a cray in the  
near future -- hopefully we didn't break anything [badly]...).



On Mar 21, 2008, at 1:54 PM, Josh Hursey wrote:

Go ahead and bring it in. I have c/r working with forcing poll for
the event engine via the amca file. Supporting the other mechanisms
will take a while and should not prevent this from being merged into
the trunk.

Thanks for checking though.
Josh

On Mar 21, 2008, at 11:53 AM, Jeff Squyres wrote:

Josh --

Where do we stand on bringing in the new libevent to the trunk this
weekend?  Is it ok to import, or do you need more time to work with
the ramifications to the FT stuff?

--
Jeff Squyres
Cisco Systems

___
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



--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] New libevent to trunk?

[Paul H. Hargrove]

Josh,

  As you saw off-list, I've entered a BLCR bug for the epoll problems,
which I a certain are mine.

  What is the status of the problems you saw when testing w/ select()?
I don't know of any reason why BLCR would/could interfere with select(),
assuming the caller of select() is prepared to handle EINTR.  So I don't
think that BLCR is at fault here, but am willing to be convinced
otherwise.  Do you have any idea what the problem is w/ select()?

-Paul

Josh Hursey wrote:
> Go ahead and bring it in. I have c/r working with forcing poll for  
> the event engine via the amca file. Supporting the other mechanisms  
> will take a while and should not prevent this from being merged into  
> the trunk.
> 
> Thanks for checking though.
> Josh
> 
> On Mar 21, 2008, at 11:53 AM, Jeff Squyres wrote:
>> Josh --
>>
>> Where do we stand on bringing in the new libevent to the trunk this
>> weekend?  Is it ok to import, or do you need more time to work with
>> the ramifications to the FT stuff?
>>
>> -- 
>> Jeff Squyres
>> Cisco Systems
>>
>> ___
>> 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


-- 
Paul H. Hargrove  phhargr...@lbl.gov
Future Technologies Group
HPC Research Department   Tel: +1-510-495-2352
Lawrence Berkeley National Laboratory Fax: +1-510-486-6900

Re: [OMPI devel] Makefile.am updates

[Jeff Squyres]

On Mar 21, 2008, at 1:37 PM, Jeff Squyres wrote:


1. Per recent off-list discussions about the build system, I have done
some cleanups and standardizations in the various */tools/*/
Makefile.am files.  A commit is coming soon that will:
  - Somewhat simplify these Makefile.am's
  - Make them consistent with each other (do similar actions in
similar ways)
  - Update to remove old kruft that was required by older versions of
AM

This work is nearly done; barring any problems from a code review,
it'll likely be committed soon.



I have committed this to the trunk in r17921:

https://svn.open-mpi.org/trac/ompi/changeset/17921

Please let me know if you have any problems with it.

--
Jeff Squyres
Cisco Systems