* add "register" function to mca_base_component_t
* converted coll:basic and paffinity:linux and paffinity:solaris to
use this function
* we'll convert the rest over time (I'll file a ticket once all
this is committed)
* add 32 bytes of "reserved" space to the end of mca_base_component_t
and mca_base_component_data_2_0_0_t to make future upgrades
[slightly] easier
* new mca_base_component_t size: 196 bytes
* new mca_base_component_data_2_0_0_t size: 36 bytes
* MCA base version bumped to v2.0
* '''We now refuse to load components that are not MCA v2.0.x'''
* all MCA frameworks versions bumped to v2.0
* be a little more explicit about version numbers in the MCA base
* add big comment in mca.h about versioning philosophy
This commit was SVN r19073.
The following Trac tickets were found above:
Ticket 1392 --> https://svn.open-mpi.org/trac/ompi/ticket/1392
Kinda found by MTT. MTT calls 'ompi_info --all --parsable' and it was livelocked and had to be killed by hand.
I'm going to push this one to Jeff to push to v1.3 since he did the original implementation and should check this code.
This commit was SVN r19014.
Modify the odls to remove a (size_t) typecast in front of the num_processors variable just in case it is returned negative. This usually is accompanied by an opal_error, so this shouldn't make any difference - but it is more technically correct.
This commit was SVN r19008.
* Fix linux paffinity component to make a "best" guess when PLPA
can't find topology information in the Linux kernel. That is, if
PLPA can't tell us the max_processor_id, just assume that it's the
same as the number of processors. If you have a more complex
system than that (e.g., you have holes in your available processor
IDs), you'll likely be running a Linux kernel that supports the
topology information, and this problem won't happen.
* Make sure to conver the return codes from PLPA to OPAL_ERR* codes.
This commit was SVN r19001.
The following Trac tickets were found above:
Ticket 1250 --> https://svn.open-mpi.org/trac/ompi/ticket/1250
For now, hide the OSX component with .ompi_ignore so only I can see it until I can ensure that it doesn't inadvertently interfere with Linux and Solaris support.
This clears the conflict with Windows.
This commit was SVN r18989.
- Revert the $2, which was correct.
- It fixes the problem, that memchecker valgrind component could be
compiled and is required, but it is unable to be selected.
This commit was SVN r18906.
The following SVN revision numbers were found above:
r18899 --> open-mpi/ompi@0b1b96b598
Short version: remove opal_paffinity_alone and restore
mpi_paffinity_alone. ORTE makes various information available for the
MPI layer to decide what it wants to do in terms of processor
affinity.
Details:
* remove opal_paffinity_alone MCA param; restore mpi_paffinity_alone
MCA param
* move opal_paffinity_slot_list param registration to paffinity base
* ompi_mpi_init() calls opal_paffinity_base_slot_list_set(); if that
succeeds use that. If no slot list was set, see if
mpi_paffinity_alone was set. If so, bind this process to its Node
Local Rank (NLR). The NLR is the ORTE-maintained slot ID; if you
COMM_SPAWN to a host in this ORTE universe that already has procs
on it, the NLR for the new job will start at N (not 0). So this is
slightly better than mpi_paffinity_alone in the v1.2 series.
* If a slot list is specified *and* mpi_paffinity_alone is set, we
display an error and abort.
* Remove calls from rmaps/rank_file component to register and lookup
opal_paffinity mca params.
* Remove code in orte/odls that set affinities - instead, have them
just pass a slot_list if it exists.
* Cleanup the orte/odls code that determined
oversubscribed/want_processor as these were just opposites of each
other.
This commit was SVN r18874.
The following Trac tickets were found above:
Ticket 1383 --> https://svn.open-mpi.org/trac/ompi/ticket/1383
meat of it was commented out long ago, anyway (because of the way it
was written, it violates OPAL<->OMPI abstraction barriers); we never
ended up using the MPI keyval MCA parameter stuff. So just delete it.
This commit was SVN r18860.
Lenny and I went back and forth on whether we should simply register
another "mpi_paffinity_alone" MCA param and then try to figure out
which one was set in ompi_mpi_init, but there was difficulty in
figuring out what to do. So it seemed like the Right Thing to do was
to implement what was committed in r18770; then we could tell where
MCA parameters were set from and you could do Better Things (this is
also useful in the openib BTL, where parameters can be set either via
MCA parameter or via an INI file).
But after that was done, it seemed only a few steps further to
actually implement two new features in the MCA params area:
* Synonyms (where one MCA param name is a synonym for another)
* Allow MCA params and/or their synonyms to be marked as "deprecated"
(printing out warnings if they are used)
These features have actually long been discussed/desired, and I had
some time in airports and airplanes recently where I could work in
this stuff on a standalone laptop. So I did it. :-)
This commit introduces these two new features, and then uses them to
register mpi_paffinity_alone as a non-deprecated synonym for
opal_paffinity_alone. A few other random points in this commit:
* Add a few error checks for conditions that were not checked before
* Correct some comments in mca_base_params.h
* Add a few comments in strategic places
* ompi_info now prints additional information:
* for any MCA parameter that has synonyms, it lists all the
synonyms
* synonyms are also output as 1st-class MCA params, but with an
additional attribute indicating that they have a "parent"
* all MCA param name (both "real" or "synonym") will output an
attribute indicating whether it is deprecated or not. A synonym
is deprecated if it iself is marked as deprecated (via the
mca_base_param_regist_syn() or mca_base_param_register_syn_name()
functions) or if its "parent" MCA parameter is deprecated
This commit was SVN r18859.
The following SVN revision numbers were found above:
r18770 --> open-mpi/ompi@8efe67e08c
The following Trac tickets were found above:
Ticket 1383 --> https://svn.open-mpi.org/trac/ompi/ticket/1383
I promoted the ''none'' component to a full component, and updated the other components to reflect this code movement. The ''none'' component is the default component unless the user requests '''-am ft-enable-cr''' to auto-select a component. There is an MCA parameter to show a warning if the application requested an FT enabled job, but the ''none'' component was selected ({{{crs_none_select_warning}}}).
This temporarily fixes the problem mentioned in r18739. The full fix will entail working on ticket #1291.
Thanks to Ethan from Sun for finding this bug.
This commit was SVN r18840.
The following SVN revision numbers were found above:
r18739 --> open-mpi/ompi@a003fa7a50
an MCA parameter's value came from. Note that the actual value of the
parameter is irrelevant. For example, if a value was specified in an
MCA parameter file that happened to have the same defaultvalue that
was specified when the parameter was registered, the returned location
will indicate that the value was set from the file.
Possible answers:
* '''MCA_BASE_PARAM_SOURCE_DEFAULT:''' no user-specified values were
found, so the default value was used
* '''MCA_BASE_PARAM_SOURCE_ENV:''' the value came from the
environment (which also means the mpirun/orterun command line!)
* '''MCA_BASE_PARAM_SOURCE_FILE:''' the value came a file (or the
Windows registry)
* '''MCA_BASE_PARAM_SOURCE_KEYVAL:''' the value came from a keyval
(can currently never happen)
* '''MCA_BASE_PARAM_SOURCE_OVERRIDE:''' the value came from an MCA
param API "set" function
This commit was SVN r18770.
bother to check to see whether they exist or not. Specifically, this
will not cause an error:
{{{
shell$ mpirun --mca btl ^does_not_exist ...
}}}
but neither will this:
{{{
shell$ mpirun --mca btl ^sm ...
}}}
(where the sm BTL ''does'' exist)
This commit was SVN r18760.
The following Trac tickets were found above:
Ticket 1365 --> https://svn.open-mpi.org/trac/ompi/ticket/1365
Make sure that if we ask for the 'none' component (which is not a 'real' component, but a component in crs/base) then we do not fail out of the box when using tools. We check for the {{{OPAL_ERR_NOT_FOUND}}} error.
Also make sure that component_open() returns {{{OPAL_ERR_NOT_FOUND}}} when it cannot find a value instead of {{{OPAL_ERROR}}} which means something quite a bit different.
C/R is working but the tools still print the warning below everytime they are ran:
{{{
--------------------------------------------------------------------------
A requested component was not found, or was unable to be opened. This
means that this component is either not installed or is unable to be
used on your system (e.g., sometimes this means that shared libraries
that the component requires are unable to be found/loaded). Note that
Open MPI stopped checking at the first component that it did not find.
Host: odin.cs.indiana.edu
Framework: crs
Component: none
--------------------------------------------------------------------------
}}}
I'll have to figure out a work around for this warning (maybe work on the {{{MCA_NULL}}} Ticket #1291).
This commit was SVN r18739.
The following SVN revision numbers were found above:
r18707 --> open-mpi/ompi@bdaaf01d8a
but not anything in libc. Which causes an incorrect answer for
AC_CHECK_FUNCS. Work around that by also checking for the
#define.
This commit was SVN r18730.
components. If they are not found / able to be opened, a warning will
be printed and the mca_base_component_find() will return
OPAL_ERR_NOT_FOUND. It is the upper-layer's responsibility to handle
this error appropriately.
This commit was SVN r18707.
The following Trac tickets were found above:
Ticket 1338 --> https://svn.open-mpi.org/trac/ompi/ticket/1338
Some minor changes to help facilitate debugger support so that both mpirun and yod can operate with it. Still to be completed.
This commit was SVN r18664.
don't have MPOL_MF_MOVE). I know that this is a configure change in
the middle of the US workday, but this compile problem is preventing
work on several kinds of systems (e.g., RHEL4).
This commit was SVN r18659.
is still to use the C based wrapper compilers (which have many more features
and are more well tested). The Perl compilers are enabled with the option
--enable-script-wrapper-compilers, which also ignores the option
--disable-binaries (ie --enable-script-wrapper-compilers --disable-binaries
will result in perl-based wrapper compilers being installed, but no other
binaries being installed).
This commit was SVN r18655.
a standalone library named libopenmpi-malloc. Users wanting to
use leave_pinned with ptmalloc2 will now need to link the library
into their application explicitly. All other users will use the
libc-provided allocator instead of Open MPI's ptmalloc2. This change
may be overriden with the configure option enable-ptmalloc2-internal
- The leave_pinned options will now default to using mallopt on
Linux in the cases where ptmalloc2 was not linked in. mallopt
will also only be available if munmap can be intercepted (the
default whenever Open MPI is not compiled with --without-memory-
manager.
- Open MPI will now complain and refuse to use leave_pinned if
no memory intercept / mallopt option is available.
This commit was SVN r18654.
After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach.
I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive.
This commit was SVN r18619.
Add a new function to opal_progress that tells us our recursion depth to support that solution.
Yes, I know this sounds picky, but good ol' Jeff managed to make it happen by driving his cluster near to death...
Also ensure that we declare "failed" for the daemon job when daemons fail instead of the application job. This is important so that orte knows that it cannot use xcast to tell daemons to "exit", nor should it expect all daemons to respond. Otherwise, it is possible to hang.
After lots of testing, decide to default (again) to slurm detecting failed orteds. This proved necessary to avoid rather annoying hangs that were difficult to recover from. There are conditions where slurm will fail to launch all daemons (slurm folks are working on it), and yet again, good ol' Jeff managed to find both of them.
Thanks you Jeff! :-/
This commit was SVN r18611.
to modify the callback array (add or remove), make sure we don't call
the same callback twice if it get remove in another thread.
This commit was SVN r18608.
orte-checkpoint/orte-restart seem to not seem to totally like orte_output so revert them to opal_output for now. Since we have no need for the additional complexity of orte_output we can drop it for now and revisit this if anyone needs it later.
It seems that if you set the verbose level on an output handle then try to call a normal orte_output() on it then the message will *not* be printed. This is the same for opal_output, and seems incorrect to me because it stops some error messages from being printed out if you do not directly specify opal_output(0, ...). Maybe someone should take a look a this.
orte-checkpoint would segv if passed an incorrect PID. Fixed the return code so it errors out properly.
Thanks to Eric Roman for bringing this to my attention.
This commit was SVN r18583.
If Valgrind is requested but wrong version is supplied, print error messages and stop.
Save the CPPFLAGS in opal_memchecker_valgrind_CPPFLAGS, which could be used in
Makefile.am.
Many thanks to Jeff.
This commit was SVN r18573.
that can *sometimes* cause problems with "make -j [N>1] install".
Ensure to make the target directory before we copy stuff into it --
read the thread starting here for more details:
http://www.open-mpi.org/community/lists/devel/2008/06/4080.php
This commit was SVN r18570.
1. If we don't have the topology information, don't bother trying to
create cross-referencing information
1. Ensure to only check for valid processor ID's
This commit was SVN r18462.
made in r18345 for ompi_version_string. This was done per request from Jeff
Squyres to maintain consistency and to remove some warnings caused by the
non-use of some static const char.
This commit was SVN r18461.
The following SVN revision numbers were found above:
r18345 --> open-mpi/ompi@8dd0421015
such, the commit message back to the master SVN repository is fairly
long.
= ORTE Job-Level Output Messages =
Add two new interfaces that should be used for all new code throughout
the ORTE and OMPI layers (we already make the search-and-replace on
the existing ORTE / OMPI layers):
* orte_output(): (and corresponding friends ORTE_OUTPUT,
orte_output_verbose, etc.) This function sends the output directly
to the HNP for processing as part of a job-specific output
channel. It supports all the same outputs as opal_output()
(syslog, file, stdout, stderr), but for stdout/stderr, the output
is sent to the HNP for processing and output. More on this below.
* orte_show_help(): This function is a drop-in-replacement for
opal_show_help(), with two differences in functionality:
1. the rendered text help message output is sent to the HNP for
display (rather than outputting directly into the process' stderr
stream)
1. the HNP detects duplicate help messages and does not display them
(so that you don't see the same error message N times, once from
each of your N MPI processes); instead, it counts "new" instances
of the help message and displays a message every ~5 seconds when
there are new ones ("I got X new copies of the help message...")
opal_show_help and opal_output still exist, but they only output in
the current process. The intent for the new orte_* functions is that
they can apply job-level intelligence to the output. As such, we
recommend that all new ORTE and OMPI code use the new orte_*
functions, not thei opal_* functions.
=== New code ===
For ORTE and OMPI programmers, here's what you need to do differently
in new code:
* Do not include opal/util/show_help.h or opal/util/output.h.
Instead, include orte/util/output.h (this one header file has
declarations for both the orte_output() series of functions and
orte_show_help()).
* Effectively s/opal_output/orte_output/gi throughout your code.
Note that orte_output_open() takes a slightly different argument
list (as a way to pass data to the filtering stream -- see below),
so you if explicitly call opal_output_open(), you'll need to
slightly adapt to the new signature of orte_output_open().
* Literally s/opal_show_help/orte_show_help/. The function signature
is identical.
=== Notes ===
* orte_output'ing to stream 0 will do similar to what
opal_output'ing did, so leaving a hard-coded "0" as the first
argument is safe.
* For systems that do not use ORTE's RML or the HNP, the effect of
orte_output_* and orte_show_help will be identical to their opal
counterparts (the additional information passed to
orte_output_open() will be lost!). Indeed, the orte_* functions
simply become trivial wrappers to their opal_* counterparts. Note
that we have not tested this; the code is simple but it is quite
possible that we mucked something up.
= Filter Framework =
Messages sent view the new orte_* functions described above and
messages output via the IOF on the HNP will now optionally be passed
through a new "filter" framework before being output to
stdout/stderr. The "filter" OPAL MCA framework is intended to allow
preprocessing to messages before they are sent to their final
destinations. The first component that was written in the filter
framework was to create an XML stream, segregating all the messages
into different XML tags, etc. This will allow 3rd party tools to read
the stdout/stderr from the HNP and be able to know exactly what each
text message is (e.g., a help message, another OMPI infrastructure
message, stdout from the user process, stderr from the user process,
etc.).
Filtering is not active by default. Filter components must be
specifically requested, such as:
{{{
$ mpirun --mca filter xml ...
}}}
There can only be one filter component active.
= New MCA Parameters =
The new functionality described above introduces two new MCA
parameters:
* '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that
help messages will be aggregated, as described above. If set to 0,
all help messages will be displayed, even if they are duplicates
(i.e., the original behavior).
* '''orte_base_show_output_recursions''': An MCA parameter to help
debug one of the known issues, described below. It is likely that
this MCA parameter will disappear before v1.3 final.
= Known Issues =
* The XML filter component is not complete. The current output from
this component is preliminary and not real XML. A bit more work
needs to be done to configure.m4 search for an appropriate XML
library/link it in/use it at run time.
* There are possible recursion loops in the orte_output() and
orte_show_help() functions -- e.g., if RML send calls orte_output()
or orte_show_help(). We have some ideas how to fix these, but
figured that it was ok to commit before feature freeze with known
issues. The code currently contains sub-optimal workarounds so
that this will not be a problem, but it would be good to actually
solve the problem rather than have hackish workarounds before v1.3 final.
This commit was SVN r18434.
Also set the 'best_priority' to the smallest 32 bit integer possible so negaive priority component can be selected if they are the highest ranking component available.
This commit was SVN r18427.
to allow explicit grouping of hot functions into similar code
sections upon link-time. Should decrease TLB misses (iff the code-
section is really too large)...
Candidates for __opal_attribute_hot__ are MPI_Isend MPI_Irecv,
MPI_Wait, MPI_Waitall
Candidates for __opal_attribute_cold__ are MPI_Init, MPI_Finalize and
MPI_Abort...
This commit was SVN r18421.
* Remove the opal_only option. This was suffering from bit rot, and no one uses it. It can be added back fairly easily if wanted.
* Cleanup metadata interactions at the local level.
* Touch up some of the INC funcitonality (fix typos and a minor ordering issue)
This commit was SVN r18416.
http://www.open-mpi.org/community/lists/devel/2008/04/3779.php
{{{
svn merge -r 18276:18380 https://svn.open-mpi.org/svn/ompi/tmp-public/jjh-mca-play .
}}}
Any components not in the trunk, but in one of the effected frameworks *must* be
updated. Contact the list, look at the RFC, or look at the diff for how to do this.
Sorry for the early commit of this, but I wanted to get it in today (per RFC) and
didn't know if I would have a chance later today.
This commit was SVN r18381.
The problem was caused by a bad ordering between the restart of the ORTE level tcp connections (in the OOB - out-of-band communication) and the Open MPI level tcp connections (BTLs). Before this commit ORTE would shutdown and restart the OOB completely before the OMPI level restarted its tcp connections. What would happen is that a socket descriptor used by the OMPI level on checkpoint was assigned to the ORTE level on restart. But the OMPI level had no knowledge that the socket descriptor it was previously using has been recycled so it closed it on restart. This caused the ORTE level to break as the newly created socket descriptor was closed without its knowledge.
The fix is to have the OMPI level shutdown tcp connections, allow the ORTE level to restart, and then allow the OMPi level to restart its connections. This seems obvious, and I'm surprised that this bug has not cropped up sooner. I'm confident that this specific problem has been fixed with this commit.
Thanks to Eric Roman and Tamer El Sayed for their help in identifying this problem, and patience while I was fixing it.
* Add a new state {{{OPAL_CRS_RESTART_PRE}}}. This state identifies when we are on the down slope of the INC (finalize-like) which is useful when you want to close, but not reopen a component set for fear of interfering with a lower level.
* Use this new state in OMPI level coordination. Here we want to make sure to play well with both the OMPI/BTL/TCP and ORTE/OOB/TCP components.
* Update ft_event functions in PML and BML to handle the new restart state.
* Add an additional flag to the error output in OOB/TCP so we can see what the socket descriptor was on failure as this can be helpful in debugging.
This commit was SVN r18276.
{{{
svn merge -r 18218:18240 https://svn.open-mpi.org/svn/ompi/tmp/jjh-scratch .
}}}
Contains:
* Primarily a fix for a user reported problem where a cached file descriptor is causing a SIGPIPE on restart.
* Cleanup some small memory leaks from using mca_base_param_env_var() - Thanks Jeff
* Cleanup ORTE FT tool compilation in non-FT builds - Thanks Tim P.
* Cleanup mpi interface with missplaced {{{OPAL_CR_ENTER_LIBRARY}}} - Thanks Terry
* Some other sundry cleanup items all dealing with C/R functionality in the trunk.
This commit was SVN r18241.
Restore the "do-not-launch" functionality so users can test a mapping without launching it.
Add a "do-not-resolve" cmd line flag to mpirun so the opal/util/if.c code does not attempt to resolve network addresses, thus enabling a user to test a hostfile mapping without hanging on network resolve requests.
Add a function to hostfile to generate an ordered list of host names from a hostfile
This commit was SVN r18190.
1. applied prefix rule to functions and variables of RMAPS rank_file component
2. cleaned ompi_mpi_init.c from paffinity code
3. paffinity code moved to new opal/mca/paffinity/base/paffinity_base_service.c file
4. added opal_paffinity_slot_list mca parameter
This commit was SVN r18019.
mechanisms (such as epoll) if someone (ompi_mpi_init()) requests
otherwise. See big comment in opal/event/event.c for a full
explanation.
This commit was SVN r17956.
Greatly reduce the number of "foo" -> "opal_foo" symbol renames in the
libevent source, and instead greatly expand the event_rename.h file
that uses preprocessor macros to make all public symbols be
"opal_foo".
This commit was SVN r17923.
some cleanups and standardizations in the various */tools/*/
Makefile.am files. This commit:
* Somewhat simplify the tool Makefile.am's
* Makes the tool Makefile.am's consistent with each other (do similar
actions in similar ways)
* Update the tool Makefile.am's to remove old kruft that was required
by older versions of AM (trunk requires AM >=1.10)
This commit was SVN r17921.
* The opal_sys_timer_get_cycles() call was implemented for
Sparc v9 using inline assembly, but not in the assembly files.
This would only currently matter on Linux Sparc systems using
a compiler that didn't support inline assembly (not many of
those), but it should be there for completion.
* The linux timer component would always build on non-Alpha
platforms, rather than only building on platforms where
opal_sys_timer_get_cycles() was implemented. This would
only matter on a very narrow set of platforms that we don't
really support, but still, it could be more right. We now
only build the component on platforms where we have the
assembly call to get the cycle counter.
* Added a comment to opal/sys/timer.h to note that the linux
timer component needed to be updated if another platform was
added.
This should be harmless to commit. It will only really change
behaviors on platforms we don't have assembly support for, which
currently won't make it through configure. It really only matters
when (if?) we support atomic operations through libatomic_ops.
This commit was SVN r17887.
This commit lowers the priority of the darwin backtrace component
below that of the ''execinfo'' and ''stackprint'' components, which
will cause OS X Leopard to use the ''execinfo'' component. execinfo
utilizes a public API for printing the stacktrace. The ''darwin''
component uses some evil hacks and a not-so supported package from
Apple to print the stack trace.
This commit was SVN r17840.
environment variables in a consistent manner. These functions
retrieve the user and the temporary directories (based on the
system).
This commit was SVN r17815.
seemed to be the right thing(tm), but broke the Sun Studio C++
compiler under Linux (ticket 747).
This patch should allow inclusion into C and C++ from other header
files without problems.
This commit was SVN r17792.
The following SVN revision numbers were found above:
r17488 --> open-mpi/ompi@d53131f261
r17504 --> open-mpi/ompi@b22e8e7567
* Extension to the ESS framework to support C/R
* Fixed support for {{{snapc_base_establish_global_snapshot_dir}}}
* Fixed FileM support
* Misc. minor code modifications
There are some outstanding visability issues that I want to fix next.
This commit was SVN r17725.
Also, update some properties (source files should not be executeable...), and remove a couple unneeded inclusions of orte_proc_table.h
This commit was SVN r17655.
Basically, the method employed here is to have a recv create a zero-time timer event that causes the event library to execute a function that processes the message once the recv returns. Thus, any action taken as a result of processing the message occur outside of a recv.
Created two new macros to assist:
ORTE_MESSAGE_EVENT: creates the zero-time event, passing info in a new orte_message_event_t object
ORTE_PROGRESSED_WAIT: while waiting for specified conditions, just calls progress so messages can be recv'd.
Also fixed the failed_launch function as we no longer block in the orted callback function. Updated the error messages to reflect revision. No change in API to this function, but PLM "owners" may want to check their internal error messages to avoid duplication and excessive output.
This has been tested on Mac, TM, and SLURM.
This commit was SVN r17647.
threaded CR builds. MTT caught this by running the IU FT CR test 'inflight'
which under certian timing scenarios will trigger this.
This commit was SVN r17538.
Some MPI C interface files saw some spacing changes to conform to the coding standards of Open MPI.
Changed MPI C interface files to use {{{OPAL_CR_ENTER_LIBRARY()}}} and {{{OPAL_CR_EXIT_LIBRARY()}}} instead of just {{{OPAL_CR_TEST_CHECKPOINT_READY()}}}. This will allow the checkpoint/restart system more flexibility in how it is to behave.
Fixed the configure check for {{{--enable-ft-thread}}} so it has a know dependance on {{{--enable-mpi-thread}}} (and/or {{{--enable-progress-thread}}}).
Added a line for Checkpoint/Restart support to {{{ompi_info}}}.
Added some options to choose at runtime whether or not to use the checkpoint polling thread. By default, if the user asked for it to be compiled in, then it is used. But some users will want the ability to toggle its use at runtime.
There are still some places for improvement, but the feature works correctly. As always with Checkpoint/Restart, it is compiled out unless explicitly asked for at configure time. Further, if it was configured in, then it is not used unless explicitly asked for by the user at runtime.
This commit was SVN r17516.
by the checkpoint/restart feature. Other constraints could be enforced here,
but at the moment it is only the checkpointable constraint.
So this commit just removes this logic from non-c/r builds. If someone
wanted to add a new constraint in the future then there is a comment in
the code that directs them a bit.
This commit was SVN r17447.
implement specific function, thereby
removing bogus requirement on valgrind/valgrind.h
dough...
- Call specific function runindebugger() before
doing expensive checks on each component of struct.
- Get rid of void* warnings..
This commit was SVN r17438.
Update properties to ignore the carto_file_lex.c file since that is also dynamically generated.
Update the build-hgignore.pl to properly disregard DS_Store files
This commit was SVN r17301.
map_to_processor_id,
map_to_socket_core,
max_processor_id,
max_socket,
max_core.
In OS other then Linux, those functions will return OPAL_ERR_NOT_SUPPORTED.
--This Line, and those below, will be ignored--
M paffinity/linux/paffinity_linux_module.c
M paffinity/paffinity.h
M paffinity/base/base.h
M paffinity/base/paffinity_base_wrappers.c
M paffinity/windows/paffinity_windows_module.c
M paffinity/solaris/paffinity_solaris_module.c
This commit was SVN r17173.
This patch fixes the segfault, so closing the ticket might be possible.
It's a very conservative patch. Perhaps the freeaddrinfo spec says that
it will never allocate res in case of errors, but for now, I neither
have the spec nor the will to rely on it.
This commit was SVN r17150.
"const" in the argument creates [correct] warnings (because __FILE__
is a (const char*)). Plus, opal_object.cls_init_file_name is already
(const char*).
This commit was SVN r17145.
ompi_pointer_array.c:ompi_pointer_array_set_item() was slightly
changed such that the "find the next open slot when the requested
index was already open" logic was no longer right -- since the new
lowest_free value is not set until ''after'' we look for the next open
slot, we need to start searching for the new lowest_free slot at the
(index+1) position (not the index position).
This commit was SVN r17021.
The following SVN revision numbers were found above:
r17007 --> open-mpi/ompi@906e8bf1d1
(sometimes after the merge with the ORTE branch), the opal_pointer_array
will became the only pointer_array implementation (the orte_pointer_array
will be removed).
This commit was SVN r17007.
about linkers, have all OPAL, ORTE, and OMPI components '''not'' link
against the OPAL, ORTE, or OMPI libraries.
See ttp://www.open-mpi.org/community/lists/users/2007/10/4220.php for
details (or https://svn.open-mpi.org/trac/ompi/wiki/Linkers for a
better-formatted version of the same info).
This commit was SVN r16968.
* Conditionalize around `static inline` using
`OPAL_HAVE_INLINE_ATOMIC*` macros
* Remove redundant `opal_atomic*` prototypes (they
belong in the top-level `sys/atomic.h`
This commit was SVN r16957.
The following SVN revision numbers were found above:
r16807 --> open-mpi/ompi@b7c885247a
(e.g., gcc) are indifferent about this, while others are more
particular (e.g., Sun Studio 12).
* Typo: `asms.s` to `asm.s`
* Eliminate "foo is multiply-defined" linker errors on
Solaris by making the declarations in `opal/sys/atomic.h` agree
with their corresponding definitions (use `static inline` in *both*
places).
This commit was SVN r16807.
requesting it. This commit adds a bit of error checking to keep us from
participating in a checkpoint that we did not initiate and therefore are
not ready for.
Thanks to Paul Hargrove and Eric Roman for their help with this.
This commit was SVN r16694.
getting rid of compiler-warning when compiled with trunk of g++:
when doing --enable-debug:
../../../../orte/class/orte_pointer_array.h:128: warning: deprecated
conversion from string constant to 'char*'
This commit was SVN r16656.
methods (in order of precedence):
1. #pragma ident <ident string> (e.g., Intel and Sun)
1. #ident <ident string> (e.g., GCC)
1. static const char ident[] = <ident string> (all others)
By default, the ident string used is the standard Open MPI version string. Only
the following libraries will get the embedded version strings (e.g., DSOs will
not):
* libmpi.so
* libmpi_cxx.so
* libmpi_f77.so
* libopen-pal.so
* libopen-rte.so
* Added two new configure options:
* `--with-package-name="STRING"` (defaults to "Open MPI username@hostname
Distribution"). `STRING` is displayed by `ompi_info` next to the "Package"
heading.
* `--with-ident-string="STRING"` (defaults to the standard Open MPI version
string - e.g., X.Y.Zr######). `%VERSION%` will expand to the Open MPI
version string if it is supplied to this configure option.
This commit was SVN r16644.
* Fix some missing includes in a few places.
* Add the cr_request() functionality to the BLCR CRS component.
We are now dependent upon the 0.6.* series of BLCR.
* Made the CR notification mechanism a registered function.
This way we can have an OPAL-only version and it can be replaced at
runtime with the ORTE version.
* Add a 'opal_cr_allow_opal_only' parameter that will enable OPAL-only
CR functionality when the user wants it. Default: Disabled.
* Fix the placement of a checkpoint request check in MPI_Init
* Pull the OPAL notification mechanism into the SnapC framework.
* We no longer fork/exec the 'opal-checkpoint' command for local
checkpointing, the Local coordinator in the orted does this directly.
* The Local and Application coordinator talk together bypassing the OPAL
notifiation mechanism.
* Optimized the Local <-> App Coordinator communication.
* Improved the structure used to track vpid_snapshots in the local coord.
* Fix a race condition in which an application under heavy communication load
may produce an inconsistent global checkpoint.
This commit was SVN r16389.
The commit has been tested for C/R and Cray operations, and on Odin (SLURM, rsh) and RoadRunner (TM). I tried to update all environments, but obviously could not test them. I know that Windows needs some work, and have highlighted what is know to be needed in the odls process component.
This represents a lot of work by Brian, Tim P, Josh, and myself, with much advice from Jeff and others. For posterity, I have appended a copy of the email describing the work that was done:
As we have repeatedly noted, the modex operation in MPI_Init is the single greatest consumer of time during startup. To-date, we have executed that operation as an ORTE stage gate that held the process until a startup message containing all required modex (and OOB contact info - see #3 below) info could be sent to it. Each process would send its data to the HNP's registry, which assembled and sent the message when all processes had reported in.
In addition, ORTE had taken responsibility for monitoring process status as it progressed through a series of "stage gates". The process reported its status at each gate, and ORTE would then send a "release" message once all procs had reported in.
The incoming changes revamp these procedures in three ways:
1. eliminating the ORTE stage gate system and cleanly delineating responsibility between the OMPI and ORTE layers for MPI init/finalize. The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info. The allgather is implemented using the orte_grpcomm framework since the BTL's are not active at that point. At the moment, the grpcomm framework only has a "basic" component analogous to OMPI's "basic" coll framework - I would recommend that the MPI team create additional, more advanced components to improve performance of this step.
The other stage gates have been replaced by orte_grpcomm barrier functions. We tried to use MPI barriers instead (since the BTL's are active at that point), but - as we discussed on the telecon - these are not currently true barriers so the job would hang when we fell through while messages were still in process. Note that the grpcomm barrier doesn't actually resolve that problem, but Brian has pointed out that we are unlikely to ever see it violated. Again, you might want to spend a little time on an advanced barrier algorithm as the one in "basic" is very simplistic.
Summarizing this change: ORTE no longer tracks process state nor has direct responsibility for synchronizing jobs. This is now done via collective operations within the MPI layer, albeit using ORTE collective communication services. I -strongly- urge the MPI team to implement advanced collective algorithms to improve the performance of this critical procedure.
2. reducing the volume of data exchanged during modex. Data in the modex consisted of the process name, the name of the node where that process is located (expressed as a string), plus a string representation of all contact info. The nodename was required in order for the modex to determine if the process was local or not - in addition, some people like to have it to print pretty error messages when a connection failed.
The size of this data has been reduced in three ways:
(a) reducing the size of the process name itself. The process name consisted of two 32-bit fields for the jobid and vpid. This is far larger than any current system, or system likely to exist in the near future, can support. Accordingly, the default size of these fields has been reduced to 16-bits, which means you can have 32k procs in each of 32k jobs. Since the daemons must have a vpid, and we require one daemon/node, this also restricts the default configuration to 32k nodes.
To support any future "mega-clusters", a configuration option --enable-jumbo-apps has been added. This option increases the jobid and vpid field sizes to 32-bits. Someday, if necessary, someone can add yet another option to increase them to 64-bits, I suppose.
(b) replacing the string nodename with an integer nodeid. Since we have one daemon/node, the nodeid corresponds to the local daemon's vpid. This replaces an often lengthy string with only 2 (or at most 4) bytes, a substantial reduction.
(c) when the mca param requesting that nodenames be sent to support pretty error messages, a second mca param is now used to request FQDN - otherwise, the domain name is stripped (by default) from the message to save space. If someone wants to combine those into a single param somehow (perhaps with an argument?), they are welcome to do so - I didn't want to alter what people are already using.
While these may seem like small savings, they actually amount to a significant impact when aggregated across the entire modex operation. Since every proc must receive the modex data regardless of the collective used to send it, just reducing the size of the process name removes nearly 400MBytes of communication from a 32k proc job (admittedly, much of this comm may occur in parallel). So it does add up pretty quickly.
3. routing RML messages to reduce connections. The default messaging system remains point-to-point - i.e., each proc opens a socket to every proc it communicates with and sends its messages directly. A new option uses the orteds as routers - i.e., each proc only opens a single socket to its local orted. All messages are sent from the proc to the orted, which forwards the message to the orted on the node where the intended recipient proc is located - that orted then forwards the message to its local proc (the recipient). This greatly reduces the connection storm we have encountered during startup.
It also has the benefit of removing the sharing of every proc's OOB contact with every other proc. The orted routing tables are populated during launch since every orted gets a map of where every proc is being placed. Each proc, therefore, only needs to know the contact info for its local daemon, which is passed in via the environment when the proc is fork/exec'd by the daemon. This alone removes ~50 bytes/process of communication that was in the current STG1 startup message - so for our 32k proc job, this saves us roughly 32k*50 = 1.6MBytes sent to 32k procs = 51GBytes of messaging.
Note that you can use the new routing method by specifying -mca routed tree - if you so desire. This mode will become the default at some point in the future.
There are a few minor additional changes in the commit that I'll just note in passing:
* propagation of command line mca params to the orteds - fixes ticket #1073. See note there for details.
* requiring of "finalize" prior to "exit" for MPI procs - fixes ticket #1144. See note there for details.
* cleanup of some stale header files
This commit was SVN r16364.
and implementation. This has shown drastic performance benefit when
transferring Many files at roughly the same time.
I tested this for many different filem operations and everything was working
fine. Let me know if you have any problems with this functionality.
Some Notes:
- opal-checkpoint now has a 'quiet' flag to keep it from being too verbose.
- FileM RSH component is fully non-blocking.
- FileM RSH component has incomming connection throttling since by default
ssh only allows 10 concurrent scp connections to any single host. This
default can be adjusted via an MCA parameter.
{{{-mca filem_rsh_max_incomming 10}}}
- There is an MCA parameter for max outgoing connections, but it is currently
not implemented. If someone needs it then it should not be hard to implement.
{{{-mca filem_rsh_max_outgoing 10}}}
- Changed the FileM request structure so that it is a bit more explicit and
flexible.
- Moved the 'preload-binary' and 'preload-files' functionality into odls/base
allowing for code reuse in the 'process' and 'default' ODLS components.
- Fixed a bug in the process name resolution which broke the 'preload-*'
functionality due to GPR table structure changes.
- The FileM RSH component might be able to see even more speedup from using a
thread pool to operate on the work_pool structures, but that is for future
work.
- Added a 'opal-show-help' file to ODLS Base
This commit was SVN r16252.
was taken form the $CWD to the storage directory. Now we just store directly
to the storage directory which can reduce NFS traffic if working in that mode.
A slight performance boost, but at the point you are using NFS you are paying
a penalty anyway. Now you just don't have to pay it twice :)
This commit was SVN r16099.
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
was brought in. This supercedes the GLOBL patch that we had been using
with Libtool 2.1a versions prior to the lt_dladvise code. Autogen
tries to figure out which version you're on, so either will now work with
the trunk.
This commit was SVN r15903.
- If one wants to use this solution, remember to unload the project 'orte-restart' which is currently not working for Windows.
This commit was SVN r15680.
This is because internally 'self' uses dlopen to look at the application
running to determine if it can/should be used or not.
This commit was SVN r15673.
in a callback from the event library and post an RML receive, we'll
deadlock because the event library wouldn't be entered until the
event library was not already entered. Now just protect data structures
(which we were basically already doing) instead of code, like good
threading people ;).
This commit was SVN r15585.
* 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
