1
1
Граф коммитов

928 Коммитов

Автор SHA1 Сообщение Дата
Tim Prins
08d5ca821f Don't get the node architecture when useing the LoadLevleer RAS. It is slow (about a second for ~300 nodes) and we don't even use the value.
This commit was SVN r12758.
2006-12-05 13:47:53 +00:00
Ralph Castain
eb941d8ae2 Fix a bug that declared a node as "oversubscribed" a little early during the mapper procedure. This only affected the mapping procedure, and only if you had set the "--no-oversubscribe" flag.
Kudos to Tim Prins for finding it.

This commit was SVN r12757.
2006-12-05 13:04:27 +00:00
George Bosilca
6f28bcdc21 Remove the last set of compiler warnings from the precondition file.
This commit was SVN r12753.
2006-12-04 21:45:57 +00:00
Brian Barrett
d64fa194f1 Instead of continually screwing around with different format strings to
make this warning-proof, loop over the uint64_ts as an array of integers
and use %x.  The final string is just as random and formatted exactly
the same, so we're all good in that department.

Refs trac:655

This commit was SVN r12742.

The following Trac tickets were found above:
  Ticket 655 --> https://svn.open-mpi.org/trac/ompi/ticket/655
2006-12-04 18:07:24 +00:00
Gleb Natapov
f0132b2499 Provide parameters in a correct order (processor/oversubscribed was swapped).
This commit was SVN r12737.
2006-12-04 12:55:45 +00:00
Rainer Keller
d078bb3e8a - Revert changes and include pointers to discussion.
This commit was SVN r12736.
2006-12-03 17:05:15 +00:00
Rainer Keller
e61dd8722e - Silence compiler on ORTE_TRANSPORT_KEY_FMT, it is fixed to llx
- No functional changes, just indentation and corrections to error
   output.

This commit was SVN r12734.
2006-12-03 13:59:23 +00:00
George Bosilca
a0ed53d70b Make the compilers happy.
This commit was SVN r12729.
2006-12-03 00:19:11 +00:00
Ralph Castain
4151a46871 Per Jeff's request (which made a lot of sense), setup the default buffer type to be DESCRIBED for debug/devel builds, and NON-DESC for optimized builds. The user can still select the default buffer type via mca parameter at runtime - this just sets the default default. :-)
Also, change the dss buffer type mca param to something more easily remembered (it is now "dss_buffer_type"). Heck, even I had to keep looking at the darn code to remember it.

This commit was SVN r12728.
2006-12-02 13:32:16 +00:00
George Bosilca
3fd278c522 Make the tree compile in debug mode.
This commit was SVN r12724.
2006-12-01 23:03:09 +00:00
Ralph Castain
897744cdeb Two major changes to the runtime:
1. implement and enable the non-described buffer operations. I will send out a more detailed explanation separately. However, this mode of operation (which is now the default) significantly reduces message size during startup. If you want the described buffers, set the mca param "-mca dss_describe_buffer 1".

2. revise the xcast system to support both linear and binomial tree broadcast methods. Since we are seeing scenarios where the binomiall tree can cause problems, I have made the linear method the default. To run with the binomial tree, set the mca param "-mca oob_xcast_mode binomial".

3. add some detailed timing reports to the xcast operation. These are enabled via "-mca oob_xcast_timing 1".

4. add some more unit tests for the dss and gpr (focused on support for the non-described buffer)

This commit was SVN r12722.
2006-12-01 22:30:39 +00:00
Jeff Squyres
3cf7dddd47 Fixes trac:635.
Ralph identified the problem, I tracked down ''where'' the fd was
being closed, and Brian figured out ''why'' (and the fix).

What was happening is that a remote process was closing its
stdout/stderr and therefore sending a 0-byte IOF message to mpirun.
mpirun, in turn, closed the iof endpoint associated with that stream
(i.e., stdout/stderr).  IOF does this to handle the case where
mpirun's stdin is closed -- this therefore causes the stdin on all the
ORTE-started processes to have their stdin's closed as well.

So the workaround here is to check that if we get a 0-byte IOF message
on a sink (indicating a remote closure), and if that sink is the
special stdout or stderr stream, don't actually close anything in the
local process.

This commit was SVN r12691.

The following Trac tickets were found above:
  Ticket 635 --> https://svn.open-mpi.org/trac/ompi/ticket/635
2006-11-28 21:42:49 +00:00
Ralph Castain
0398c9e0c5 Correctly setup the sched_yield when launching processes via the orteds. This still doesn't adjust the yield schedule "on-the-fly" as more procs are dynamically added to a node - it just sets it when they are first launched.
This commit was SVN r12683.
2006-11-28 08:27:20 +00:00
George Bosilca
8df8d86b85 Complete the functions to match the expected prototype.
This commit was SVN r12680.
2006-11-28 00:44:30 +00:00
Ralph Castain
bc4e97a435 First stage in the move to a faster startup. Change the ORTE stage gate xcast into a binary tree broadcast (away from a linear broadcast). Also, removed the timing report in the gpr_proxy component that printed out the number of bytes in the compound command message as the answer was "not much" - reduces the clutter in the data.
This commit was SVN r12679.
2006-11-28 00:06:25 +00:00
Ralph Castain
652b91ee26 Remove some compiler warnings
This commit was SVN r12678.
2006-11-27 23:47:36 +00:00
Ralph Castain
9bc25f0bec Fix a potential bug in the registry where it didn't fully check a segment's name when searching for it. Will have to verify that this doesn't break other things.
Bring the bproc system close to being back online....

This commit was SVN r12659.
2006-11-23 04:17:37 +00:00
Brian Barrett
32833deff0 since orteboot, ortehalt, and ortekill were all added today (including to
configure.ac), we need to add them to SUBDIRS to make them end up in the
tarball as well...

This commit was SVN r12658.
2006-11-23 03:10:57 +00:00
Ralph Castain
deb2470ba3 Move the waitpid callback in the bproc pls *after* we store the daemon info. Otherwise, a short-lived app could terminate before we store the daemon info, causing mpirun to not terminate the daemons since the call to get_active_daemons would return a NULL list.
This commit was SVN r12656.
2006-11-22 22:49:22 +00:00
Rainer Keller
b63500f62c - Dont unlock ompi_rte_mutex unconditionally, use the macro instead.
This commit was SVN r12655.
2006-11-22 21:01:43 +00:00
Ralph Castain
b1ff5fe868 Move the name of the bproc common segment to the central schema location - avoids conflicts when bproc 3 components try to build
This commit was SVN r12654.
2006-11-22 20:23:17 +00:00
Ralph Castain
8080034eb2 Clean up a compile issue for bproc
This commit was SVN r12653.
2006-11-22 19:50:27 +00:00
Ralph Castain
428c1f14c3 Modify the bproc components to resolve the current allocation problem
This commit was SVN r12652.
2006-11-22 19:10:58 +00:00
Ralph Castain
7f95b27141 Correctly "hide" the new orte tools - they shouldn't get compiled or seen unless you specifically go into those subdirectories and manually do a "make".
This commit was SVN r12650.
2006-11-22 14:35:16 +00:00
Sven Stork
dc116d4814 - Add missing mutex lock
This commit was SVN r12649.
2006-11-22 13:37:58 +00:00
Ralph Castain
6fca1431f3 Back out some prior commits. These commits fixed bproc so it would run, but broke several other things (singleton comm_spawn and hostfile operations have been identified so far). Since bproc is the culprit here, let's leave bproc broken for now - I'll work on a fix for that environment that doesn't impact everythig else.
This commit was SVN r12648.
2006-11-22 13:30:21 +00:00
Brian Barrett
0895f5e08d Rename OMPI_PROCESS_NAME_{HTON, NTOH} macros to ORTE_PROCESS_NAME_{HTON, NTOH}
because they are in ORTE, not OMPI.  Also, remove the ORTE_PROCESS_NAME macros
in iof base as they are duplicates of the ones that were in ns_types, which 
meant that bad things happened if you changed what an orte_process_name_t
looked like.

This commit was SVN r12646.
2006-11-22 03:03:21 +00:00
Brian Barrett
33320b7165 Rework the opal_progress interface to better support dynamic processes and at
the same time, remove some of the MPI-related options from OPAL:

  - provide mechanism to change at runtime whether sched_yield() should 
    be called when the progress engine is idle
  - provide mechanism for changing the rate at which the event engine
    is called when there are "no" users of the event engine (ie, when
    using MPI but not TCP)
  - fix some function names in the progress engine to better match
    their intended use (and remove MPI naming scheme)
  - remove progress_mpi_enable / progress_mpi_disable because 
    we can now use the functions to set the sched_yield and
    tick rate interfaces
  - rename opal_progress_events() to opal_progress_set_event_flag()
    because the first really isn't descriptive of what the function
    does and I always got confused by it

This commit was SVN r12645.
2006-11-22 02:06:52 +00:00
Ralph Castain
9f3dcd147a Round and round the mulberry bush we go...
Fix comm_spawn by singletons. orte_init does some voodoo to let the system know about localhost when we are a singleton. This includes allocating it so that any comm_spawn'd children can use their parent "allocation". Unfortunately, the fix that bproc needs (due to that smr filling up the node segment!) causes the singleton startup to fail. The fix is to just have the singleton startup force an allocation of its localhost.

Only issue here is: what happens if we are in a persistent universe? The singleton will now overwrite any prior info on slots used on localhost by other jobs (won't affect anything else). The answer, of course, is to do something more intelligent - lookup localhost on the registry and just update its info instead of overwriting it.

Something for another day (or month....or year)

This commit was SVN r12644.
2006-11-21 21:51:58 +00:00
Ralph Castain
761d4fab25 cleanup unused variables
This commit was SVN r12643.
2006-11-21 20:51:39 +00:00
Ralph Castain
a30c65ca24 Fix the allocator to make bproc happy.
We were burned again by the fact that the bproc state monitor creates entries on the node segment for  *all* the nodes in the cluster when it is opened during orte_init. As a result, the bjs allocator was never being called, and the system merrily assumed that *all* nodes in the cluster had been allocated to it.

To fix this, I removed a test that had been inserted into the allocation procedure that checked for a non-zero node segment. This was an old artifact - the RAS components already know that they are not to overwrite any existing node segment entries (at least, bproc does - I will check the others. For now, I just want to save the bproc fix on this machine).

This commit was SVN r12640.
2006-11-21 19:52:55 +00:00
Ralph Castain
050e401671 Simplify - the cellid is simply a field in the process name. Recently, we decided to just directly access it and get rid of extraneous function calls.
This commit was SVN r12638.
2006-11-21 09:59:24 +00:00
Tim Prins
2afb401e39 fix some compile warnings
This commit was SVN r12636.
2006-11-21 00:33:10 +00:00
Galen Shipman
c06b740220 a few more opps to get the cellid...
This fixes a compilation error on bproc machines.. 

This commit was SVN r12631.
2006-11-20 19:45:01 +00:00
Ralph Castain
33affed09c Bring ortehalt to a preliminary capability. It will corectly order a persistent daemon to exit cleanly. Need to now interface it to orterun, clean up a few things here and there
This commit was SVN r12626.
2006-11-18 04:47:51 +00:00
Ralph Castain
ea1e0d34c8 Fix the SLURM PLS and SDS components so they correctly communicate the name of the node. This repairs a number of comm_spawn issues seen on Odin and other SLURM machines.
This commit was SVN r12621.
2006-11-17 20:51:03 +00:00
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