1
1
Граф коммитов

1092 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
3c5a2cd17b Cleanup a few warnings for unused variables
This commit was SVN r12620.
2006-11-17 19:32:49 +00:00
Ralph Castain
f771cc4fbd Modify the reuse daemons procedure so we only generate the add_local_procs message once. Revise the display-map-at-launch option so the RMAPS framework takes responsibility for implementation of that option.
Modify the RMAPS framework so we eliminate communicating a map to a backend node when certain attributes are set. The proxy functions are now implemented in the base, and a check made for HNP/non-HNP operation made in the map_jobs function prior to execution.

This commit was SVN r12619.
2006-11-17 19:06:10 +00:00
Jeff Squyres
d248f608b4 Remove svn:executable from a bunch of files.
This commit was SVN r12617.
2006-11-17 11:01:39 +00:00
Ralph Castain
ca5b4358fa Need to revise the display-map-at-launch option so it is active not only for the initial launch, but applies to any subsequent comm_spawn events too.
Add placeholders for the new orte tools. These don't actually do anything yet - in fact, I have set the .ompi_ignore so that you won't compile them (I have set a .ompi_unignore for me). Please let me know if you encounter any trouble with this - the ompi_ignore's should protect everyone.

This commit was SVN r12616.
2006-11-17 02:58:46 +00:00
Ralph Castain
5ddcb8a652 Ensure the orted kills *all* local procs when exiting. Add a little clarity to some of the debugging output
This commit was SVN r12615.
2006-11-16 21:15:25 +00:00
Ralph Castain
c1813e5c5a Extend the daemon reuse functionality to *most* of the other environments.
Note that Bproc won't support this operation, so we just ignore the --reuse-daemons directive.

I'm afraid I don't understand the POE and XGrid environments well enough to attempt the necessary modifications.

Also, please note that XGrid support has been broken on the trunk. I don't understand the code syntax well enough to make the required changes to that PLS component, so it won't compile at the moment. I'm hoping Brian has a few minutes to fix it after SC.

This commit was SVN r12614.
2006-11-16 15:11:45 +00:00
Ralph Castain
044898f4bf My eyes may be deceiving me....but I do believe these comparisons are backwards! I think we only really want to "free" these variables if they are NOT NULL - as opposed to "free"ing them if they ARE NULL.
This commit was SVN r12612.
2006-11-15 22:59:01 +00:00
Ralph Castain
a17e27dfd5 Sign of old age.....fix some compiler complaints
This commit was SVN r12611.
2006-11-15 22:28:14 +00:00
Ralph Castain
f7fc19a2ca Create the ability to re-use existing daemons. Included in the commit:
1. new functionality in the pls base to check for reusable daemons and launch upon them

2. an extension of the odls API to allow each odls component to build a notify message with the "correct" data in it for adding processes to the local daemon. This means that the odls now opens components on the HNP as well as on daemons - but that's the price of allowing so much flexibility. Only the default odls has this functionality enabled - the others just return NOT_IMPLEMENTED

3. addition of a new command line option "--reuse-daemons" to orterun. The default, for now, is to NOT reuse daemons. Once we have more time to test this capability, we may choose to reverse the default. For one thing, we probably want to investigate the tradeoffs in start time for comm_spawn'd processes that reuse daemons versus launch their own. On some systems, though, having another daemon show up can cause problems - so they may want to set the default as "reuse".

This is ONLY enabled for rsh launch, at the moment. The code needing to be added to each launcher is about three lines long, so I'll be doing that as I get access to machines I can test it on.

This commit was SVN r12608.
2006-11-15 21:12:27 +00:00
Andrew Friedley
3f550c3a83 missing a semicolon...
This commit was SVN r12607.
2006-11-15 20:35:27 +00:00
Ralph Castain
437f2b044d Modify the orted command communication system in two ways:
1. use non-blocking sends to transmit commands (this was actually done in a prior commit)

2. have an "ack" message sent back from the orted when it completes the command

The latter item is the new one here. With my prior commit, it was possible for the HNP to move on to other things before the orted had completed its command. This caused the HNP to occassionally exit before the orted, thus generating "lost connection" errors. With this change, we retain the parallel nature of the command communications, but still hold the HNP at that point until the orteds are done.

Best of both worlds.

This commit was SVN r12605.
2006-11-15 15:09:28 +00:00
Ralph Castain
22a473a831 Fix a compiler complaint for too many arguments to a printf command - thanks to Tim Prins for pointing it out to me.
This commit was SVN r12604.
2006-11-15 14:52:48 +00:00
Ralph Castain
6d6cebb4a7 Bring over the update to terminate orteds that are generated by a dynamic spawn such as comm_spawn. This introduces the concept of a job "family" - i.e., jobs that have a parent/child relationship. Comm_spawn'ed jobs have a parent (the one that spawned them). We track that relationship throughout the lineage - i.e., if a comm_spawned job in turn calls comm_spawn, then it has a parent (the one that spawned it) and a "root" job (the original job that started things).
Accordingly, there are new APIs to the name service to support the ability to get a job's parent, root, immediate children, and all its descendants. In addition, the terminate_job, terminate_orted, and signal_job APIs for the PLS have been modified to accept attributes that define the extent of their actions. For example, doing a "terminate_job" with an attribute of ORTE_NS_INCLUDE_DESCENDANTS will terminate the given jobid AND all jobs that descended from it.

I have tested this capability on a MacBook under rsh, Odin under SLURM, and LANL's Flash (bproc). It worked successfully on non-MPI jobs (both simple and including a spawn), and MPI jobs (again, both simple and with a spawn).

This commit was SVN r12597.
2006-11-14 19:34:59 +00:00
Ralph Castain
7b4261001a Forgot to modify the orted end of the communication subsystem
This commit was SVN r12586.
2006-11-13 22:08:47 +00:00
Ralph Castain
f95e20e2e1 Add another test program - an MPI app that just spins. This supports testing of system response to signal-terminated processes.
Add some debugger output to the ODLS default component.

Modify the orted command communication system so that it is done via non-blocking sends. This removes the linearity of the transmission and improves the response time.

This commit was SVN r12585.
2006-11-13 21:51:34 +00:00
Tim Prins
39bc652899 Refs trac:612
Make it so if -np was not passed and -pernode was, we map bynode

This commit was SVN r12580.

The following Trac tickets were found above:
  Ticket 612 --> https://svn.open-mpi.org/trac/ompi/ticket/612
2006-11-13 19:13:21 +00:00
Ralph Castain
4636125e2d Modify the RMGR components to allow job setup with a given jobid, and add another attribute so that we can setup triggers without launching.
Add some debugging output to the ODLS default module, and the orted.

Remove the nodename data from the ODLS info report - that info is already stored in the registry by the RMAPS framework upon completing the mapping procedure.

Add another test program that does an ORTE-only dynamic spawn (gasp!). Looks just like comm_spawn - just no MPI involved.

Modify the ODLS to release the processor when we "kill" local procs in a more scalable fashion. It previously had a sleep in it that Jeff's prior commit removed. However, he introduced some Windows code into the non-Windows component (protected by "if"s, but unnecessary). This is a more general solution he proposed - included here so I could get things to compile properly.

This commit was SVN r12579.
2006-11-13 18:51:18 +00:00
Jeff Squyres
bfdf801487 Replace a "sleep(1)" with a yield so that the orted can reap processes
much faster.

This commit was SVN r12575.
2006-11-13 12:45:03 +00:00
Ralph Castain
4e50cdae52 This commit accomplishes two things:
1. Fix the "hang" condition when an application isn't found. It turned out that the ODLS had some difficulty with the process actually not having been started - hence, it never called the waitpid callback. As a result, the "terminated" trigger didn't fire, and so mpirun didn't wake up. With this change, the HNP's errmgr forces the issue by causing the trigger to fire itself when an abort condition occurs.

2. Shift the recording of the pid and the nodename from mpi_init to the orted launcher. This allows programs such as Eclipse PTP to get the pids even for non-MPI applications. In the case of bproc, the pls handles this chore since we don't use orteds in that system.

This commit was SVN r12558.
2006-11-11 04:03:45 +00:00
Sven Stork
9ba4c4a7ee - Add support for "sh" handling. Instead of detecting of bash we now
check for bourne shell, because bourne shell is the smallest
  common divisor for bash/ksh/sh.
- Make some shell expressions sh compatible 

This commit was SVN r12509.
2006-11-09 10:16:45 +00:00
Ralph Castain
a3be8261fb Fix a bug that had us generate an error message and abort startup when there were stale universe directories around. Now, we just ignore them.
This commit was SVN r12472.
2006-11-07 21:34:57 +00:00
Ralph Castain
ea77beca29 cleanup the TM modules in prep for T-bird tests. The TM RAS will now report time required to resolve hostnames
This commit was SVN r12449.
2006-11-06 20:56:18 +00:00
Ralph Castain
884caeb2c7 Add timing tests for the TM ras
This commit was SVN r12445.
2006-11-06 18:41:22 +00:00
Galen Shipman
68d9922f44 enable/disable connection sleep in oob_tcp.c via mca param.. on by default..
This commit was SVN r12444.
2006-11-06 18:00:46 +00:00
Ralph Castain
194bdd413b Cleanup the problem of connecting to default universes.
This commit was SVN r12438.
2006-11-06 15:28:38 +00:00
Ralph Castain
d182ae7472 Clean up a few compiler warnings courtesy of Jeff
This commit was SVN r12430.
2006-11-03 20:45:22 +00:00
Ralph Castain
c77f6c605e Update timing reports:
1. Remove timing of xcast from mpi_init

2. Add timing report from oob_xcast on how long it took to send the message

This commit was SVN r12428.
2006-11-03 18:55:05 +00:00
Ralph Castain
761c8beeb7 Add output of the compound command size to the timing reports
This commit was SVN r12423.
2006-11-03 16:11:37 +00:00
Ralph Castain
60e27c77e7 Add some additional timing reporting:
1. Added reporting points around the xcasts in MPI_Init. Note that these times will include time spent waiting for a trigger to fire, which is why the times between stage gates did NOT include these times initially. The inter-stage-gate times still do NOT include the xcast time - the xcast time is reported separately.

2. Added the process vpid on the MPI_Init timing reports for clarity.

3. Added a report from the xcast function on the HNP that outputs the number of bytes in the message being sent to the processes.

This commit was SVN r12422.
2006-11-03 16:04:40 +00:00
Ralph Castain
2472f76d89 Make sure the print_map doesn't get called if we don't do the map step in rmgr.spawn
This commit was SVN r12404.
2006-11-02 05:52:24 +00:00
Ralph Castain
dc4de57253 Per request from the Eclipse team, change the attributes that control the "flow" through the rmgr.spawn procedure from "stop after this step" to "do this step". This allows them to use the spawn procedure to complete the launch one step at a time so they can let the user see the results after each step.
Shouldn't affect anyone else.

This commit was SVN r12403.
2006-11-02 05:15:24 +00:00
Ralph Castain
233dac8bba Enable the new attributes for remote operations such as comm_spawn
This commit was SVN r12382.
2006-10-31 23:52:25 +00:00
Ralph Castain
30de73a712 Add a few attributes that are helpful for folks doing things like Eclipse. Also add yet another command-line option to orterun to support one of the new attributes. These include:
1. ORTE_RMAPS_DISPLAY_AT_LAUNCH: pretty-prints out the process map right before we launch so you can see where everyone is going. This is settable via the command line option "--display-map-at-launch"

2. ORTE_RMGR_STOP_AFTER_SETUP: just setup the job and then return from the spawn command.

3. ORTE_RMGR_STOP_AFTER_ALLOC: return from the rmgr.spawn call after allocating the job

4. ORTE_RMGR_STOP_AFTER_MAP: return from the rmgr.spawn call after mapping the job. This gives folks a chance to retrieve and graphically display the map, let the user edit it, and store the results. They can then call "launch" on their own and the system will use the revised map.

Enjoy! My personal favorite is the first one - helps with debugging.

This commit was SVN r12379.
2006-10-31 22:16:51 +00:00
Ralph Castain
17c71f8d2a Fix ticket #545
Setup subscriptions to correctly return the MPI_APPNUM attribute.

Fix an unreported bug that was found. The universe size was incorrectly defined in the attributes code. As coded, it looked for size_t values and based its size computation on those numbers. Unfortunately, the node_slots value had been changed to an orte_std_cntr_t awhile back! So the universe size was never updated.

Update the hello_nodename test to check for MPI_APPNUM.

Add a definition to ns_types for ORTE_PROC_MY_NAME - just a shortcut for orte_process_info.my_name. Brought over from ORTE 2.0 as it will be used extensively there.

This commit was SVN r12377.
2006-10-31 21:29:07 +00:00
Tim Prins
894b220fbb Fixes trac:487
Give a more intelligible error message when someone passes -nolocal and the only available node is the local node.

This commit was SVN r12325.

The following Trac tickets were found above:
  Ticket 487 --> https://svn.open-mpi.org/trac/ompi/ticket/487
2006-10-26 21:46:18 +00:00
Ralph Castain
36d4511143 Bring the timing instrumentation to the trunk.
If you want to look at our launch and MPI process startup times, you can do so with two MCA params:

OMPI_MCA_orte_timing: set it to anything non-zero and you will get the launch time for different steps in the job launch procedure. The degree of detail depends on the launch environment. rsh will provide you with the average, min, and max launch time for the daemons. SLURM block launches the daemon, so you only get the time to launch the daemons and the total time to launch the job. Ditto for bproc. TM looks more like rsh. Only those four environments are currently supported - anyone interested in extending this capability to other environs is welcome to do so. In all cases, you also get the time to setup the job for launch.

OMPI_MCA_ompi_timing: set it to anything non-zero and you will get the time for mpi_init to reach the compound registry command, the time to execute that command, the time to go from our stage1 barrier to the stage2 barrier, and the time to go from the stage2 barrier to the end of mpi_init. This will be output for each process, so you'll have to compile any statistics on your own. Note: if someone develops a nice parser to do so, it would be really appreciated if you could/would share!

This commit was SVN r12302.
2006-10-25 15:27:47 +00:00
Brian Barrett
d6ff14ed61 Hand-pack the connection information for each peer rather than just
packing a sockaddr_in, as there are some endianness and padding issues
with sending a sockaddr_in.  Note that the sin_port and sin_addr are
already in network byte order, which is why we pack them as a byte
string.

Refs trac:493

This commit was SVN r12301.

The following Trac tickets were found above:
  Ticket 493 --> https://svn.open-mpi.org/trac/ompi/ticket/493
2006-10-25 15:09:30 +00:00
Ralph Castain
601443e690 Fix the other end of the attribute store/retrieve to correctly handle attributes with no value
This commit was SVN r12290.
2006-10-25 01:41:58 +00:00
Ralph Castain
46166a9c77 Fix a bug that would cause a segfault when someone specified an option that had no corresponding value
This commit was SVN r12288.
2006-10-24 22:06:18 +00:00
Ralph Castain
a7acd22e47 Fix a fix so we see the correct MCA param
This commit was SVN r12282.
2006-10-24 17:24:09 +00:00
George Bosilca
ed3caa9fc7 mca_base_param_reg_int require a pointer to a component not a name.
This commit was SVN r12281.
2006-10-24 16:41:51 +00:00
George Bosilca
7dec7731ce Instead of size_t use orte_std_cntr_t. Remove all warnings.
This commit was SVN r12280.
2006-10-24 16:40:49 +00:00
Ralph Castain
8636ac6a4d Fix ticket 353 - print out a nice message that the combination of debug-daemons and num_concurrent in the pls rsh launcher will cause deadlock and exit
This commit was SVN r12279.
2006-10-24 15:59:02 +00:00
Tim Prins
cb622db7c9 Fixes trac:352
Only close off stdout/stderr from the daemons if we are not debugging the slurm pls and --debug-daemons was not passed.

This commit was SVN r12276.

The following Trac tickets were found above:
  Ticket 352 --> https://svn.open-mpi.org/trac/ompi/ticket/352
2006-10-24 13:05:13 +00:00
Tim Prins
93d61d01fb Fix for a problem on SLURM we have neen having since r12243 where mpirun would hang after the process had finished. It turns out that we were always reporting the name of the daemon wrong, but we simply never noticed as we never used it, until r12243. This makes it so we report the name of the daemon correctly.
This commit was SVN r12274.

The following SVN revision numbers were found above:
  r12243 --> open-mpi/ompi@153e38ffc9
2006-10-24 01:41:28 +00:00
Ralph Castain
7a77ef0ae3 Given the amount of pain singletons cause, one can't help but wonder if it REALLY was that much trouble for people to type "mpirun -n 1 foo"....sigh.
Get the ordering right so that a singleton can start.

Protect the rmgr copy app_context function from NULL fields

Tell the mapper it is okay for there not to be a pre-existing mapping plan for a parent when dynamically spawning processes

This commit was SVN r12257.
2006-10-23 15:15:45 +00:00
Ralph Castain
c5b59829aa Fix a long-lingering annoyance. Calling mpirun with a non-existent application would cause the system to hang on all environments. Reason was that the orted would exit, which it should never do without explicit orders to that affect.
This commit was SVN r12255.
2006-10-23 13:27:31 +00:00
George Bosilca
ee559e9947 Do not completely reset the orterun_globals. Keep the condition and the mutex,
but reset everything else. Once initialized the condition (and the attached
mutex) should be kept alive as long as possible if we want to be able to
retrieve all the informations.

This commit was SVN r12253.
2006-10-23 03:34:08 +00:00
George Bosilca
2a863df0a5 Newline is required by some compilers at the end of a file.
This commit was SVN r12244.
2006-10-21 05:56:04 +00:00
Ralph Castain
153e38ffc9 Lesson to be learned: if you send an ack to a recv'd command, better not send it to the same tag it came from - at least, not if there is a persistent recv on that tag!
Fix the persistent daemon problem where it was exiting when a job completed. Problem was that the persistent daemon would order the job daemons to exit. They would then send an 'ack' back to the persistent daemon - but the ack consisted of an echo of the "exit" command, which was recv'd by the wrong listener who treated it as a properly sent cmd....and exited.

This commit was SVN r12243.
2006-10-21 02:53:19 +00:00
Ralph Castain
ab7bbb80a5 Teach the mapper to correctly handle the unbalanced --host scenario. We now map in a more expected fashion.
This commit was SVN r12240.
2006-10-20 20:48:24 +00:00
George Bosilca
548b94e4e1 Add a missing ORTE_DECLSPEC.
This commit was SVN r12236.
2006-10-20 19:37:21 +00:00
Tim Prins
28bf4d85ab A couple of small fixes:
- It is possible to leave a byslot/bynode routine and have cur_node_item be NULL, so check for that.
- After we do an allocation where the user has provided a map (i.e. with --host), cur_node_item is pointing into the map list, not the global list. Change it to point into the global list.

This commit was SVN r12232.
2006-10-20 19:00:17 +00:00
Ralph Castain
955d11fa7b The bookmark now respects slot assignments a little better. It will not oversubscribe the first node, but will take only what is available there before moving on.
See the comment in orte/mca/rmaps/round_robin/rmaps_rr.c if you want the details... :-)

This commit was SVN r12230.
2006-10-20 18:24:14 +00:00
Ralph Castain
ec0bb9ffda Fix the bookmark system - we now have children being correctly spawned where they should!
Also, I am no longer seeing any issue with the child job spawning its own daemons - this appears to be fixed. We still don't reuse the existing daemons, however, but that will come.

This commit was SVN r12229.
2006-10-20 18:05:16 +00:00
Ralph Castain
c07d4e2510 Cleaner rendition now extended to other environments. Remove MCA params for backend procs that can cause trouble. Specifically, any directives on the selection of components for RDS, RAS, RMAPS, PLS, and RMGR can be bad mojo on the backend.
This patch will cause a problem for cnos, however, as there we want to specifically tell the backends to be "null". I'm working on that issue.

This commit was SVN r12225.
2006-10-20 16:50:13 +00:00
Ralph Castain
02efd07b60 Fix the MCA param passing issue, at least for rsh at the moment. I will clean this up and move it to the other environments once I shift back to a local computer.
This commit was SVN r12224.
2006-10-20 15:27:29 +00:00
Ralph Castain
b07a6b1d7a Fix a major typo that caused remote launch to crash - had something inside the wrong brace
This commit was SVN r12221.
2006-10-20 14:30:23 +00:00
Brian Barrett
37fad860b7 Grrr... Forgot that EXTRA_DIST and man_MANS are not set to include all the
possible things contained in the conditional like other rules are (for
example, a SOURCES rule in a conditional automatically has its files
added to the dist rules, even if that conditional isn't tru when
make dist occurs).  So the man files weren't in the tarball.

Put the EXTRA_DIST with the files explicitly listed outside any conditionals
so the man pages always end up in the tarball.

This commit was SVN r12220.
2006-10-20 14:15:38 +00:00
George Bosilca
2aa3e51223 Nothing relevant. Only a set of castings to have a clean compile on
Windows. The cl.exe compiler is pretty good at complaining about
any kind of non explicit cast.

This commit was SVN r12207.
2006-10-20 02:25:50 +00:00
George Bosilca
7982a23bde ORTE_DECLSPEC should be ...
This commit was SVN r12206.
2006-10-20 02:23:54 +00:00
George Bosilca
5a939e21b2 Populate the file with ORTE_DECLSPEC declarations.
This commit was SVN r12205.
2006-10-20 02:19:30 +00:00
Tim Prins
ade94b523b Fixed a number of issues related to resource allocation:
- Simplified the logic of the ras modules by moving the attribute handling into the base allocation function. This allows us to decide how to allocate based on the situation, and solves some of the allocation problems we were having with comm_spawn.
- moved the proxy component into the base. This was done because we always want to call the proxy functions if we are not on a HNP regardless of the attributes passed. 
- Got rid of the hostfile component. What little logic was in it was moved into the base to deal with other circumstances. The hostfile information is currently being propagated into the registry by the RDS, so we just use what is already in the registry.
- renamed some slurm function so that they have the proper prefix. Not strictly necessary as they were static, but it makes debugging much easier.
- fixed a buglet in the round_robin rmaps where we would return an error when really no error occured.

I tried to make proper corrections to all the ras modules, but I cannot test all of them.

This commit was SVN r12202.
2006-10-19 23:33:51 +00:00
Ralph Castain
ab196c3121 Okay, this fixes the problem of MCA params spreading too far. Sorry for the multiple corrections.
This commit was SVN r12201.
2006-10-19 22:51:02 +00:00
George Bosilca
c788f0dd51 Apparently, the MCA params are being loaded into the environment params
of the individual app_contexts as well. Clear them of "bad" ones.

This commit was SVN r12198.
2006-10-19 21:19:08 +00:00
Ralph Castain
d0d3d7fd41 Apparently, the MCA params are being loaded into the environment params of the individual app_contexts as well. Clear them of "bad" ones.
This commit was SVN r12197.
2006-10-19 20:49:35 +00:00
Ralph Castain
382f954fff Fix a bug in the way we saved and passed environments to child processes on remote nodes. The problem was that MCA directives for component selection were being passed back to the children. However, now that we only allow certain components to operate on HNPs, this caused the children to bomb out of orte_init.
This commit was SVN r12196.
2006-10-19 20:35:55 +00:00
Brian Barrett
204f5b8f52 - Clean up wrapper compiler man pages during maintainer-clean, since
they might require special tools (not sure if sed with multiple -e
    arguments is totally portable)
  - ignore the opalcc.1 man page.  Couldn't do this in the previous
    man page commit (r12192) because I was removing opalcc.1 in that
    commit.

This commit was SVN r12194.

The following SVN revision numbers were found above:
  r12192 --> open-mpi/ompi@581a4b0a4e
2006-10-19 20:14:40 +00:00
Ralph Castain
263f4379e8 Clean up an error in the mapper that caused "-hosts" to bomb.
Update the mapper so it correctly points to the next node to be used if we are mapping by slots. As it was, if we had an app_context that used only one slot on a node, the next app_context would start on the next node - leaving a blank slot in-between.

This commit was SVN r12193.
2006-10-19 18:57:29 +00:00
Brian Barrett
581a4b0a4e A few cleanups to the wrapper compiler build system / man pages:
- Only install opal{cc,c++} and orte{cc,c++} if configured with
     --with-devel-headers.  Right now, they are always installed, but 
    there are no header files installed for either project, so there's
    really not much way for a user to actually compile an OPAL / ORTE
    application.

  - Drop support for opalCC and orteCC.  It's a pain to setup all the 
    symlinks (indeed, they are currently done wrong for opalCC) and 
    there's no history like there is for mpiCC.

  - Change what is currently opalcc.1 to opal_wrapper.1 and add some
    macros that get sed'ed so that the man pages appear to be 
    customized for the given command.  

  - Install the wrapper data files even if we compiled with 
    --disable-binaries.  This is for the use case of doing multi-lib
    builds, where one word size will only have the library built, but 
    we need both set of wrapper data files to piece together to 
    activate the multi-lib support in the wrapper compilers.

This commit was SVN r12192.
2006-10-19 18:34:17 +00:00
Tim Prins
81d400ddfd break when they are equal, not not equal
This commit was SVN r12182.
2006-10-18 21:47:01 +00:00
Tim Prins
ab964d096a Need a terminating NULL...
This commit was SVN r12180.
2006-10-18 20:52:31 +00:00
Ralph Castain
d0eb7d7216 Complete the attribute management functions.
Modify the mapper to better bookmark its stopping place each time, and to pick up the next time from there. This needs to be validated on a multi-node system.

Fix a major memory corruption problem in the registry put/get functions that was doing multiple free's. Not sure how valgrind missed this one, though it only occurred in specific circumstances (such as comm_spawn).

This commit was SVN r12179.
2006-10-18 20:02:16 +00:00
Ralph Castain
f4a458532b This doesn't totally resolve the comm_spawn problem, but it helps a little. I'll continue working on it and hope to resolve it completely shortly. The issue primarily centers on where to start mapping the child job's processes, and how to deal with oversubscription that might result. At the moment, I am trying to resolve the first issue first (hey, that even sounds right!).
This change does a couple of things:

1. Since the USE_PARENT_ALLOC attribute is a directive about regarding allocation of resources to a job, it more properly should be an attribute of the RAS. Change the name to reflect that and move the attribute define to the ras_types.h file.

2. Add the attributes list to the RMAPS map_job interface. This provides us with the desired flexibility to dynamically specify directives for mapping. The system will - in the absence of any attribute-based directive - default to the values provided in the MCA parameters (either from environment or command-line interface).

This commit was SVN r12164.
2006-10-18 14:01:44 +00:00
George Bosilca
50649dd6a9 What we write it's a long long so we should be using the long long format.
This commit was SVN r12157.
2006-10-18 00:02:20 +00:00
George Bosilca
1d69375dd7 Somehow, somewhere we have to initialize rc ...
This commit was SVN r12156.
2006-10-17 22:32:21 +00:00
Ralph Castain
0c0fe022ff This is a first cut at fixing the problem of comm_spawn children being mapped onto the same nodes as their parents. I am not convinced the behavior implemented here is the long-term right one, but hopefully it will help alleviate the situation for now.
In this implementation, we begin mapping on the first node that has at least one slot available as measured by the slots_inuse versus the soft limit. If none of the nodes meet that criterion, we just start at the beginning of the node list since we are oversubscribed anyway.

Note that we ignore this logic if the user specifies a mapping - then it's just "user beware".

The real root cause of the problem is that we don't adjust sched_yield as we add processes onto a node. Hence, the node becomes oversubscribed and performance goes into the toilet. What we REALLY need to do to solve the problem is:

(a) modify the PLS components so they reuse the existing daemons, 

(b) create a way to tell a running process to adjust its sched_yield, and

(c) modify the ODLS components to update the sched_yield on a process per the new method

Until we do that, we will continue to have this problem - all this fix (and any subsequent one that focuses solely on the mapper) does is hopefully make it happen less often.

This commit was SVN r12145.
2006-10-17 19:35:00 +00:00
Tim Prins
720eb88cad Make no-op function match new interface.
This commit was SVN r12142.
2006-10-17 17:34:06 +00:00
Tim Prins
8b0170148e Add some missing headers.
This commit was SVN r12141.
2006-10-17 17:28:02 +00:00
Tim Prins
5d31332f97 Goodbye poe, long live LoadLeveler...
This commit was SVN r12140.
2006-10-17 17:07:48 +00:00
Ralph Castain
13227e36ab This commit looks a lot bigger than it is, so relax :-)
Fix the problem observed by multiple people that comm_spawned children were (once again) being mapped onto the same nodes as their parents. This was caused by going through the RAS a second time, thus overwriting the mapper's bookkeeping that told RMAPS where it had left off.

To solve this - and to continue moving forward on the ORTE development - we introduce the concept of attributes to control the behavior of the RM frameworks. I defined the attributes and a list of attributes as new ORTE data types to make it easier for people to pass them around (since they are now fundamental to the system, and therefore we will be packing and unpacking them frequently). Thus, all the functions to manipulate attributes can be implemented and debugged in one place.

I used those capabilities in two places:

1. Added an attribute list to the rmgr.spawn interface.

2. Added an attribute list to the ras.allocate interface. At the moment, the only attribute I modified the various RAS components to recognize is the USE_PARENT_ALLOCATION one (as defined in rmgr_types.h).

So the RAS components now know how to reuse an allocation. I have debugged this under rsh, but it now needs to be tested on a wider set of platforms.

This commit was SVN r12138.
2006-10-17 16:06:17 +00:00
Rainer Keller
3f88937081 - Error logging is really not yet enabled.
- Correct the error log for orte_errmgr_base_select
 - Spelling fixes

This commit was SVN r12135.
2006-10-17 09:11:20 +00:00
Ralph Castain
16e52c5784 Fix a non-compliance issue regarding hostfiles as reported by Sun. The man page states that an entry that specifies slots_max but does not specify "slots" will have the soft limit default to the hard limit. The hostfile implementation, however, defaulted the soft limit to 1.
This fix changes that behavior to conform to the man page.

This commit was SVN r12129.
2006-10-17 00:43:12 +00:00
Brian Barrett
9adde4f7b8 Allow multilib capability based on compiler flags. See:
https://svn.open-mpi.org/trac/ompi/wiki/compilerwrapper3264
for more information.

Refs trac:374

This commit was SVN r12120.

The following Trac tickets were found above:
  Ticket 374 --> https://svn.open-mpi.org/trac/ompi/ticket/374
2006-10-15 21:21:08 +00:00
Ralph Castain
3f55d6897a Remove the memory debugging options. Fix what appears to be a typo in a help file.
This commit was SVN r12107.
2006-10-12 00:44:48 +00:00
Brian Barrett
fce5130333 Delay opening the listen socket until module init, so that we can have the
seed value have something set to true.  Allow selection of the listen
type to thread if (and only if) the process is the HNP...

This commit was SVN r12105.
2006-10-11 21:29:29 +00:00
Brian Barrett
29c91cf2f3 * Fix issue in odls_bproc where we were using vpid instead of the number of
processes launched locally for the stdio file names.  This was causing
    the expected files to not exist and bproc_vexecmove_io to fail.
  * Clean up a bunch of debugging output in the bproc pls

This commit was SVN r12102.
2006-10-11 20:34:12 +00:00
Ralph Castain
f91a95b3fe Fix the bug that caused mpirun to hang when a remote executable wasn't found using the rsh launcher. Will now test on a remote node
This commit was SVN r12095.
2006-10-11 18:43:13 +00:00
Ralph Castain
2da8245be0 Correctly propagate no-daemonize
This commit was SVN r12093.
2006-10-11 17:53:17 +00:00
Ralph Castain
e5877cc459 Add the proper valgrind params
This commit was SVN r12092.
2006-10-11 17:48:41 +00:00
George Bosilca
b56636c855 orte_pls belong to the PLS framework, therefore it should only be defined
in pls.h.

This commit was SVN r12089.
2006-10-11 17:12:22 +00:00
Ralph Castain
27e305347c Add a couple of options to orterun that support debugging of daemons for memory corruption.
Ensure that the environment provided to local application processes isn't "polluted" by the orteds

This commit was SVN r12087.
2006-10-11 15:18:57 +00:00
Brian Barrett
f5b8f1f2f0 Work around Automake not knowing how to properly configure libtool to build
Objective C libraries

Refs trac:483

This commit was SVN r12080.

The following Trac tickets were found above:
  Ticket 483 --> https://svn.open-mpi.org/trac/ompi/ticket/483
2006-10-10 20:14:26 +00:00
Ralph Castain
699ffcf359 Restore the "bynode" mapping functionality - accidentally deleted setting of parameter
This commit was SVN r12078.
2006-10-10 19:41:22 +00:00
George Bosilca
7dadc1832d Correctly export the required functions. They are defined in a private file, but they are completely public.
This commit was SVN r12070.
2006-10-10 04:54:51 +00:00
Ralph Castain
0e9dc590b7 Fix typo that didn't make it over from testing on vogon
This commit was SVN r12068.
2006-10-09 20:37:39 +00:00
Ralph Castain
cebdc51762 Remove a debugging output
This commit was SVN r12066.
2006-10-09 02:10:52 +00:00
Ralph Castain
e7f6fa22d6 Fix return code so that mpirun returns the right thing when an abort is encountered.
This commit was SVN r12065.
2006-10-09 01:04:00 +00:00
Ralph Castain
2e09128337 Many thanks to Jeff for tracking down the typo causing the orte_job_map_t destuctor to fail!!
Restore the OBJ_RELEASE calls to cleanup map objects.

This commit was SVN r12064.
2006-10-07 22:44:00 +00:00
Ralph Castain
98dd57b70e Add a new option to launch "pernode" - launches one process/node across all available nodes.
The other options also work correctly: "-bynode" with no -np will launch on all *slots*, mapped on a per-node basis.

This commit was SVN r12063.
2006-10-07 19:50:12 +00:00
Jeff Squyres
efe28d62e9 Fix some compiler errors. I have *not* checked this for correctness;
but it does now compile.

This commit was SVN r12062.
2006-10-07 19:10:56 +00:00
Ralph Castain
889ddefe85 Remove release that caused totalview connection to bomb
This commit was SVN r12061.
2006-10-07 18:25:56 +00:00
Ralph Castain
ae79894bad Bring the map fixes into the main trunk. This should fix several problems, including the multiple app_context issue.
I have tested on rsh, slurm, bproc, and tm. Bproc continues to have a problem (will be asking for help there).

Gridengine compiles but I cannot test (believe it likely will run).

Poe and xgrid compile to the extent they can without the proper include files.

This commit was SVN r12059.
2006-10-07 15:45:24 +00:00
Ralph Castain
82a023c731 Fix a typo that caused a segfault if a caller requested that we abort an array of procs (i.e., MPI_Abort when it specifies the other procs to be aborted).
Should hopefully address the recent problem seen with the BLACS AUX test as discussed on the user mailing list.

This commit was SVN r12055.
2006-10-07 01:58:11 +00:00
Ralph Castain
ee0df85ece Add a stupid, useless const since someone put it in the odls.h file.
This commit was SVN r12054.
2006-10-07 01:42:23 +00:00
George Bosilca
cda46efd2a Some missing DECLSPEC
This commit was SVN r12047.
2006-10-06 15:21:52 +00:00
Jeff Squyres
72cf2fe813 Oops: --noprefix should not take an argument.
This commit was SVN r12043.
2006-10-06 13:02:56 +00:00
George Bosilca
017af37291 Keep only the useful _DECLSPEC and _DECLSPEC some globals.
This commit was SVN r12042.
2006-10-06 07:24:34 +00:00
George Bosilca
b7579b09c7 Correctly handle the ORTE_DECLSPEC attribute.
This commit was SVN r12041.
2006-10-06 07:08:17 +00:00
George Bosilca
422ce1d3f8 If we are in the ODLS framework then the types should be called odls not pls.
This commit was SVN r12040.
2006-10-06 07:05:58 +00:00
George Bosilca
7fed79434e Windows is now able to create local processes.
This commit was SVN r12039.
2006-10-06 07:04:43 +00:00
George Bosilca
fa01b9b9aa Last step for the name reversion (from windows back to process).
This commit was SVN r12014.
2006-10-05 06:36:11 +00:00
George Bosilca
b7a793a6db Rename all the files in the process directory.
This commit was SVN r12013.
2006-10-05 06:34:30 +00:00
George Bosilca
fee0909815 Rename the Windows component.
This commit was SVN r12012.
2006-10-05 06:32:57 +00:00
George Bosilca
c79c436c8d Cleanups. Remove all __WINDOWS__ checks as this module will never
get compiled on Windows.

This commit was SVN r12011.
2006-10-05 06:17:30 +00:00
George Bosilca
f3f2463dc9 Do the correct cast.
This commit was SVN r12010.
2006-10-05 06:03:01 +00:00
George Bosilca
dbe7f8ac32 Always return bool.
This commit was SVN r12009.
2006-10-05 05:45:18 +00:00
George Bosilca
b2b2ade6c9 Remove the last underscore. Look like a typo ...
This commit was SVN r12006.
2006-10-05 05:41:57 +00:00
George Bosilca
f51e3ec338 Create the key on windows too even if the security is lower.
This commit was SVN r12005.
2006-10-05 05:39:49 +00:00
George Bosilca
c2d397ee7d Add the second part of the C++ protection and declare external functions
with the expected attribute.

This commit was SVN r12004.
2006-10-05 05:30:10 +00:00
George Bosilca
6a9f0b6ba9 Explicit cast to keep some compilers quiet.
This commit was SVN r12003.
2006-10-05 05:29:08 +00:00
George Bosilca
d1e884fbf5 Make sure we always return a bool (true/false).
This commit was SVN r12002.
2006-10-05 05:27:46 +00:00
George Bosilca
3a34f9340e If the enum is defined inside the struct it will has a scope. We don't
really need that.

This commit was SVN r12001.
2006-10-05 05:27:04 +00:00
George Bosilca
090b8a9098 opal_list_is_empty return true or false ...
This commit was SVN r12000.
2006-10-05 05:26:08 +00:00
George Bosilca
03083cc1f6 Don't release the values[0] before it get initialized.
This commit was SVN r11999.
2006-10-05 05:25:18 +00:00
George Bosilca
fd76e56279 One protection against C++ compilers is more than enough.
This commit was SVN r11998.
2006-10-05 05:24:43 +00:00
George Bosilca
ad5810e33f ORTE_DECLSPEC what needs to be ORTE_DECLSPES.
This commit was SVN r11997.
2006-10-05 05:22:22 +00:00
George Bosilca
d628a18411 Right now there is no support for TotalView on Windows. Therefore, we don't
really care how these functions and variables are declared.

This commit was SVN r11996.
2006-10-05 05:19:03 +00:00
Ralph Castain
faf3a558e6 Missing CR at end of file
This commit was SVN r11959.
2006-10-03 18:17:52 +00:00
Ralph Castain
cd7d87aa7b Define the map data types for dss compatibility. Setup to debug bproc
This commit was SVN r11955.
2006-10-03 17:40:00 +00:00
Ralph Castain
4e39878944 Add a "dump" capability to the DSS so one can display a single data value to an output stream.
Add some comments to the map type def in prep for building its data type support.

This commit was SVN r11947.
2006-10-03 08:40:35 +00:00
Ralph Castain
99f2986db7 Bring comm_spawn back online. Shift the trigger hosting responsibilities to the HNP.
We still have an issue with the io forwarding going through the spawning process, but that will be dealt with at a future time.

This commit was SVN r11943.
2006-10-03 02:07:58 +00:00
Ralph Castain
b269e4da9b Add missing functionaltiy to the ns replica to support remote get_job_peers requests. Add trace commands to help try and track down remaining problem with comm_spawn.
This commit was SVN r11939.
2006-10-02 19:44:35 +00:00
Ralph Castain
9eb14425b7 The last of the debug messages that keep hiding. My apologies.
This commit was SVN r11937.
2006-10-02 18:43:32 +00:00
Ralph Castain
3fd67a038f Bring comm_spawn and persistent operations online. Still some minor problems, though - so don't use them yet, please.
This won't affect anything except those two scenarios.

This commit was SVN r11936.
2006-10-02 18:29:15 +00:00
Ralph Castain
12328395ae Missed a couple of debug statements
This commit was SVN r11935.
2006-10-02 15:46:41 +00:00
Tim Prins
53b116d309 This commit fixes trac:452.
It turns out that we were improperly allocating an array if -np was not passed. Also, we were not really using this array for anything. So this gets rid of the array and performs some minor cleanup.

This commit was SVN r11934.

The following Trac tickets were found above:
  Ticket 452 --> https://svn.open-mpi.org/trac/ompi/ticket/452
2006-10-02 15:03:43 +00:00
Ralph Castain
7494a7a83f Clean out some debugging statements that were inadvertently left in the commit
This commit was SVN r11933.
2006-10-02 15:03:18 +00:00
Ralph Castain
559b9b0ae8 Continue beating on comm_spawn. Setup to debug bproc.
This commit was SVN r11932.
2006-10-02 14:58:22 +00:00
Ralph Castain
65593cd67e Fix a few Cyrador warnings
This commit was SVN r11930.
2006-10-02 13:00:32 +00:00
Brian Barrett
8f7ab1c584 num_procs can be zero if something went partly wrong before. This will
cause a math exception on some platforms, so don't let that happen.

This commit was SVN r11929.
2006-10-02 01:27:22 +00:00
Ralph Castain
121f834776 Continue bringing comm_spawn back online. Ensure all RM frameworks post their HNP receives. Fix the rmgr proxy component.
Still need some work on the proxy component, and on job termination for persistent daemon case.

This commit was SVN r11928.
2006-10-02 00:46:31 +00:00
Brian Barrett
e464adcd51 Need to tell the daemon how many procs it will start (always 1, because of
the way we do the fake mapping thing...

This commit was SVN r11924.
2006-10-01 23:25:22 +00:00
Brian Barrett
95ba51fbd4 * Clean up debugging output so that it's useful
* Error message in an NSError object is localizedDescription, not
    localizedErrorReason.  The latter is a decription of how the error
    can occur, which is usually nothing in XGrid frameworks.
  * Clean up silly error in finding the Kerberos Service Principal
    when using Kerberos authenticaion
  * Print useful error message when a connection unexpectedly closes, 
    as this is usually authentication related...

This commit was SVN r11923.
2006-10-01 22:43:17 +00:00
Brian Barrett
9807a38458 Always initialize the base output stream, but only set verbose if requested.
Otherwise, the PLS components have pay more attention to debugging streams
than the rest of the OMPI source code

This commit was SVN r11922.
2006-10-01 22:37:30 +00:00
Dan Lacher
ba0389723e Ticket: #346
remove requirements on .la files on wrapper scripts

Ticket: #374
  extend compilers to support 32 bit and 64 bit in one version of the wrapper

Submitted by: Dan Lacher
Reviewed by: Rolf Vandevaart

This commit was SVN r11908.
2006-09-29 23:58:58 +00:00
Ralph Castain
33a46cff40 Grrrr....ok, this time actually put a *value* in the silly command buffer!
This commit was SVN r11901.
2006-09-29 21:44:11 +00:00
Ralph Castain
0625ead54a Fix comm_spawn communications
This commit was SVN r11900.
2006-09-29 21:10:48 +00:00
Jeff Squyres
785a2e1c90 Move the man page installs to install-data-hook. Putting them in
install-exec-hook is not only wrong, it can cause ordering issues such
as trying to put sym links to man pages in directories that do not yet
exist.

This commit was SVN r11893.
2006-09-29 14:34:39 +00:00
Ralph Castain
0411f9772e Begin instrumenting for scalability tests.
I have added a new MCA param (hey, you can't have too many!) called OMPI_MCA_orte_timing. If set to anything other than zero, the system will report out critical timing loops. At the moment, this includes three measurements:

1. Time spent going through the RDS->RAS->RMAPS, setting up triggers, etc. prior to calling the actual PLS launch function. This is reported out as time to setup job.

2. Time spent in MPI_Init from start of that function (well, right after opal_init) to the place where we send all of our info the registry. Reported out as time from start to exec_compound_cmd

3. Time actually spent executing the compound cmd. Reported out as time to exec_compound_cmd.

A few additional timing points will be added shortly.

These may eventually be removed or (better) setup with a conditional compile flag.

This commit was SVN r11892.
2006-09-29 13:19:44 +00:00
Ralph Castain
db6a93fa63 Fix a couple of reported issues:
1. PLS finalize was not being called. Now ensure that happens during orte_finalize.

2. Errmgr proxies were sending their messages to the wrong tag - typical cut/paste error.

This commit was SVN r11891.
2006-09-29 12:45:50 +00:00
Tim Prins
1b35e7adff cleanup
This commit was SVN r11863.
2006-09-28 13:28:48 +00:00
Brian Barrett
d00a0de716 * It appears that in their infinite wisdom, Apple removed the
__DARWIN_ALIGN_POWER define from the last release of the OS X compiler
    toolchain.  The bug in net/if.h, however, is still there.  So look
    for the hints that we're on a 64 bit Apple PowerPC instead.
  * If we don't find a buffer size that works by 10MB, we're never
    going to.  So add some code to limit the buffer size we'll try
    so that we don't fall into an infinite loop
  * Detect errors in opal_ifcount in the oob init code

Refs trac:420

This commit was SVN r11825.

The following Trac tickets were found above:
  Ticket 420 --> https://svn.open-mpi.org/trac/ompi/ticket/420
2006-09-26 16:37:04 +00:00
Brian Barrett
8943f583bf quiet some debugging output
This commit was SVN r11813.
2006-09-26 04:10:07 +00:00
Brian Barrett
d8d55a760f First attempt at Kerberos support for the XGrid process starter
refs trac:345

This commit was SVN r11812.

The following Trac tickets were found above:
  Ticket 345 --> https://svn.open-mpi.org/trac/ompi/ticket/345
2006-09-26 03:54:38 +00:00
Brian Barrett
9733c8e3bd Update XGrid RAS and PLS to the new infrastructure. Not yet super well
tested, but starting to get there...

This commit was SVN r11810.
2006-09-26 03:26:45 +00:00
Tim Prins
e4f8ad303e Fix for #397
on 64 bit platforms sizeof(size_t) != sizeof(orte_std_cntr_t), and we were incorrectly 
assuming this when dealing with num procs. It worked on little endian platforms, but
not big endian. So change num_procs to type int, and cast where needed. 

This commit was SVN r11796.
2006-09-25 19:41:54 +00:00
Jeff Squyres
38b34b6a7c * Use time(NULL) to seed the random number generator because it has a
wider space than getpid()
 * Include <time.h> to get time()'s prototype
 * Fix typo that prevented using /dev/urandom on systems that had it

This commit was SVN r11780.
2006-09-25 15:32:54 +00:00
Jeff Squyres
c5cc1f0c1a Add man page for wrapper compilers.
Fixes trac:358.

This commit was SVN r11773.

The following Trac tickets were found above:
  Ticket 358 --> https://svn.open-mpi.org/trac/ompi/ticket/358
2006-09-25 14:11:21 +00:00
Brian Barrett
2bfb2b8a8a * Add sys/stat.h so that this compiiles on OS X
* Properly protect headers with #ifdefs

This commit was SVN r11771.
2006-09-24 18:40:55 +00:00
Galen Shipman
01de9de9a0 Use /dev/urandom.. doesn't block like /dev/random may..
This commit was SVN r11769.
2006-09-24 07:52:42 +00:00
Tim Prins
a4f1018afd cleanup compiler warning
This commit was SVN r11763.
2006-09-23 01:17:39 +00:00
Brian Barrett
3c814fdd23 fixes trac:391
Fix for double mutex free that would cause an abort condition in the orted
whenever threads were enabled.

This commit was SVN r11759.

The following Trac tickets were found above:
  Ticket 391 --> https://svn.open-mpi.org/trac/ompi/ticket/391
2006-09-22 19:24:42 +00:00
Andrew Friedley
798c19d395 Blah.. we should always return after try_connect() here, not just when we have an error.
Another fix for ticket #362.

This commit was SVN r11756.
2006-09-22 15:51:11 +00:00
Tim Prins
567676f3c1 - Formatting and minor cleanup
- made it so we now set the architecture of each node we discover
- remove debugging output

This commit was SVN r11751.
2006-09-22 13:24:32 +00:00
Tim Prins
83a7f6e4de Fix for bug #369.
LoadLeveler only sets LOADL_PROCESSOR_LIST when there are 128 or less tasks allocated to a job. The POE RAS relied on this variable so I created a new RAS which uses the LoadLeveler API instead of relying on the environment variable. This still needs some testing, so for now we use the POE RAS whenever LOADL_PROCESSOR_LIST, otherwise we fall back on this component.

Unfortunately, this will require an autogen...

This commit was SVN r11732.
2006-09-21 00:08:49 +00:00
Galen Shipman
04e9483aab fall back to rand() if /dev/random doesn't exist or the read to /dev/random
would block.. 

This commit was SVN r11725.
2006-09-20 16:59:44 +00:00
Andrew Friedley
8895bf7369 Fix the fix (r11718) for bug #362.
We were still waiting the entire duration of the timeout before we figured out that a connect() was successful.  Re-introduce adding the peer_send_event so that we detect immediately when a connect() completes.

Also make sure to delete the timeout event in complete_connect().

Fixed a struct timeval initialization warning reported by Jeff.

Remove an erroneous opal_output().

This commit was SVN r11724.

The following SVN revision numbers were found above:
  r11718 --> open-mpi/ompi@1b6231a9b5
2006-09-20 14:29:37 +00:00
Andrew Friedley
1b6231a9b5 Fix for running jobs that span multiple 's' partitions on IU BigRed.
Each 's' partition has its own TCP network.  It's fine to use this network for jobs that fit inside the partition, but the TCP OOB errors when trying to connect across two partitions, because there are two disjoint networks.  Each node also has another TCP network connecting ALL nodes together.

So the solution is to actually try all the available TCP interfaces on a node, instead of erroring when the first one fails.

Also, the default TCP connect() timeout is way too long (5 minutes) - use our own timeout mechanism, with the timeout value expressed as an MCA parameter.

This commit was SVN r11718.
2006-09-19 19:33:49 +00:00
Tim Prins
c4db5654fa Fix for bug #370
The POE ras did not correctly enter the number of slots per node. This fixes that.

This commit was SVN r11716.
2006-09-19 16:27:15 +00:00
Ralph Castain
977e3c5ca1 Let's see if Cyrador understands this version a little better...
This commit was SVN r11709.
2006-09-19 13:05:40 +00:00
Ralph Castain
0ad0d84afd Add two new API functions to the RMGR, and modify the "spawn" API to support the enhanced MPI-2 functionality.
No implementation backs these new APIs - just placeholders for now.

This commit was SVN r11699.
2006-09-19 01:45:05 +00:00
George Bosilca
f8de894efe This one wasn't supposed to get into the repository.
This commit was SVN r11697.
2006-09-18 21:28:55 +00:00
George Bosilca
7ad23ff97b Be 100% total view friendly. Let tv find out the real name of our
executable and export all functions as they should be.

This commit was SVN r11694.
2006-09-18 17:55:14 +00:00
Ralph Castain
d7e61e40fc Quiet a few warnings from Cyrador
This commit was SVN r11686.
2006-09-18 12:40:42 +00:00
Ralph Castain
8a291afda6 Ensure the rds_private.h file gets included in the distribution
This commit was SVN r11682.
2006-09-16 11:45:02 +00:00
Ralph Castain
f906af983a Forgot to change the silly Makefile.am names - sorry Cyrador!
This commit was SVN r11670.
2006-09-15 04:52:20 +00:00
Jeff Squyres
8226dab86c Fixes trac:377
Add --enable-orterun-prefix-by-default (and a synonym:
--enable-mpirun-prefix-by-default) to make orterun always behave as if
"--prefix $prefix" was given on the command line (where $prefix is the
value given to the --prefix option to configure).  This prevents many
rsh/ssh users from needing to modify their shell startup files to set
the LD_LIBRARY_PATH for Open MPI (they will still need to set PATH or
otherwise find the OMPI executables to mpicc/mpirun/etc. their MPI
applications).

Also added --noprefix option to orterun to disable this behavior.
Finally, note that even if --enable-orterun-prefix-by-default is
specified, if the user specifies --prefix or /path/to/mpirun, these
options will override the default value of the prefix ($prefix).

This commit was SVN r11669.

The following Trac tickets were found above:
  Ticket 377 --> https://svn.open-mpi.org/trac/ompi/ticket/377
2006-09-15 02:52:08 +00:00
Jeff Squyres
3e239f4532 Add a missing .ompi_ignore
This commit was SVN r11666.
2006-09-15 02:36:22 +00:00
George Bosilca
4fe39a4e7d The old PLS is now called a ODLS. However, the real name is not windows but process. This
change will follow shortly...

This commit was SVN r11663.
2006-09-14 22:22:34 +00:00
Ralph Castain
37dfdb76eb Here is the major MAD-cure commit. I have written plenty about it, so I refer you here to those messages for a description of everything that was done.
This commit was SVN r11661.
2006-09-14 21:29:51 +00:00
George Bosilca
17afe7dc9f Do it on the correct way as this is normally compiled as a module.
This commit was SVN r11660.
2006-09-14 21:22:41 +00:00
George Bosilca
01c5a115b2 Don't export the POE module. Only the component have to be exported (visible).
This commit was SVN r11659.
2006-09-14 21:20:31 +00:00
Galen Shipman
b02185374f Push a generated "key" out to all the processes. This is necessary for some
interconnect wireup in which all processes must agree on a "key" to initialize
the interconnect with. 

This commit was SVN r11653.
2006-09-14 15:27:17 +00:00
Josh Hursey
908f31fe9f Fix a code clarity issue in the POE PLS.
Allow the POE RAS to be compled for linux as well as AIX.
The POE RAS is really a Loadleveler RAS, and IU now has
a cluster that uses Loadleveler in a Linux environment (BigRed).

This seems to be the only thing we need to do so far to run 
Open MPI on BigRed. Yay :)

This commit was SVN r11600.
2006-09-09 05:13:15 +00:00
Josh Hursey
160120b4c5 Fix a cut-n-paste error that causes the 'num_concurrent' to be
set to 1 or 0 instead of the user defined number or default (128).

This caused the PLS to deadlock when using '--debug-daemons' with
more than 2 processes. :(

svn blame says that it was broken in r11347

It is *not* a problem on v1.1 or v1.2 branches.

Bug spotted by Tim Mattox and myself.

This commit was SVN r11575.

The following SVN revision numbers were found above:
  r11347 --> open-mpi/ompi@f52c10d18e
2006-09-08 15:17:17 +00:00
Jeff Squyres
0f11584a6c * Update svn:ignore
* Remove svn:executable from non-executable files

This commit was SVN r11555.
2006-09-07 17:17:40 +00:00
George Bosilca
e33c35112b Correct the conversion between int and bool. Apply it on all files except
the one that will be modified by Ralph for the ORTE 2.0. The missing ones
are in the rsh PLS.

This commit was SVN r11476.
2006-08-28 18:59:16 +00:00
Ralph Castain
9e6e9b8619 Fix a couple of variable declarations
This commit was SVN r11467.
2006-08-28 13:28:10 +00:00
George Bosilca
07b8d3c72c On Windows we can now deliver Open MPI on several flavors:
- everything statically built (dynamically opened).
- OPAL, ORTE and OMPI static libraries and all the components
  as dynamic files(DLL).
- everything as dynamic files (DLL).

This commit was SVN r11461.
2006-08-28 04:19:42 +00:00
George Bosilca
c2311f6e42 Don't define the yywrap function.
This commit was SVN r11459.
2006-08-28 04:11:25 +00:00
George Bosilca
693c835137 No need to cast as the returned value is already in the
expected type.

This commit was SVN r11458.
2006-08-28 04:10:43 +00:00
George Bosilca
ba1514f2e7 A slightly more Windows friendly version. Unfortunately there
is no support for SGE on Windows.

This commit was SVN r11436.
2006-08-27 04:46:43 +00:00
George Bosilca
7e7bae335e Protect the environ variable on windows.
This commit was SVN r11435.
2006-08-27 04:44:17 +00:00
Pak Lui
131f0eff04 fix the verbose value.
This commit was SVN r11418.
2006-08-24 21:30:08 +00:00
Pak Lui
65a524dd0d - need to provide option for showing the grid engine's JOB_ID in case the grid engine job needs to be killed
- clean up the orted_path and debug message

This commit was SVN r11413.
2006-08-24 20:27:19 +00:00
Pak Lui
4f75dfd353 - missed the opal_os_path() for LD_LIBRARY_PATH
This commit was SVN r11410.
2006-08-24 18:58:50 +00:00
George Bosilca
9110ea2b80 Add the Windows fork component. As fork is not available on Windows, I
create a process component which use CreateProcess to spawn the child.
Special care should be taken in order to correctly redirect the stdin,
stdout and stderr of the child process.

This commit was SVN r11405.
2006-08-24 17:51:20 +00:00
George Bosilca
0d607c1346 Use opal_os_path and OPAL_PATH_SEP to build the file path. I don't have any
machine to test, so I hope I get it right.

This commit was SVN r11398.
2006-08-24 16:20:32 +00:00
George Bosilca
e04032ca2f Correct a comment and protect the usage of the environ variable against Windows.
This commit was SVN r11397.
2006-08-24 16:18:42 +00:00
Pak Lui
5220c1ca42 - converted some tabs into spaces
This commit was SVN r11384.
2006-08-23 23:21:08 +00:00
Pak Lui
9dda057f05 - Do the changes as in r11347 for gridengine to use opal_os_path().
- Remove extra NULL argument from rsh module.

This commit was SVN r11377.

The following SVN revision numbers were found above:
  r11347 --> open-mpi/ompi@f52c10d18e
2006-08-23 20:40:01 +00:00
Jeff Squyres
715bae369c Remove extra argument - now obsoleted by the use of opal_os_path().
This commit was SVN r11366.
2006-08-23 14:32:06 +00:00
Brian Barrett
e39f0096a0 * add header file to sources list so make dist works
This commit was SVN r11357.
2006-08-23 13:31:56 +00:00
George Bosilca
fdfae70dbe Use environ.
This commit was SVN r11353.
2006-08-23 06:19:47 +00:00
George Bosilca
75fa0317da Keep environ as the prefered storage for the environment variables.
This commit was SVN r11351.
2006-08-23 06:14:24 +00:00
George Bosilca
c03ef692c1 And the missing header.
This commit was SVN r11348.
2006-08-23 03:33:35 +00:00
George Bosilca
f52c10d18e And ORTE is ready for prime-time. All Windows tricks are in:
- use the OPAL functions for PATH and environment variables
- make all headers C++ friendly
- no unamed structures
- no implicit cast.

Plus a full implementation for the orte_wait functions.

This commit was SVN r11347.
2006-08-23 03:32:36 +00:00
George Bosilca
aecdfc80eb Don't orget to relase the object if we detect an error.
This commit was SVN r11346.
2006-08-23 02:43:05 +00:00
George Bosilca
b4732f557a Now it's time to update ORTE. Cleanup most of the ORTE tools. Force them
to use opal_basename and opal_dirname. Don't create the path manually. Use
the specialized opal functions instead.

This commit was SVN r11345.
2006-08-23 02:35:00 +00:00
George Bosilca
0417d27f46 orte_std_cntr_t vs. size_t round 2. Advantage for size_t ...
This commit was SVN r11317.
2006-08-22 14:58:31 +00:00
Ralph Castain
c3ba1c1cc1 Fix a pack/unpack mismatch
This commit was SVN r11315.
2006-08-22 13:50:59 +00:00
George Bosilca
6ef0acf99f The names of the defines should start with OPAL as they belong to the
OPAL layer.
We now support 64 bits Windows too.

This commit was SVN r11312.
2006-08-21 21:55:41 +00:00
Ralph Castain
73a7916946 For Ollie...fix a few names. Should help the Bproc SMR component compile.
This commit was SVN r11284.
2006-08-21 15:11:20 +00:00
George Bosilca
6afa4c6c64 Windows friendly version. We have to split the OMPI_DECLSPEC in at least 3
different macros, one for each project. Therefore, now we have OPAL_DECLSPEC,
ORTE_DECLSPEC and OMPI_DECLSPEC. Please use them based on the sub-project.

This commit was SVN r11270.
2006-08-20 15:54:04 +00:00
Ralph Castain
ee04e04dd0 Attempt to cleanup the xgrid pls module
This commit was SVN r11261.
2006-08-18 21:21:31 +00:00
Ralph Castain
6bf06d4602 Fix connect-accept by cleaning up two minor bugs.
This commit was SVN r11260.
2006-08-18 21:12:03 +00:00
Ralph Castain
517d6fda49 Add the smr_private include file so it gets put in tarballs
This commit was SVN r11243.
2006-08-17 12:24:44 +00:00
Ralph Castain
8c7f0ed9ae Change the SOH to the new State Monitoring and Reporting (SMR) framework. New API's will be appearing in the new framework shortly - this just gets the name change into the system.
Other changes:

1. Remove the old xcpu components as they are not functional.

2. Fix a "bug" in orterun whereby we called dump_aborted_procs even when we normally terminated. There is still some kind of bug in this procedure, however, as we appear to be calling the orterun job_state_callback function every time a process terminates (instead of only once when they have all terminated). I'll continue digging into that one.

This will require an autogen/configure, I'm afraid.

This commit was SVN r11228.
2006-08-16 16:35:09 +00:00
Ralph Castain
5dfd54c778 With the branch to 1.2 made....
Clean up the remainder of the size_t references in the runtime itself. Convert to orte_std_cntr_t wherever it makes sense (only avoid those places where the actual memory size is referenced).

Remove the obsolete oob barrier function (we actually obsoleted it a long time ago - just never bothered to clean it up).

I have done my best to go through all the components and catch everything, even if I couldn't test compile them since I wasn't on that type of system. Still, I cannot guarantee that problems won't show up when you test this on specific systems. Usually, these will just show as "warning: comparison between signed and unsigned" notes which are easily fixed (just change a size_t to orte_std_cntr_t).

In some places, people didn't use size_t, but instead used some other variant (e.g., I found several places with uint32_t). I tried to catch all of them, but...

Once we get all the instances caught and fixed, this should once and for all resolve many of the heterogeneity problems.

This commit was SVN r11204.
2006-08-15 19:54:10 +00:00
Brian Barrett
cd7b138d74 propogate up errors when setting up standard input forwarding
This commit was SVN r11187.
2006-08-14 21:09:05 +00:00
Ralph Castain
d2912f03e0 Cleanup a historical naming convention problem. Move the socket_errno definitions to the OPAL layer and change the name accordingly. This cleans up some interrelationship issues as well as removing a name confusion.
This commit was SVN r11186.
2006-08-14 20:14:44 +00:00
Ralph Castain
663e25f7cb Finalize the Bproc vpid algorithm.
Bproc is now fully operational and supports oversubscribed conditions for both bynode and byslot mapping procedures.

This commit was SVN r11180.
2006-08-14 19:16:11 +00:00
Ralph Castain
285aea1c0c Update to bproc algorithm to support oversubscription - committing to move to another test environment.
Note that this may break bproc for the moment.

This commit was SVN r11178.
2006-08-14 18:34:13 +00:00
Ralph Castain
d56df1c48e Add a simply program that reports the node and process name.
Note that some compile warnings are generated here because of the direct inclusion of an orte include file in the program. Not entirely sure why that is happening (it is relatively new phenomenon), but it doesn't cause any problems in terms of operation.

This commit was SVN r11175.
2006-08-14 17:45:50 +00:00
Ralph Castain
de9156552b I have confirmed that the later version of the bproc launcher does support Bproc 3, so it appears that the outdated bproc_seed launcher truly is no longer required.
This commit was SVN r11164.
2006-08-12 07:47:21 +00:00
Ralph Castain
0ccc910485 Fix the Bproc vpid computation so that, when we map by slot, adjacent processes have vpids differing by only one.
I will ammend the documentation in the files shortly to explain why this was previously broken.

This commit was SVN r11162.
2006-08-11 19:41:33 +00:00
Pak Lui
8fab3d5b82 * Inadvertently removed a wrong variable during the last change.
This commit was SVN r11157.
2006-08-11 16:00:39 +00:00
Ralph Castain
59d6f1e2eb Remove ompi_ignores on gridengine components as this seems resolved - thanks Pak for quick response!
Fixed a few very minor compiler complaints in the pls_gridengine_module.c file. ISO C is less forgiving about where variables get declared.

This commit was SVN r11156.
2006-08-11 15:32:17 +00:00
Pak Lui
99a0521e44 * Fix the issue that Ralph observed in MacOS X with an invalid header file
and other warnings.

This commit was SVN r11155.
2006-08-11 15:04:51 +00:00
Ralph Castain
5fd6306c2f Add ompi_ignores until the configuration can be fixed
This commit was SVN r11154.
2006-08-11 14:11:41 +00:00
Pak Lui
08352878cc * Added in new ras and pls components to support Sun N1 Grid Engine (N1GE)
6 and its open source version as the job launchers for ORTE.

This commit was SVN r11153.
2006-08-10 21:46:52 +00:00
Ralph Castain
ec3eeb819d Remove unused variable to make Cyrador happy.
This commit was SVN r11144.
2006-08-10 12:57:55 +00:00
Ralph Castain
bd937b219d Tell xcast not to send to processes that have "aborted".
One of those fixes that has been sitting on another branch for awhile...sigh.

This commit was SVN r11142.
2006-08-09 18:23:43 +00:00
Ralph Castain
56c15963af Finalize the session directory and runtime when the orted exits due to a failed launch.
This commit was SVN r11141.
2006-08-09 17:00:53 +00:00
Ralph Castain
8496b6aff4 When a "fork" launch cannot find the executable, the system used to just return an error. This meant that the state of that process was never updated in the registry, leaving the counters at the incorrect levels. As a result, the triggers would never fire to indicate that the job had been aborted. This left orterun and other orteds/processes hanging.
This fix should fix the problem. I will test it on a broader range of systems forsooth...

This commit was SVN r11140.
2006-08-09 15:29:08 +00:00
Ralph Castain
ddd575d126 Ensure that the localhost gets placed on the registry with the same name as found in the system_info structure. Otherwise, we wind up with confusion in the session directory names.
This commit was SVN r11139.
2006-08-09 15:26:37 +00:00
Brian Barrett
59844f2119 Galen noticed that the soh component wasn't linking against the bproc
libraries.  Fix that issue.

This commit was SVN r11119.
2006-08-07 16:20:33 +00:00
Brian Barrett
16186978bb - Fix some compile issues in r11109
- indent / whitespace cleanup
- don't set --daemon-debug when pls debug is given, as it seems to make
  the daemons abort.

This commit was SVN r11113.

The following SVN revision numbers were found above:
  r11109 --> open-mpi/ompi@da7df6d257
2006-08-03 18:51:42 +00:00
Galen Shipman
da7df6d257 monitor bproc node state and terminate the job if a node in our job goes
down.. 

This commit was SVN r11109.
2006-08-03 05:29:49 +00:00
Ralph Castain
e0cd034e13 Remove unused variable
This commit was SVN r11084.
2006-08-02 12:26:41 +00:00
Ralph Castain
bd7e8febb1 Bring over the ORTE 2.0 DSS. This introduces a few changes, almost all of which are transparent to the user:
1. Introduces a flag for the type of buffer that now allows a user to either have a fully described or a completely non-described buffer. In the latter case, no data type descriptions are included in the buffer. This obviously limits what we can do for debugging purposes, but the intent here was to provide an optimized communications capability for those wanting it.

Note that individual buffers can be designated for either type using the orte_dss.set_buffer_type command. In other words, the buffer type can be set dynamically - it isn't a configuration setting at all. The type will default to fully described. A buffer MUST be empty to set its type - this is checked by the set_buffer_type command, and you will receive an error if you violate that rule.

IMPORTANT NOTE: ORTE 1.x actually will NOT work with non-described buffers. This capability should therefore NOT be used until we tell you it is okay. For now, it is here simply so we can begin bringing over parts of ORTE 2.0. The problem is that ORTE 1.x depends upon the transmission of non-hard-cast data types such as size_t. These "soft" types currently utilize a "peek" function to see their actual type in the buffer - obviously, without description, the system has no idea how to unpack these "soft" types. We will deal with this later - for now, please don't use the non-described buffer option.

2. Introduces the orte_std_cntr_t type. This will become the replacement for the size_t's used throughout ORTE 1.x. At the moment, it is actually typedef'd to size_t for backward compatibility.

3. Introduces the orte_dss.arith API that supports arbitrary arithmetic functions on numeric data types. Calling the function with any other data type will generate an error.

This commit was SVN r11075.
2006-08-01 18:42:25 +00:00
Josh Hursey
d1e1a68645 This commit contains the necessary changes to get "mpirun a.out" working
correctly with MPI_Comm_spawn.

The problem wiht MPI_Comm_spawn was that the 'parent' process was 
rmgr.create'ing and then rmgr.launch'ing the children via the rmgr proxy
component. The HNP saw these commands and processed them normally, but
since we never went through the HNP's rmgr (urm component) spawn() 
logic the triggers and key/value pairs were never created. So the
children were launched correctly, but since the HNP did not
have any triggers setup, never triggered the xcast for the
children to finish orte_init().

This fix puts the trigger and key/value pair initialization in 
rmgr_urm_spawn() for the 'mpirun a.out' case, *and* in the 
rmgr_base_unpack routine that deals with the creation of the
job for the child as requested by the proxy component. This
will allow the triggers to be registered for the proxy's request
which only happens during MPI_Comm_spawn*

Small change for a lot of debugging. Notice that his reverts r11037
to its previous version, and adds a newline to handle the spawn
cases.

This commit was SVN r11046.

The following SVN revision numbers were found above:
  r11037 --> open-mpi/ompi@5813fb7d2a
2006-07-28 17:17:31 +00:00
Josh Hursey
5813fb7d2a It seems that MPI_Comm_spawn{_multiple} has been broken since r10708
By reverting this file (changeset from commit r10708) to its previous
version fixes the problem.

This should be moved to the v1.1 branch where it is also broken.

This commit was SVN r11037.

The following SVN revision numbers were found above:
  r10708 --> open-mpi/ompi@febc143d8c
2006-07-27 21:21:10 +00:00
Brian Barrett
c744f650ba * really didn't mean for this patch (the threaded accept() code) to come in with
r10841, so revert it (and it's fixes) out.  Will bring back once cleaned up from
  the code used in the tbird experiment

This commit was SVN r10991.

The following SVN revision numbers were found above:
  r10841 --> open-mpi/ompi@dfa1221c3b
2006-07-25 22:32:01 +00:00
Jeff Squyres
c2d4dfce78 Remove unused variable
This commit was SVN r10985.
2006-07-25 21:43:21 +00:00
Jeff Squyres
bdab8d744c Send a pointer to the data, not the data itself. Otherwise, we could
get a segv in some cases.

This commit was SVN r10984.
2006-07-25 21:42:44 +00:00
Ralph Castain
65acc9325a Fix a bug that crept in during the last change to support "mpirun a.out" operations. Since we now reserve a range of vpids for each app_context, we no longer need to track the rank and offset the starting vpid each time through the mapper - the name service automatically accounts for the offset when allocating the next starting vpid for the job.
This should be shifted to v1.1.

This commit was SVN r10916.
2006-07-20 21:06:15 +00:00
Ralph Castain
8bec270f90 Fix a bug noted by Jeff - we were no longer accurately recording in the registry that a process had been terminated when the user initiated the "kill" process (via cntrl-c).
Added another system-level test function for ORTE that just spins until terminated by a ctrl-c signal.

Modified orterun - added a couple of newlines to the output when abnormally terminating so the prompt always is on a new line.

This commit was SVN r10866.
2006-07-18 14:42:27 +00:00
Gleb Natapov
f15fc4ef2f include signal.h for SIGPIPE definition
This commit was SVN r10863.
2006-07-18 09:07:53 +00:00