1
1
Граф коммитов

732 Коммитов

Автор SHA1 Сообщение Дата
Aurelien Bouteiller
ccb3f75e8f Make sure that the pml v parasite never get loaded when user did not requested FT. This does not break the ability to switch protocol on the fly.
This commit was SVN r16114.
2007-09-12 20:47:17 +00:00
Aurelien Bouteiller
828af95be8 Major modification of the vprotocol framework build system. With a better integration in autogen.sh, it allows for generating static-components.h the usual way.
NOTE: This build system does not work with the current autogen.sh. Modified one is under heavy testing to make sure it does not have side effects 

This commit was SVN r16110.
2007-09-12 18:46:37 +00:00
George Bosilca
05ae27c68b Don't segfault if we receive a fragment for a non existing communicator.
Instead, drop it by now.

This commit was SVN r16105.
2007-09-12 17:52:02 +00:00
Shiqing Fan
a0660f4deb - Just some type casts.
This commit was SVN r16100.
2007-09-12 15:29:58 +00:00
Gleb Natapov
07c8fddeef Fix scheduling of pending send request. It should be scheduled req_lock times.
This commit was SVN r16096.
2007-09-12 07:08:38 +00:00
George Bosilca
d8fed2cfa1 Set a default value so that some compilers stop complaining about
uninitialized values.

This commit was SVN r16094.
2007-09-11 18:00:53 +00:00
Gleb Natapov
79011279e5 Remove debug output.
This commit was SVN r16016.
2007-08-30 13:29:41 +00:00
Gleb Natapov
690fb95bda Cleanup send scheduling code.
This commit was SVN r16014.
2007-08-30 12:10:04 +00:00
Gleb Natapov
0b0f9d14aa Mark send request complete on PML level only when absolutely sure there is
no more work associated with this request. No more outstanding completions or
packets and send scheduling isn't running in another thread.

This commit was SVN r16013.
2007-08-30 12:08:33 +00:00
Gleb Natapov
eac2674f66 The inner voice tells me this is a typo.
This commit was SVN r16004.
2007-08-29 13:28:47 +00:00
Brian Barrett
59b22533f2 Enable RDMA for heterogeneous situations. Currently done by overloading
the ompi_convertor_need_buffers function to only return 0 if the convertor
is homogeneous (which it never does on the trunk, but does to on v1.2, but
that's a different issue).  Only enable the heterogeneous rdma code for
a btl if it supports it (via a flag), as some btls need some work for this
to work properly.  Currently only TCP and OpenIB extensively tested

This commit was SVN r15990.
2007-08-28 21:23:44 +00:00
Gleb Natapov
fa69c5cc10 If a memory on a sender's size is not registered don't register it on a receive
side too. Otherwise a content of the recvreq->req_rdma array is replaced later
without freeing previous content and refcount on registration in mpool become
wrong.

This commit was SVN r15978.
2007-08-28 07:43:06 +00:00
Gleb Natapov
e1a1d9d90e Receive request converter can be accessed in parallel by a thread that receives
data and a thread that run RDMA schedule function. Protect access to the
converter by a lock.

This commit was SVN r15967.
2007-08-27 11:41:42 +00:00
Gleb Natapov
065d04dfde Do not free recvreq while schedule function is running in another thread.
This commit was SVN r15964.
2007-08-27 11:31:40 +00:00
Rainer Keller
1b5fa48a29 - Add missing PERUSE_COMM_REQ_REMOVE_FROM_POSTED_Q when matching
from the posted generic_recv-queue.
 - Move the PERUSE_COMM_MSG_MATCH_POSTED_REQ from
   MCA_PML_OB1_RECV_REQUEST_MATCHED to
   mca_pml_ob1_recv_frag_match() as suggested by Terry Dontje
   Only post, if this is not a probe/iprobe request.
 - Do not post PERUSE_COMM_REQ_MATCH_UNEX for probes / iprobes and
   do in correct order before PERUSE_COMM_MSG_REMOVE_FROM_UNEX_Q

This commit was SVN r15947.
2007-08-23 07:09:43 +00:00
Rainer Keller
c175801f98 - Initialize in the order of mca_pml_ob1_comm_proc_t...
This commit was SVN r15946.
2007-08-23 05:56:22 +00:00
Rainer Keller
b0df55d53b - For MPI_Probe/MPI_Iprobe, we should not have a
PERUSE_COMM_REQ_ACTIVATE event.
   Therefore move the PERUSE_TRACE_COMM_EVENT for this event from
   MCA_PML_BASE_SEND_REQUEST_INIT / MCA_PML_BASE_RECV_REQUEST_INIT
   to the proper places into pml_ob1_isend.c / pml_ob1_irecv.c right
   after the MCA_PML_OB1_SEND_REQUEST_INIT /
   MCA_PML_OB1_RECV_REQUEST_INIT.

This commit was SVN r15945.
2007-08-23 05:52:33 +00:00
Gleb Natapov
5596aa5f53 The sizes of mca_pml_ob1_send_request_t and mca_pml_ob1_recv_request_t depend
on a parameter and are determined in runtime. r15346 removed calculation of
correct sizes for this structures. This patch adds it back and fixes trac:1116, #1114.

This commit was SVN r15932.

The following SVN revision numbers were found above:
  r15346 --> open-mpi/ompi@433f8a7694

The following Trac tickets were found above:
  Ticket 1116 --> https://svn.open-mpi.org/trac/ompi/ticket/1116
2007-08-20 12:06:27 +00:00
George Bosilca
c7e0ab93ae Don't forget to include string.h for the strcmp function.
This commit was SVN r15927.
2007-08-19 19:59:15 +00:00
Josh Hursey
729c63cf9d Fix invalid MCA 'base' names so they appear in ompi_info.
A subset of this patch needs to be applied to v1.2

Refs trac:928

This commit was SVN r15918.

The following Trac tickets were found above:
  Ticket 928 --> https://svn.open-mpi.org/trac/ompi/ticket/928
2007-08-18 03:05:45 +00:00
Aurelien Bouteiller
3a83c61c40 Fixed a bug with available space in sender based.
This commit was SVN r15889.
2007-08-16 17:54:26 +00:00
Aurelien Bouteiller
77565d60d9 Heavy modification of the pml_v framework.
* Code cleanup and rationalization
* Fixed: mca_pml_base_send/recv_request are now allocated before recreation by the PML-V
* Fixed: pointer arithmetic bug in sender based that crashed 
* Changed: directory structure. This is one step forward using autogen.sh to build static-components.h (it needs to have the directory structure of a mca framework for this). 

This commit was SVN r15878.
2007-08-16 05:52:30 +00:00
Aurelien Bouteiller
ee708d702d Slight modification to register the name of the selected pml (from the pml framework) instead of the generic mca name. This might be a different name when enabling FT features. This name modification in the modex allows the PMLS to detect a FT protocol mismatch among hosts.
This commit was SVN r15877.
2007-08-16 05:46:11 +00:00
Aurelien Bouteiller
fa7f6f6722 Improved error detection of request types
This commit was SVN r15857.
2007-08-14 17:24:46 +00:00
Aurelien Bouteiller
67399e7c31 Added a debug type checking for request types (to make sure request size is correctly computed).
This commit was SVN r15856.
2007-08-14 17:18:15 +00:00
Aurelien Bouteiller
1d97c183e7 Better argument checking for output function and added a routine for error printing.
This commit was SVN r15855.
2007-08-14 17:17:12 +00:00
Aurelien Bouteiller
ca69915b1e Code cleanup
This commit was SVN r15783.
2007-08-06 22:20:44 +00:00
Mohamad Chaarawi
59a7bf8a9f Merging in the Sparse Groups..
This commit includes config changes..

This commit was SVN r15764.
2007-08-04 00:41:26 +00:00
George Bosilca
e41ee17ca5 Add a small comment that hopefully will enforce the correct ordering of
the fields between CM and the other PML in the requests structure.

This commit was SVN r15760.
2007-08-03 23:59:29 +00:00
Aurelien Bouteiller
1d160ca583 Needed change for vampir pml to work
This commit was SVN r15750.
2007-08-03 02:23:24 +00:00
Gleb Natapov
627d9bc8ed Delay freeing of a send request if scheduling function is running by other
thread.

This commit was SVN r15722.
2007-08-01 12:19:16 +00:00
Aurelien Bouteiller
a403fed18a More checkings (assert) on the output system so that malformed format string does not crash the application at a later random time.
Changed various debug messages to retain most usefull messages

This commit was SVN r15715.
2007-07-31 19:33:39 +00:00
Aurelien Bouteiller
cec9ce8106 Fixed: various warnings with printf(%x, uint64_t) on 32 bit architectures + some left (long) cast for size_t printf.
This commit was SVN r15706.
2007-07-31 17:12:21 +00:00
Aurelien Bouteiller
a5d0e53bb3 Moved replay macros to functions. The performance improvement in process recovery does not worth the debugging hassle.
This commit was SVN r15703.
2007-07-31 16:01:32 +00:00
Aurelien Bouteiller
5a792a3fad (hopefully) fixed various pedantic warning about casts on 32bit machines. Not tried only have 64bits available.
This commit was SVN r15702.
2007-07-31 15:58:19 +00:00
Aurelien Bouteiller
3559fd5d1a Fixed issues with "verbose" output being too silent.
This commit was SVN r15691.
2007-07-30 19:11:15 +00:00
Gleb Natapov
afac5eb93f Guard recv request with lock against simultaneous access from different
threads.

This commit was SVN r15681.
2007-07-30 12:50:38 +00:00
Gleb Natapov
21dd061696 Init req_send_range_lock. Found by Terry Dontje.
This commit was SVN r15677.
2007-07-30 08:21:52 +00:00
Aurelien Bouteiller
17e10ff918 Modified the output system to comply with a wider range of compilers.
Jelena: this should solve the issue you faced today. 

This commit was SVN r15668.
2007-07-27 23:11:00 +00:00
Aurelien Bouteiller
e07b95bdd5 Fixed: warnings with printf(%d, size_t)
Fixed: All copyrights are now correct up to 2007
Fixed: Build system now works with VPATHs
Changed: protocol_example is now ignored by default

This commit was SVN r15627.
2007-07-25 22:28:04 +00:00
Galen Shipman
f6a20715b7 minor nit..
This commit was SVN r15619.
2007-07-25 17:34:37 +00:00
George Bosilca
873bd41796 More fixes for the Windows suport.
This commit was SVN r15602.
2007-07-25 04:22:21 +00:00
George Bosilca
10175c3014 No more warnings in the PML V.
This commit was SVN r15601.
2007-07-25 04:19:58 +00:00
George Bosilca
c6d2e03cdd Correct the prototype for non GNU compilers.
This commit was SVN r15598.
2007-07-25 03:50:35 +00:00
Aurelien Bouteiller
16da13c79e Missing file...
This commit was SVN r15540.
2007-07-20 22:24:02 +00:00
Aurelien Bouteiller
70bb44d7a9 Moving the Message Log framework to the trunk. Protocol example (simple
showcase) and sender based are provided for now.

Ignored by default except for utk folks. 

This commit was SVN r15539.
2007-07-20 21:36:11 +00:00
Brian Barrett
5b9fa7e998 reapply r15517 and r15520, which were removed in r15527 so that I could get
the RML/OOB merge in slightly easier

This commit was SVN r15530.

The following SVN revision numbers were found above:
  r15517 --> open-mpi/ompi@41977fcc95
  r15520 --> open-mpi/ompi@9cbc9df1b8
  r15527 --> open-mpi/ompi@2d17dd9516
2007-07-20 02:34:29 +00:00
Brian Barrett
39a6057fc6 A number of improvements / changes to the RML/OOB layers:
* General TCP cleanup for OPAL / ORTE
  * Simplifying the OOB by moving much of the logic into the RML
  * Allowing the OOB RML component to do routing of messages
  * Adding a component framework for handling routing tables
  * Moving the xcast functionality from the OOB base to its own framework

Includes merge from tmp/bwb-oob-rml-merge revisions:

    r15506, r15507, r15508, r15510, r15511, r15512, r15513

This commit was SVN r15528.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r15506
  r15507
  r15508
  r15510
  r15511
  r15512
  r15513
2007-07-20 01:34:02 +00:00
Brian Barrett
2d17dd9516 temporarily back our r15517 and 15520 so that I can get the RML / OOB changes
to cleanly apply

This commit was SVN r15527.

The following SVN revision numbers were found above:
  r15517 --> open-mpi/ompi@41977fcc95
2007-07-20 01:10:34 +00:00
Ralph Castain
41977fcc95 Remove the cellid field from the orte_process_name_t structure. This only affects a handful of files in itself, but...
Cleanup ALL instances of output involving the printing of orte_process_name_t structures using the ORTE_NAME_ARGS macro so that the number of fields and type of data match. Replace those values with a new macro/function pair ORTE_NAME_PRINT that outputs a string (using the new thread safe data capability) so that any future changes to the printing of those structures can be accomplished with a change to a single point.

Note that I could not possibly find outputs that directly print the orte_process_name_t fields, but only dealt with those that used ORTE_NAME_ARGS. Hence, you may still have a few outputs that bark during compilation. Also, I could only verify those that fall within environments I can compile on, so other environments may yield some minor warnings.

This commit was SVN r15517.
2007-07-19 20:56:46 +00:00
Rich Graham
f2a30cde5d add table of send completion callback functions, on a per send-type
basis.

This commit was SVN r15471.
2007-07-17 21:26:56 +00:00
Rich Graham
0991c3d5f5 move buffered send component clean up out of the pml to ompi_mpi_finalize.
This commit was SVN r15463.
2007-07-17 14:50:52 +00:00
Rich Graham
1a4ce2a961 move setting of the component used to managed buffer sends out of the
pmls, and into ompi_mpi_init.  This is the first of several steps to pull
buffered send management out of the pmls.

This commit was SVN r15451.
2007-07-16 21:52:25 +00:00
George Bosilca
1e825888a5 Fix the problem reported on #1087. The global send and receive requests queues are
now release in the base close, so there is no need for the cm PML to destroy them.

This commit was SVN r15425.
2007-07-13 23:56:09 +00:00
George Bosilca
8643f38adf Don't allow the BTL to be closed before the end of the process. Count the
number of times the BTLs are opened, and then don't remove them until
close was called the same number of times.

This commit was SVN r15376.
2007-07-11 22:21:04 +00:00
George Bosilca
9ed3ede73e Correct the thin and heavy requests management for the CM PML.
This commit was SVN r15361.
2007-07-11 15:10:01 +00:00
George Bosilca
ef7d17d814 Fix a copy&paste typo.
This commit was SVN r15360.
2007-07-11 15:09:06 +00:00
George Bosilca
9b501eb66d Looks like MAX is not a standard macro. Anyway, that the heavy requests is larger than the thin
seems to be a "correct" assumption.

This commit was SVN r15348.
2007-07-11 00:04:33 +00:00
George Bosilca
e19777e910 A more consistent version. As we now share the send and receive queue, we
have to construct/destruct only once. Therefore, the construction will
happens before digging for a PML, while the destruction just before
finalizing the component.

Add some OPAL_LIKELY/OPAL_UNLIKELY.

This commit was SVN r15347.
2007-07-10 23:45:23 +00:00
George Bosilca
433f8a7694 This patch bring full support for message queues in Open MPI. Now the send and
receive queues are shared among all PMLs, they are declared in the base PML,
and the selected PML is in charge of initializing and releasing them. 

The CM PML is slightly different compared with OB1 or DR. Internally it use
2 different types of requests: light and heavy. However, now with this patch
both types of requests are stored in the same queue, and cast appropriately
on the allocation macro. This means we might use less memory than we allocate,
but in exchange we got full support for most of the parallel debuggers.

Another thing with this patch, is that now for all PML (CM included) the basic
PML requests start with the same fields, and they are declared in the same order
in the request structure. Moreover, the fields have been moved in such a way
that only one volatile/atomic will exist per line of cache (hopefully).

This commit was SVN r15346.
2007-07-10 22:16:38 +00:00
Brian Barrett
8b9e8054fd Move modex from pml base to general ompi runtime, sicne it's used by more
than just the PML/BTLs these days.  Also clean up the code so that it
handles the situation where not all nodes register information for a given
node (rather than just spinning until that node sends information, like
we do today).

Includes r15234 and r15265 from the /tmp/bwb-modex branch.

This commit was SVN r15310.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r15234
  r15265
2007-07-09 17:16:34 +00:00
Tim Prins
f3ac4ac20e Fix order of function arguments
This commit was SVN r15304.
2007-07-08 16:37:51 +00:00
Rainer Keller
cff1b6a71b - PERUSE_COMM_REQ_XFER_BEGIN should be emited for first fragment
of larger message as well.

This commit was SVN r15299.
2007-07-06 15:02:36 +00:00
George Bosilca
951e4929b9 Usually it's unlikely to have additional fragments.
This commit was SVN r15253.
2007-07-01 16:19:53 +00:00
George Bosilca
c435094639 Only trigger the PERUSE_COMM_REQ_XFER_BEGIN event on the initial fragment.
This commit was SVN r15252.
2007-07-01 16:19:13 +00:00
George Bosilca
60319f99ac Make sure in case of error what we return is clean (set to NULL).
This commit was SVN r15251.
2007-07-01 16:17:43 +00:00
George Bosilca
11656e20aa Remove few warnings.
This commit was SVN r15250.
2007-07-01 16:16:05 +00:00
Gleb Natapov
77e54ebc7e Schedule RDMA op on the last BTL that got completion.
This commit was SVN r15249.
2007-07-01 11:35:55 +00:00
Gleb Natapov
54b40aef91 Schedule SEND traffic of pipeline protocol between BTLs in accordance with
relative bandwidths of each BTL. Precalculate what part of a message should
be send via each BTL in advance instead of doing it during scheduling.

This commit was SVN r15248.
2007-07-01 11:34:23 +00:00
Gleb Natapov
e74aa6b295 Schedule RDMA traffic between BTLs in accordance with relative bandwidths of
each BTL. Precalculate what part of a message should be send via each BTL in
advance instead of doing it during scheduling.

This commit was SVN r15247.
2007-07-01 11:31:26 +00:00
Gleb Natapov
1c7141df4d Remove unused struct.
This commit was SVN r15228.
2007-06-28 11:58:16 +00:00
Gleb Natapov
b88b7dedfe Rename btl_rdma_offset to btl_pipeline_send_length.
This commit was SVN r15153.
2007-06-21 07:12:40 +00:00
Josh Hursey
7fd1805e97 Fix a couple of compile warnings that Tim P brought to by attention.
This commit was SVN r15132.
2007-06-19 00:46:16 +00:00
George Bosilca
10a017d1bf For a obscure reason this have to be defined on Windows. The obscure
reason it's that we don't have the nice configure stuff, so detecting
when to enable the CR PML it's kind of hard. Keep it defined and at
least it compile smoothly.

This commit was SVN r15116.
2007-06-17 05:01:09 +00:00
Rainer Keller
ca09aae2cc - Get PERUSE compile again with latest RDMA changes in r14768/r14842.
This commit was SVN r15042.

The following SVN revision numbers were found above:
  r14768 --> open-mpi/ompi@3401bd2b07
  r14842 --> open-mpi/ompi@10266fb467
2007-06-13 12:47:47 +00:00
Brian Barrett
84d1512fba Add the potential for doing some basic error checking on mutexes during
single threaded builds.  In its default configuration, all this does
is ensure that there's at least a good chance of threads building
based on non-threaded development (since the variable names will be
checked).  There is also code to make sure that a "mutex" is never
"double locked" when using the conditional macro mutex operations.
This is off by default because there are a number of places in both
ORTE and OMPI where this alarm spews mega bytes of errors on a
simple test.  So we have some work to do on our path towards
thread support.

Also removed the macro versions of the non-conditional thread locks,
as the only places they were used, the author of the code intended
to use the conditional thread locks.  So now you have upper-case
macros for conditional thread locks and lowercase functions for
non-conditional locks.  Simple, right? :).

This commit was SVN r15011.
2007-06-12 16:25:26 +00:00
Gleb Natapov
423f404c34 Shut up compiler warning. Ugly, but I can see better way except changing
converter to use uint64_t(ssize_t?) for offset.

This commit was SVN r14950.
2007-06-07 11:33:28 +00:00
Gleb Natapov
9f9b64db4e Revert r14947 as this doesn't solve the problem.
This commit was SVN r14949.

The following SVN revision numbers were found above:
  r14947 --> open-mpi/ompi@5b9fe28e3f
2007-06-07 11:24:24 +00:00
Gleb Natapov
5b9fe28e3f Fix warning on 32bit systems.
This commit was SVN r14947.
2007-06-07 08:57:34 +00:00
Rich Graham
e276f7bcc7 undo my error.
This commit was SVN r14890.
2007-06-05 23:32:47 +00:00
Rich Graham
ce0e9ac329 initialize lock properly.
This commit was SVN r14881.
2007-06-05 20:34:11 +00:00
Shiqing Fan
c142c23f88 Initialize req_ompi.req_status._count to be 0 before starting the request.
This commit was SVN r14861.
2007-06-05 09:50:06 +00:00
Shiqing Fan
0961669912 Spaces after backslash are removed.
This commit was SVN r14844.
2007-06-04 10:10:24 +00:00
Shiqing Fan
7bf18a4fd5 MPI_SOURCE should be initialized.
This commit was SVN r14843.
2007-06-04 09:37:21 +00:00
Gleb Natapov
10266fb467 Fix deadlock in OB1 protocol by by sending memory by copying if registration
fails.

This commit was SVN r14842.
2007-06-03 08:31:58 +00:00
Gleb Natapov
a25e1e7b15 Implement new function mca_pml_ob1_send_requst_copy_in_out(req, offset, len)
that allows to send any range of a request by send/recv instaed of RDMA
and use it to send data from the end of a request in pipeline protocol. 

This commit was SVN r14841.
2007-06-03 08:30:07 +00:00
Gleb Natapov
06bf5d74e7 Remove mca_pml_ob1_send_fin_btl function.
This commit was SVN r14784.
2007-05-28 06:51:12 +00:00
Gleb Natapov
f5078db0db Fix order of parameters to function.
This commit was SVN r14783.
2007-05-27 13:45:24 +00:00
Gleb Natapov
ad69d3c6ac Fix out of resource handling for FIN packets broken by r14768.
This commit was SVN r14780.

The following SVN revision numbers were found above:
  r14768 --> open-mpi/ompi@3401bd2b07
2007-05-27 08:29:38 +00:00
Galen Shipman
3401bd2b07 Add optional ordering to the BTL interface.
This is required to tighten up the BTL semantics. Ordering is not guaranteed,
but, if the BTL returns a order tag in a descriptor (other than
MCA_BTL_NO_ORDER) then we may request another descriptor that will obey
ordering w.r.t. to the other descriptor.


This will allow sane behavior for RDMA networks, where local completion of an
RDMA operation on the active side does not imply remote completion on the
passive side. If we send a FIN message after local completion and the FIN is
not ordered w.r.t. the RDMA operation then badness may occur as the passive
side may now try to deregister the memory and the RDMA operation may still be
pending on the passive side. 

Note that this has no impact on networks that don't suffer from this
limitation as the ORDER tag can simply always be specified as
MCA_BTL_NO_ORDER.

This commit was SVN r14768.
2007-05-24 19:51:26 +00:00
Ralph Castain
4fff584a68 Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.

Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.

Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.

With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.

Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".

This commit was SVN r14711.
2007-05-21 18:31:28 +00:00
Gleb Natapov
3ebaff8dfe Implement new BTL parameters:
We eagerly send data up to btl_*_eager_limit with the match
Upon ACK of the MATCH we start using send/receives of size
btl_*_max_send_size up to the btl_*_rdma_pipeline_offset
After the btl_*_rdma_pipeline_offset we begin using RDMA writes of
size btl_*_rdma_pipeline_frag_size.

Now, on a per message basis we only use the above protocol if the
message is larger than btl_*_min_rdma_pipeline_size

btl_*_eager_limit - > same
btl_*_max_send_size -> same
btl_*_rdma_pipeline_offset -> btl_*_min_rdma_size
btl_*_rdma_pipeline_frag_size -> btl_*_max_rdma_size


btl_*_min_rdma_pipeline_size is new..

This patch also moves all BTL common parameters initialisation into
btl_base_mca.c file.

This commit was SVN r14681.
2007-05-17 07:54:27 +00:00
Sven Stork
22af6d38e6 - UNexport symbols that shouldn't be needed outside the libraries
- replace #if/#endif with BEGIN/END_C_DECLS
- reformating

This commit was SVN r14669.
2007-05-16 15:46:52 +00:00
Gleb Natapov
2562253678 Do more work at RDMA frag preparation time and less work at RDMA frag sending
time.

This commit was SVN r14627.
2007-05-09 12:11:51 +00:00
Gleb Natapov
78fda79630 Use size_t instead of uint64_t in call to convertor cloning.
This commit was SVN r14626.
2007-05-09 10:02:06 +00:00
Sven Stork
a04c8eb39a - Bring over the visibility feature, for a finer symbol export control
via the visibility feature that is provided by some compilers.

  Per default this feature is disabled, to enable it you need to
  configure with --enable-visibility and obviously you need a compiler
  with visibility support. Please refer to the wiki for more information.
  https://svn.open-mpi.org/trac/ompi/wiki/Visibility

This commit was SVN r14582.
2007-05-04 09:03:37 +00:00
Gleb Natapov
8029893489 In multithreaded application sending of initial portion of a request may overlap
with RDMAing the rest of it. Also more than one RDMA writes can be performed
simultaneously by different threads. To make this code thread safe this patch
clones original request convertor for each RDMA fragment.

This commit was SVN r14574.
2007-05-03 09:13:17 +00:00
George Bosilca
bb481273a6 Typos.
This commit was SVN r14546.
2007-04-28 19:15:53 +00:00
Rainer Keller
6f9251ed39 - Small fixes by PGI -Minform=inform
This commit was SVN r14524.
2007-04-26 08:16:07 +00:00
Josh Hursey
8c2385416f Per a developer request -
Make sure that the wrapper selection is compiled out if not enabling FT. Before the 
logic would skip over it since the conditional if statements would not be satisfied, 
now there are no additional if statements when compiled out.

With this modification the selection logic looks nearly identical to pre-r14051
with the exception of the non-FT related improvements.

This commit was SVN r14491.

The following SVN revision numbers were found above:
  r14051 --> open-mpi/ompi@dadca7da88
2007-04-24 17:08:48 +00:00
Ralph Castain
18b2dca51c Bring in the code for routing xcast stage gate messages via the local orteds. This code is inactive unless you specifically request it via an mca param oob_xcast_mode (can be set to "linear" or "direct"). Direct mode is the old standard method where we send messages directly to each MPI process. Linear mode sends the xcast message via the orteds, with the HNP sending the message to each orted directly.
There is a binomial algorithm in the code (i.e., the HNP would send to a subset of the orteds, which then relay it on according to the typical log-2 algo), but that has a bug in it so the code won't let you select it even if you tried (and the mca param doesn't show, so you'd *really* have to try).

This also involved a slight change to the oob.xcast API, so propagated that as required.

Note: this has *only* been tested on rsh, SLURM, and Bproc environments (now that it has been transferred to the OMPI trunk, I'll need to re-test it [only done rsh so far]). It should work fine on any environment that uses the ORTE daemons - anywhere else, you are on your own... :-)

Also, correct a mistake where the orte_debug_flag was declared an int, but the mca param was set as a bool. Move the storage for that flag to the orte/runtime/params.c and orte/runtime/params.h files appropriately.

This commit was SVN r14475.
2007-04-23 18:41:04 +00:00
Adrian Knoth
339dbf6cd5 Cosmetics. Enforcing style guide.
This commit was SVN r14459.
2007-04-21 21:47:25 +00:00
Josh Hursey
4159b72a60 Some minor updates to go along with commit r14457
This commit was SVN r14458.

The following SVN revision numbers were found above:
  r14457 --> open-mpi/ompi@2af38229c1
2007-04-21 21:24:44 +00:00
Josh Hursey
eef364546c Check for NULL before trying to use the variable.
This commit was SVN r14444.
2007-04-20 17:17:11 +00:00
Josh Hursey
12e5d0e817 ft_event Commit:
- Move the PML Modex stuff out of the BML -- Abstraction violation.
- Also fix the location of the add_procs with respect to the stage gates.

This commit was SVN r14422.
2007-04-19 03:05:12 +00:00
George Bosilca
51fc2474f1 Don't keep the data attached to a fragment segmented when we have
to move it into the unexpected queue. Instead pack the data in
only one buffer. Now the code look more optimized and clear, but
I have a doubt about who's using this functionality. I think that
all BTLs always return only one memory segment attached to the
matching fragment (i.e. there is no unexpected iov type receive).

This commit was SVN r14416.
2007-04-18 15:52:11 +00:00
Adrian Knoth
e3178fd39f Cosmetics. PTLs are now called BTLs.
This commit was SVN r14382.
2007-04-16 10:12:27 +00:00
Josh Hursey
8f119d9063 Closes trac:977
Fix for memory corruption in the restarted process stack. This stemed from 
the brute force method we were previously using. This commit fixes this by
using a lighter weight solution focused in the r2 BML instead of above the PML.
This is a more efficient and flexible solution, and it solves the original
problem.

In the process I pulled out the ft_event function in the tcp BTL and r2 BML
into a set of *_ft.[c|h] files just to keep any updates to these code paths
as isolated as possible to make merging easier on everyone.

This commit was SVN r14371.

The following SVN revision numbers were found above:
  r2 --> open-mpi/ompi@58fdc18855

The following Trac tickets were found above:
  Ticket 977 --> https://svn.open-mpi.org/trac/ompi/ticket/977
2007-04-14 02:06:05 +00:00
Jeff Squyres
51f286d737 Just like r14289 on the ORTE trunk:
Per discussions with Brian and Ralph, make a slight correction in
where components are installed. Use $pkglibdir, not $libdir/openmpi,
so that when compiled in the orte trunk, components are installed to
the right directory (because the component search patch is checking
$pkglibdir).

This commit was SVN r14345.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r14289
2007-04-12 11:19:42 +00:00
Galen Shipman
d7e428909e two fixes, one mine, the other gleb's, I'm committing for gleb due to
time difference...  

1) The PML makes an assumption on local/remote completion semantics of the BTL
which Self BTL does not obey, nor should it, so we fix the PML
2) The Get protocol must handle the case when sender and reciever do not agree
on wheter the data is contiguous 

This commit was SVN r14313.
2007-04-11 22:03:06 +00:00
Josh Hursey
fbc59f668c fix typo
This commit was SVN r14301.
2007-04-11 15:39:42 +00:00
Josh Hursey
5efae25390 No functionality changes (yet).
Just fix the indentation to meet the coding standard.

This commit was SVN r14300.
2007-04-11 15:19:51 +00:00
Josh Hursey
38547459ae Improve the cleanup process in ob1
Remove a redundant statement in the r2 BML.

This commit was SVN r14228.

The following SVN revision numbers were found above:
  r2 --> open-mpi/ompi@58fdc18855
2007-04-05 17:37:29 +00:00
Josh Hursey
98fb9f26ef Some cleanup.
- Remove an old comment from crcp_base_fns.c
- Let ob1 have its very own ft_event function (which I'll fill in shortly)
- Make sure ob1 finalizes the bsend stuff so we don't leave a bunch of memory sitting around
- PML base - destruct the array upon finalize. Shrink the include search so it stops after finding a match

This commit was SVN r14222.
2007-04-05 13:52:05 +00:00
Josh Hursey
51daa15f9c play a bit nicer with references.
This commit was SVN r14201.
2007-04-02 22:27:52 +00:00
George Bosilca
f2a6b9394f Deal with the include spree. Protect "environ" on Windows.
Some others minors modifications in order to make it
compile [again] on Windows.

This commit was SVN r14188.
2007-04-01 16:16:54 +00:00
George Bosilca
1cb26e3b9c Finally the convertor export a convenience function to allow a consistent
computation of the current location on the pack/unpack process. This can
be used both for retrieving the pointer to the first byte (in the special
case of the cached RDMA protocol) and for getting the current
position (for the pipelined protocol).

I modified all BTLs, but most of them are still untested.

This commit was SVN r14180.
2007-03-30 22:02:45 +00:00
Galen Shipman
a78672be2b fix mpi_leave_pinned case for arbitrary datatypes
George will be streamlining this with a new convertor function soon... 

This commit was SVN r14174.
2007-03-30 02:06:08 +00:00
Galen Shipman
ace68b1883 Change the way we handle unexpected messages,
if less than or equal  pml_ob1_unexpected_limit just buffer in the PML level recv
fragment else allocate a buffer via the bucket allocator 

This commit was SVN r14117.
2007-03-22 01:00:34 +00:00
Josh Hursey
299332ecac fix small compiler warning
This commit was SVN r14097.
2007-03-21 04:44:54 +00:00
Josh Hursey
6d29146748 fix dumb logic break in the PML selection finalization
This commit was SVN r14053.
2007-03-17 16:33:43 +00:00
Josh Hursey
dadca7da88 Merging in the jjhursey-ft-cr-stable branch (r13912 : HEAD).
This merge adds Checkpoint/Restart support to Open MPI. The initial
frameworks and components support a LAM/MPI-like implementation.

This commit follows the risk assessment presented to the Open MPI core
development group on Feb. 22, 2007.

This commit closes trac:158

More details to follow.

This commit was SVN r14051.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r13912

The following Trac tickets were found above:
  Ticket 158 --> https://svn.open-mpi.org/trac/ompi/ticket/158
2007-03-16 23:11:45 +00:00
Sven Stork
870740efe2 - proper export symbols that are required by other components.
This commit was SVN r13841.
2007-02-28 12:51:55 +00:00
Josh Hursey
c573171b7d Mostly a cleanup commit.
- Implement the BML/r2 finialize funciton
- Cleanup the btl close routine
- Wire up a pml_base_verbose MCA parameter so you can actually watch the PML selection logic if you really want to.
- Fix a potental segfault in the selection logic.
  ompi_pointer_array_get_item() may return NULL, so we have to check for it

This commit was SVN r13734.

The following SVN revision numbers were found above:
  r2 --> open-mpi/ompi@58fdc18855
2007-02-21 16:18:43 +00:00
Pavel Shamis
2483cefc57 Additional check if descriptor is NULL. It prevents
mca_pml_dr_sendreq_cleanup_active failure on segfault.

This commit was SVN r13647.
2007-02-14 10:43:43 +00:00
Brian Barrett
c00d841741 Fix hang on Cray machine introduced with r13582. The modex will never fire
when on the Cray machine (aka when the NULL GPR is in use).

This commit was SVN r13638.

The following SVN revision numbers were found above:
  r13582 --> open-mpi/ompi@041beeb1b6
2007-02-13 18:34:03 +00:00
George Bosilca
2e042c91cf Once we compute the local offset use it (instead of the global one).
This commit was SVN r13634.
2007-02-13 09:34:04 +00:00
George Bosilca
22eca30b45 One less compiler warning.
This commit was SVN r13633.
2007-02-13 09:32:57 +00:00
Gleb Natapov
1033002595 Fix memory leak. Free allocated descriptor if operation cannot proceed.
This commit was SVN r13610.
2007-02-12 09:47:51 +00:00
Brian Barrett
041beeb1b6 Share currently selected PML in the modex information, then check whenever
adding new procs that the remote proc's pml is the same as our local pml.
Turns the hangs from mismatched PMLs into an abort, which is better,
I think.

This commit was SVN r13582.
2007-02-09 16:38:16 +00:00
Galen Shipman
f98a442c82 Fix a problem in the selection logic for MX. Basically we need to be able to
open MTL MX and BTL MX and initialize them at the same time. The problem is
that both call mx_init and mx_finalize, solution is to add an external entity
that does the init and finalize (based on ref counting).

This commit was SVN r13576.
2007-02-09 03:19:38 +00:00
Josh Hursey
90f449f675 fix a typo that got in there
This commit was SVN r13523.
2007-02-06 20:56:48 +00:00
Galen Shipman
ec610a9e65 spread priorities out a bit..
This commit was SVN r13487.
2007-02-04 00:55:25 +00:00
Galen Shipman
ddf08cb0b3 woops..
This commit was SVN r13482.
2007-02-03 02:32:00 +00:00
Galen Shipman
a94101fa62 mostly another hack around for PML selection, allows CM be select itself if an
MTL is available, if not OB1 is used. Still prevents DR and OB1 from stomping
on each other though. 

This commit was SVN r13481.
2007-02-03 02:01:18 +00:00
George Bosilca
0ff2115964 Other warnings are now silenced.
This commit was SVN r13462.
2007-02-02 06:47:35 +00:00
George Bosilca
79ea6d471b Even less warnings.
This commit was SVN r13429.
2007-02-01 19:27:11 +00:00
Brian Barrett
a0b40ce45a Fix race condition in setting MPI_ERROR -- with buffered sends, the
request can complete before the operation, meaning that a bogus MPI_ERROR
is read

This commit was SVN r13401.
2007-01-31 21:40:14 +00:00
Rainer Keller
061ba05439 - Fixes uncovered with the format attribute to
opal_output and opal_output_verbose

This commit was SVN r13371.
2007-01-30 20:56:31 +00:00
Rainer Keller
3669e8921e - Fix further compiler warnings regarding initialization
and shadowing variables.

This commit was SVN r13358.
2007-01-30 06:34:38 +00:00
Rainer Keller
ca35881cd0 - Minor bugfixes and removed compiler warnings
This commit was SVN r13343.
2007-01-28 19:52:09 +00:00
George Bosilca
790f175d4e Explicit conversions to make the code Windows friendly.
This commit was SVN r13266.
2007-01-24 00:50:24 +00:00
Rainer Keller
96030de97b - Initialize the size of the opal_object class.
- Use the OBJ_CLASS_INSTANCE macro to initialize classes.
   This also gets rid of several missing initialization errors.

This commit was SVN r13227.
2007-01-21 14:24:29 +00:00
Jeff Squyres
52ca6cf86c The mpi_leave_pinned and mpi_leave_pinned_pipeline MCA parameters were
needlessly registered in multiple different places, and none of them
had a good help string.  There was also an inconsistent check for
setting both mpi_leave_pinned and mpi_leave_pinned_pipeline (i.e., it
was only in ob1).  This commit moves the registration of these params
to one central place (ompi/runtime/ompi_mpi_params.c, with all other
mpi_* MCA params) and uses globals to propagate the values as
relevant.  The error check was also moved to the central location to
ensure that we can consistency everywhere.

This commit was SVN r13226.
2007-01-21 14:02:06 +00:00
Rolf vandeVaart
6a260e4a9a Fix two problems. For MPI_Buffer_detach, do not attempt to
return the buffer address from Fortran. It is not expected
behavior.  For MPI_Buffer_attach, adjust the address of
the buffer handed in so it is always aligned.  

Refs trac:750
Buffer detach reviewed by Jeff Squyres
Buffer attach alignment reviewed by George Bosilca

This commit was SVN r13205.

The following Trac tickets were found above:
  Ticket 750 --> https://svn.open-mpi.org/trac/ompi/ticket/750
2007-01-18 23:32:39 +00:00
Ralph Castain
4ef4cbb5ad Fix a compiler warning about comparing signed/unsigned values
This commit was SVN r13190.
2007-01-18 17:14:06 +00:00
Gleb Natapov
4c7dbd36c7 Balance RDMA operation in round robin fashion between all available RDMA BTLs.
OB1 always use first element from array of BTLs available for RDMA. The patch
change the array creation algorithm, it puts different BTL in the first element
in round robin fashion.

This commit was SVN r13174.
2007-01-18 09:15:18 +00:00
Jeff Squyres
52e8089600 Fix compiler warning.
This commit was SVN r13148.
2007-01-17 14:23:46 +00:00
George Bosilca
87ff2b5ce8 Cast to the correct type.
This commit was SVN r13046.
2007-01-08 22:04:01 +00:00
George Bosilca
53ddbe8446 Nothing relevant.
This commit was SVN r13044.
2007-01-08 22:02:17 +00:00
Brian Barrett
a34e67d743 Remove unneeded PARAM_INIT_FILE variable in configure.params files used by
components that use configure.m4 for configuration or are always built. 
The macro has not been needed since moving to configure types other than
configure.stub

Fixes trac:590

This commit was SVN r13031.

The following Trac tickets were found above:
  Ticket 590 --> https://svn.open-mpi.org/trac/ompi/ticket/590
2007-01-08 03:44:22 +00:00
Brian Barrett
8900d3ae43 Second take at fixing the issues with using ompi_ptr_t. Add helper functions for converting from .pval to .lval and vice-versa. Users of ompi_ptr_t types should only use one of the fields in the union unless using the helper conversion functions. For the BTLs, local pointers will always be stored in the .pval field and remote pointers always stored in the .lval field.
George wrote the initial patch, I extended it slightly and am responsible for all bugs found.

Refs trac:587

This commit was SVN r13023.

The following Trac tickets were found above:
  Ticket 587 --> https://svn.open-mpi.org/trac/ompi/ticket/587
2007-01-07 01:48:57 +00:00
Brian Barrett
48ec0b2071 Revert out r12974, 12976, and 12991 as George has provided a less intrusive fix
for now...

This commit was SVN r12997.

The following SVN revision numbers were found above:
  r12974 --> open-mpi/ompi@27cea44a9c
2007-01-04 22:07:37 +00:00
Galen Shipman
931a389c4f fix deadlock on rendezvous protocol..
This commit was SVN r12982.
2007-01-04 03:46:11 +00:00
Brian Barrett
27cea44a9c Fix a number of issues with the ompi_ptr_t:
* Make sure that the pval always writes to the correct portion of the
    lval.  This only matters on 32 bit big endian machines.
  * On 32 bit machines when assigning to pval, the other 4 bytes of lval
    weren't being written, which could lead to bogus data

We use macros so that there aren't casts all over the code and the pval
assignment can occur to the correct 4 bytes.  Refs trac:587

This commit was SVN r12974.

The following Trac tickets were found above:
  Ticket 587 --> https://svn.open-mpi.org/trac/ompi/ticket/587
2007-01-03 19:47:48 +00:00
Gleb Natapov
a6127fd8ce Increase req_bytes_delivered atomically.
This commit was SVN r12971.
2007-01-03 15:19:34 +00:00
Gleb Natapov
79202561f6 Don't check req_pipeline_depth on frag completion. Checking of
req_bytes_delivered should be enough.

This commit was SVN r12967.
2007-01-03 14:44:20 +00:00
Gleb Natapov
1ad6c41735 Sender can start scheduling send fragments immediately after receiving ACK. No
need to wait for RNDV completion.

This commit was SVN r12965.
2007-01-03 12:37:11 +00:00
Brian Barrett
99c0a29602 Disable CM and DR PMLs in heterogeneous situtations as neither are
heterogeneous safe.

Refs trac:587

This commit was SVN r12942.

The following Trac tickets were found above:
  Ticket 587 --> https://svn.open-mpi.org/trac/ompi/ticket/587
2006-12-30 16:17:56 +00:00
George Bosilca
0b5d879a63 ompi_convertor_pack do not return errors (all checkings are done when the
convertor is created).

This commit was SVN r12940.
2006-12-29 07:40:02 +00:00
George Bosilca
d8db9e49f3 Set the bml_btl to NULL or segfault !!!
This commit was SVN r12939.
2006-12-29 07:38:24 +00:00
Brian Barrett
2ab65eb521 Remove some debugging output that was #if 0'ed out but shouldn't have been
committed into the trunk anyway

This commit was SVN r12897.
2006-12-19 02:34:41 +00:00
Gleb Natapov
190e7a27cd Merge with gleb-mpool branch. All RDMA components use same mpool now (rdma).
udapl/openib/vapi/gm mpools a deprecated. rdma mpool has parameter that allows
to limit its size mpool_rdma_rcache_size_limit (default is 0 - unlimited).

This commit was SVN r12878.
2006-12-17 12:26:41 +00:00
Brian Barrett
01e8fc5f91 Redo of r12871, without the preconnect code change:
Move the req_mtl structure back to the end of each of the structures in 
the CM PML. The req_mtl structure is cast into a mtl_*_request_structure 
for each MTL, which is larger than the req_mtl itself. The cast will cause
the *_request to overwrite parts of the heavy requests if the req_mtl
isn't the *LAST* thing on each structure (hence the comment). This was 
moved as an optimization at some point, which caused buffer sends to fail...

Refs trac:669

This commit was SVN r12873.

The following SVN revision numbers were found above:
  r12871 --> open-mpi/ompi@597598b712

The following Trac tickets were found above:
  Ticket 669 --> https://svn.open-mpi.org/trac/ompi/ticket/669
2006-12-15 17:54:14 +00:00
Brian Barrett
bdf0b231b2 Undo r12871, as it contained some code in ompi/runtime that shouldn't have been
committed

Refs trac:669

This commit was SVN r12872.

The following SVN revision numbers were found above:
  r12871 --> open-mpi/ompi@597598b712

The following Trac tickets were found above:
  Ticket 669 --> https://svn.open-mpi.org/trac/ompi/ticket/669
2006-12-15 17:52:13 +00:00
Brian Barrett
597598b712 Move the req_mtl structure back to the end of each of the structures in the
CM PML.  The req_mtl structure is cast into a mtl_*_request_structure for
each MTL, which is larger than the req_mtl itself.  The cast will cause
the *_request to overwrite parts of the heavy requests if the req_mtl
isn't the *LAST* thing on each structure (hence the comment).  This was
moved as an optimization at some point, which caused buffer sends to
fail...

Refs trac:669

This commit was SVN r12871.

The following Trac tickets were found above:
  Ticket 669 --> https://svn.open-mpi.org/trac/ompi/ticket/669
2006-12-15 17:46:53 +00:00
Brian Barrett
10af8ab454 Corrections for when threading is enabled.
Refs trac:564

This commit was SVN r12830.

The following Trac tickets were found above:
  Ticket 564 --> https://svn.open-mpi.org/trac/ompi/ticket/564
2006-12-12 18:48:42 +00:00
Brian Barrett
cf196ce420 Instead of an unknown proc list that requires ownership transfer of data (which, in turn, requires a complex series of locks to be held during the transfer), use a modex backing store with backpointers from the proc to the backing store. The proc structures no longer own the modex data, which greatly simplifies locking when an unknown proc suddenly becomes known.
Refs trac:564

This commit was SVN r12822.

The following Trac tickets were found above:
  Ticket 564 --> https://svn.open-mpi.org/trac/ompi/ticket/564
2006-12-11 21:27:30 +00:00
Ralph Castain
0a5d41857a Complete next round of message size reduction: "strip" the descriptive info from the returned values. I have now added a flag to the gpr address mode (ORTE_GPR_STRIPPED) that instructs the gpr to not include segment names or tokens in the returned gpr_value_t objects.
I found only two places that were looking at the tokens:

1. the odls - we used the tokens to separately process the globals container data from everything else. In this case, I left the subscription that returned the globals data alone, but "stripped" the subscription that returned the launch data for the procs. These subscriptions have nothing to do with the xcast message.

2. the pml_base_modex - the callback function was getting process names from the returned tokens. Actually, this function was doing a very bad thing - it was assuming that the first token returned was *always* the process name. This is currently true, but is one of those assumptions that someone could have easily changed - and suddenly found the system inexplicably failing. I modified the function to (a) get the name sent back to us, (b) "stripped" the value structures of tokens and segment strings, and (c) correctly obtained process names from the returned values. I also reindented the heck out of the code so it was legible (at least, to my old eyes).

This commit was SVN r12813.
2006-12-09 23:10:25 +00:00
Brian Barrett
98884e45e4 Clean up the way procs are added to the global process list after MPI_INIT:
* Do not add new procs to the global list during modex callback or
    when sharing orte names during accept/connect.  For modex, we
    cache the modex info for later, in case that proc ever does get
    added to the global proc list.  For accept/connect orte name
    exchange between the roots, we only need the orte name, so no
    need to add a proc structure anyway.  The procs will be added
    to the global process list during the proc exchange later in 
    the wireup process
  * Rename proc_get_namebuf and proc_get_proclist to proc_pack
    and proc_unpack and extend them to include all information
    needed to build that proc struct on a remote node (which
    includes ORTE name, architecture, and hostname).  Change
    unpack to call pml_add_procs for the entire list of new
    procs at once, rather than one at a time.
  * Remove ompi_proc_find_and_add from the public proc
    interface and make it a private function.  This function
    would add a half-created proc to the global proc list, so
    making it harder to call is a good thing.

This means that there's only two ways to add new procs into the global proc list at this time: During MPI_INIT via the call to ompi_proc_init, where my job is added to the list and via ompi_proc_unpack using a buffer from a packed proc list sent to us by someone else.  Currently, this is enough to implement MPI semantics.  We can extend the interface more if we like, but that may require HNP communication to get the remote proc information and I wanted to avoid that if at all possible.

Refs trac:564

This commit was SVN r12798.

The following Trac tickets were found above:
  Ticket 564 --> https://svn.open-mpi.org/trac/ompi/ticket/564
2006-12-07 19:56:54 +00:00
Brian Barrett
41a70a8f01 indent, this time with the right coding standards...
This commit was SVN r12787.
2006-12-07 00:24:01 +00:00
Brian Barrett
f9ec8d6f2a reindent file to make it easier to deal with...
This commit was SVN r12786.
2006-12-07 00:21:25 +00:00
Brian Barrett
6f8b366acb Rename liborte to libopen-rte and libopal to libopen-pal per telecon today
and bug #632.

Refs trac:632

This commit was SVN r12762.

The following Trac tickets were found above:
  Ticket 632 --> https://svn.open-mpi.org/trac/ompi/ticket/632
2006-12-05 18:27:24 +00:00
Brian Barrett
441432950f Merge in changes from the bwb-heterogeneous temp branch (r12491 -
r12714) for supporting compilers / architectures with different
padding rules.

This commit was SVN r12749.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r12491
  r12714
2006-12-04 20:11:42 +00:00
Rainer Keller
6f8f28f40f - Get rid of inline definition, otherwise static-compilation fails.
This commit was SVN r12735.
2006-12-03 14:52:17 +00:00
Gleb Natapov
30ca7457b4 Some BTLs (e.g TCP) can report put/get completion before data actually
hits the buffer on the other side. For this kind of BTLs we need to send
FIN through the same BTL, PUT was performed with so network will handle
ordering for us. If we will use another BTL, receiver can get FIN before
data will hit the buffer and complete request prematurely. We mark such
problematic BTLs with MCA_BTL_FLAGS_FAKE_RDMA flag (this kind of RDMA
is really fake, because the real one guaranties that sender will see the
completion only after receiver's NIC confirmed that all the data was
received).

This commit was SVN r12732.
2006-12-03 10:12:09 +00:00
Gleb Natapov
39c930b160 The bug fixing part of r12720 introduce much more serious bug that it fixes.
It calls mca_pml_ob1_send_fin_btl() which may fail and doesn't check return
code. This breaks all RDMA transports event when only one BTL is used. Revert
it for now, I am working on a real fix for the problem (I hope).

This commit was SVN r12731.

The following SVN revision numbers were found above:
  r12720 --> open-mpi/ompi@3e3689320b
2006-12-03 08:55:59 +00:00
Gleb Natapov
65d7ad4581 The "bug fix" from the r12721 reverts part of the r12433 that fixed
regresion from v1.1 was reviewed and put to v1.2 branch. So revert this part
of r12721 back.

This commit was SVN r12730.

The following SVN revision numbers were found above:
  r12433 --> open-mpi/ompi@82f7c0dd69
  r12721 --> open-mpi/ompi@3edd850d2e
2006-12-03 08:29:55 +00:00
George Bosilca
3edd850d2e Some indentation and code arrangement. However, there is a bug fix. Force the PUT
protocol to always obey to the btl_max_rdma_size.

This commit was SVN r12721.
2006-12-01 22:26:14 +00:00
George Bosilca
3e3689320b Some indentations and one BIG fix. Avoid race conditions on the PUT RDMA
protocol when multiple NICS are available between 2 peers. The fix force
the FIN message to take exactly the same path as the fragment it describe
(i.e. same path means same BTL). Otherwise, the FIN can be received by
the peer before the RDMA complete and the request will get freed
too early.

This commit was SVN r12720.
2006-12-01 21:52:07 +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
Andrew Friedley
a4bdcb4faa Fix a segfault that turned up in more MPI_THREAD_MULTIPLE testing.
Same sort of problem and fix as described in r12323 - mca_pml_ob1_recv_frag_progress() was segfaulting due to a NULL req_proc pointer.  The path leading to this was through the mca_pml_ob1_check_cantmatch_for_match() function, where we can match a frag using the same macros as mca_pml_ob1_frag_match() and never initialize the req_proc pointer.

This commit was SVN r12582.

The following SVN revision numbers were found above:
  r12323 --> open-mpi/ompi@c752502dee
2006-11-13 20:12:51 +00:00
George Bosilca
a38cd366d7 Construct the convertor. It's not really required, but it's not in the
critical path anyway. At least in debug mode we get nice informations about
where the convertor was created.

This commit was SVN r12549.
2006-11-10 20:55:06 +00:00
George Bosilca
858ab24e8e The req_mtl field has to be the last in the struct or bad things happen.
This commit was SVN r12548.
2006-11-10 20:53:41 +00:00
George Bosilca
17405cd9c6 A temporary fix, until we figure out a better approach. The problem
is that if one add "pml=" to the configuration file, really bad things
happen. All PMLs will get initialize, and each of them will initialize
all BTLs. This patch force the mca_pml_base_pml to get initialized in
all cases before we go out of the mca_pml_base_open function.

This commit was SVN r12527.
2006-11-10 04:53:00 +00:00
George Bosilca
eab1776e9a Explicit casts for our friendly Windows environment...
This commit was SVN r12496.
2006-11-08 17:02:46 +00:00
George Bosilca
915d748d72 Initialize the convertor on _START not on _INIT. This allow us to
set it up before the match when we know the peer, saving some
time on the critical path. If the receive is ANY_SOURCE then
we initialize the convertor on _MATCHED. Anyway, we will set it
up only once per receive.

This commit was SVN r12484.
2006-11-08 05:42:29 +00:00
George Bosilca
eb45a5e402 Move things around a little bit. Mainly fields from the send and receive
request in the base request. Rearrange the fields to keep the data
together. Remove some useless tests.

This commit was SVN r12482.
2006-11-08 04:58:23 +00:00
Galen Shipman
55db17b37c don't try to use a dead btl..
This commit was SVN r12456.
2006-11-06 23:25:24 +00:00
Galen Shipman
eef37430a7 failing already failed for ACK timeout..
This commit was SVN r12452.
2006-11-06 22:09:39 +00:00
Galen Shipman
813e7faea8 more fixes for failover.. and yet still more to come..
This commit was SVN r12450.
2006-11-06 21:27:17 +00:00
Gleb Natapov
82f7c0dd69 Fix regression from v1.1.
1) make the code do what comment says
2) if memory is prepinned don't send multiple PUT messages.

This commit was SVN r12433.
2006-11-06 12:00:17 +00:00
Galen Shipman
f7c554df65 Try to failover when we get an async error from the lower layer (BTL)..
This commit was SVN r12420.
2006-11-03 15:40:26 +00:00
Gleb Natapov
7b39039cd6 Add comments to process_pending functions.
This commit was SVN r12346.
2006-10-29 09:12:24 +00:00
Gleb Natapov
8ef5b6a589 Change tabs to spaces to be consistent with the rest of the file.
This commit was SVN r12345.
2006-10-29 08:12:44 +00:00
George Bosilca
a9c6ae8f15 Minimize the number of branches, and orce the correct prediction for the
most usual one. Most of the time we expect the functions which allocate
requests to succeed.

This commit was SVN r12344.
2006-10-27 23:16:13 +00:00
George Bosilca
44f3dd81b4 Update the comment to reflect what's inside the code.
This commit was SVN r12343.
2006-10-27 23:09:37 +00:00
George Bosilca
3472d19d4d Do not modify the convertor if there is no data to be send across the network. The
req_bytes_packed field is initialized in the BASE_INIT macro, so it is set for
all requests at this stage.

This commit was SVN r12342.
2006-10-27 23:03:15 +00:00
Jeff Squyres
020efdf1f9 Refs trac:250
This commit essentially caches the invoking comm/win/file on the
ompi_request_t. This, paired with the req_type field, allows us to
retrieve the invoking MPI object and invoke the proper errhandler.

The patch is missing most updates for the MPI-2 one-sided stuff (i.e.,
the patch mainly fixes comms and files); I didn't really understand
that code and didn't want to hazard trying to figure it out when Brian
can probably do it much more quickly.

So #250 will still stay open, pending MPI-2 one-sided updates for this
stuff.

This commit was SVN r12339.

The following Trac tickets were found above:
  Ticket 250 --> https://svn.open-mpi.org/trac/ompi/ticket/250
2006-10-27 12:35:27 +00:00
Jeff Squyres
e02114dcf3 Fixes trac:529.
* Create a new request type: NOOP (described below)
 * For all MPI_*_INIT functions, OBJ_NEW an ompi_request_t and set its
   type to NOOP
 * Ensure that the NOOP requests are OBJ_RELEASE'd when they are done
 * MPI_START looks at the request type; if NOOP, just return success. If
   not, call the PML start() function
 * MPI_STARTALL always pass the entire array of requests back to the PML
   (see next point)
 * Make the PMLs only process PML requests (i.e., ignore/skip anything
   that isn't of type PML -- such as the NOOP requests)
 * Add a little more param error checking in STARTALL

This commit was SVN r12338.

The following Trac tickets were found above:
  Ticket 529 --> https://svn.open-mpi.org/trac/ompi/ticket/529
2006-10-27 12:32:36 +00:00