The intercomm "merge" function can create a linkage between procs that was not reflected anywhere in a modex, and so at least some of the procs in the resulting communicator don't know how to talk to some of the new communicator's peers.
For example, consider the case where:
1. parent job A comm_spawns a process (job B) - these processes exchange modex and can communicate
2. parent job A now comm_spawns another process (job C) - again, these can communicate, but the proc in C knows nothing of B
3. do an intercomm merge across the communicators created by the two comm_spawns. This puts B and C into the same communicator, but they know nothing about how to talk to each other as they were not involved in any exchange of contact info. Hence, collectives on that communicator now fail.
This fix adds an API to the ompi/dpm framework that (a) exchanges the modex info across the procs in the merge to ensure all procs know how to communicate, and (b) calls add_procs to give the btl's a chance to select transports to any new procs.
cmr:v1.7.3:reviewer=jsquyres
This commit was SVN r29166.
The following Trac tickets were found above:
Ticket 2904 --> https://svn.open-mpi.org/trac/ompi/ticket/2904
onflict that can cause messages to be lost. Add detection of this condition, and have both processes cancel their connect operations. The process with the higher rank will
reconnect, while the lower rank process will simply wait for the connection to be created.
Refs trac:3696
This commit was SVN r29139.
The following Trac tickets were found above:
Ticket 3696 --> https://svn.open-mpi.org/trac/ompi/ticket/3696
oob_tcp_connection.c: In function 'mca_oob_tcp_peer_accept':
oob_tcp_connection.c:725:9: warning: variable 'cmpval' set but not used [-Wunused-but-set-variable]
Refs trac:3696
This commit was SVN r29091.
The following Trac tickets were found above:
Ticket 3696 --> https://svn.open-mpi.org/trac/ompi/ticket/3696
* paccept - establish a persistent listening port for async connect requests
* pconnect - async connect to remote process that has posted a paccept port. Provides a timeout mechanism, and allows the underlying implementation to retry until timeout
* pclose - shuts down a prior paccept posting
Includes example programs paccept.c and pconnect.c in orte/test/mpi. New MPI extension interfaces coming...
This commit was SVN r29063.
*** THIS RFC INCLUDES A MINOR CHANGE TO THE MPI-RTE INTERFACE ***
Note: during the course of this work, it was necessary to completely separate the MPI and RTE progress engines. There were multiple places in the MPI layer where ORTE_WAIT_FOR_COMPLETION was being used. A new OMPI_WAIT_FOR_COMPLETION macro was created (defined in ompi/mca/rte/rte.h) that simply cycles across opal_progress until the provided flag becomes false. Places where the MPI layer blocked waiting for RTE to complete an event have been modified to use this macro.
***************************************************************************************
I am reissuing this RFC because of the time that has passed since its original release. Since its initial release and review, I have debugged it further to ensure it fully supports tests like loop_spawn. It therefore seems ready for merge back to the trunk. Given its prior review, I have set the timeout for one week.
The code is in https://bitbucket.org/rhc/ompi-oob2
WHAT: Rewrite of ORTE OOB
WHY: Support asynchronous progress and a host of other features
WHEN: Wed, August 21
SYNOPSIS:
The current OOB has served us well, but a number of limitations have been identified over the years. Specifically:
* it is only progressed when called via opal_progress, which can lead to hangs or recursive calls into libevent (which is not supported by that code)
* we've had issues when multiple NICs are available as the code doesn't "shift" messages between transports - thus, all nodes had to be available via the same TCP interface.
* the OOB "unloads" incoming opal_buffer_t objects during the transmission, thus preventing use of OBJ_RETAIN in the code when repeatedly sending the same message to multiple recipients
* there is no failover mechanism across NICs - if the selected NIC (or its attached switch) fails, we are forced to abort
* only one transport (i.e., component) can be "active"
The revised OOB resolves these problems:
* async progress is used for all application processes, with the progress thread blocking in the event library
* each available TCP NIC is supported by its own TCP module. The ability to asynchronously progress each module independently is provided, but not enabled by default (a runtime MCA parameter turns it "on")
* multi-address TCP NICs (e.g., a NIC with both an IPv4 and IPv6 address, or with virtual interfaces) are supported - reachability is determined by comparing the contact info for a peer against all addresses within the range covered by the address/mask pairs for the NIC.
* a message that arrives on one TCP NIC is automatically shifted to whatever NIC that is connected to the next "hop" if that peer cannot be reached by the incoming NIC. If no TCP module will reach the peer, then the OOB attempts to send the message via all other available components - if none can reach the peer, then an "error" is reported back to the RML, which then calls the errmgr for instructions.
* opal_buffer_t now conforms to standard object rules re OBJ_RETAIN as we no longer "unload" the incoming object
* NIC failure is reported to the TCP component, which then tries to resend the message across any other available TCP NIC. If that doesn't work, then the message is given back to the OOB base to try using other components. If all that fails, then the error is reported to the RML, which reports to the errmgr for instructions
* obviously from the above, multiple OOB components (e.g., TCP and UD) can be active in parallel
* the matching code has been moved to the RML (and out of the OOB/TCP component) so it is independent of transport
* routing is done by the individual OOB modules (as opposed to the RML). Thus, both routed and non-routed transports can simultaneously be active
* all blocking send/recv APIs have been removed. Everything operates asynchronously.
KNOWN LIMITATIONS:
* although provision is made for component failover as described above, the code for doing so has not been fully implemented yet. At the moment, if all connections for a given peer fail, the errmgr is notified of a "lost connection", which by default results in termination of the job if it was a lifeline
* the IPv6 code is present and compiles, but is not complete. Since the current IPv6 support in the OOB doesn't work anyway, I don't consider this a blocker
* routing is performed at the individual module level, yet the active routed component is selected on a global basis. We probably should update that to reflect that different transports may need/choose to route in different ways
* obviously, not every error path has been tested nor necessarily covered
* determining abnormal termination is more challenging than in the old code as we now potentially have multiple ways of connecting to a process. Ideally, we would declare "connection failed" when *all* transports can no longer reach the process, but that requires some additional (possibly complex) code. For now, the code replicates the old behavior only somewhat modified - i.e., if a module sees its connection fail, it checks to see if it is a lifeline. If so, it notifies the errmgr that the lifeline is lost - otherwise, it notifies the errmgr that a non-lifeline connection was lost.
* reachability is determined solely on the basis of a shared subnet address/mask - more sophisticated algorithms (e.g., the one used in the tcp btl) are required to handle routing via gateways
* the RML needs to assign sequence numbers to each message on a per-peer basis. The receiving RML will then deliver messages in order, thus preventing out-of-order messaging in the case where messages travel across different transports or a message needs to be redirected/resent due to failure of a NIC
This commit was SVN r29058.
So shift the cutoff param to the MPI layer, and have it solely determine whether or not we call modex_recv on the hostname. If comm_world is of size greater than the cutoff, then we don't automatically retrieve the hostname when we build the ompi_proc_t for a process - instead, we fill the hostname entry on first call to modex_recv for that process.
The param is now "ompi_hostname_cutoff=N", where N=number of procs for cutoff.
Refs trac:3729
This commit was SVN r29056.
The following Trac tickets were found above:
Ticket 3729 --> https://svn.open-mpi.org/trac/ompi/ticket/3729
* add a new MCA param orte_hostname_cutoff to specify the number of nodes at which we stop including hostnames. This defaults to INT_MAX => always include hostnames. If a value is given, then we will include hostnames for any allocation smaller than the given limit.
* remove ompi_proc_get_hostname. Replace all occurrences with a direct link to ompi_proc_t's proc_hostname, protected by appropriate "if NULL"
* modify the OMPI-ORTE integration component so that any call to modex_recv automatically loads the ompi_proc_t->proc_hostname field as well as returning the requested info. Thus, any process whose modex info you retrieve will automatically receive the hostname. Note that on-demand retrieval is still enabled - i.e., if we are running under direct launch with PMI, the hostname will be fetched upon first call to modex_recv, and then the ompi_proc_t->proc_hostname field will be loaded
* removed a stale MCA param "mpi_keep_peer_hostnames" that was no longer used anywhere in the code base
* added an envar lookup in ess/pmi for the number of nodes in the allocation. Sadly, PMI itself doesn't provide that info, so we have to get it a different way. Currently, we support PBS-based systems and SLURM - for any other, rank0 will emit a warning and we assume max number of daemons so we will always retain hostnames
This commit was SVN r29052.
This creates a really bad scaling behavior. Users have found a nearly 20% launch time differential between mpirun and PMI, with PMI being the slower method. Some of the problem is attributable to poor exchange algorithms in RM's like Slurm and Alps, but we make things worse by calling "get" so many times.
Nathan (with a tad advice from me) has attempted to alleviate this problem by reducing the number of "get" calls. This required the following changes:
* upon first request for data, have the OPAL db pmi component fetch and decode *all* the info from a given remote proc. It turned out we weren't caching the info, so we would continually request it and only decode the piece we needed for the immediate request. We now decode all the info and push it into the db hash component for local storage - and then all subsequent retrievals are fulfilled locally
* reduced the amount of data by eliminating the exchange of the OMPI_ARCH value if heterogeneity is not enabled. This was used solely as a check so we would error out if the system wasn't actually homogeneous, which was fine when we thought there was no cost in doing the check. Unfortunately, at large scale and with direct launch, there is a non-zero cost of making this test. We are open to finding a compromise (perhaps turning the test off if requested?), if people feel strongly about performing the test
* reduced the amount of RTE data being automatically fetched, and fetched the rest only upon request. In particular, we no longer immediately fetch the hostname (which is only used for error reporting), but instead get it when needed. Likewise for the RML uri as that info is only required for some (not all) environments. In addition, we no longer fetch the locality unless required, relying instead on the PMI clique info to tell us who is on our local node (if additional info is required, the fetch is performed when a modex_recv is issued).
Again, all this only impacts direct launch - all the info is provided when launched via mpirun as there is no added cost to getting it
Barring objections, we may move this (plus any required other pieces) to the 1.7 branch once it soaks for an appropriate time.
This commit was SVN r29040.
The orte rte component checks the orte_standalone_operation to decide
if it should wait for a message from the hnp or wait on the debugger.
This variable needed to be set to true in ess/pmi to enable the
correct path when direct launching.
cmr=v1.7.3:reviewer=rhc
cmr=v1.6.6:reviewer=rhc
This commit was SVN r29013.
This commit reintroduces key compression into the pmi db. This feature
compresses the keys stored into the component into a small number of
PMI keys by serializing the data and base64 encoding the result. This
will avoid issues with Cray PMI which restricts us to ~ 3 PMI keys per
rank.
This commit was SVN r28993.
Simplify the whole stripping of prefix method by consolidating it into a single MCA param. Allow for multiple prefixes to be stripped, each separated in the param by a comma. If no prefix is given, or the specified prefix isn't in the nodename, then just use the hostname itself.
This commit was SVN r28974.
The following Trac tickets were found above:
Ticket 3710 --> https://svn.open-mpi.org/trac/ompi/ticket/3710
on.
This corrects a problem with Cray systems where the login node's hostname
was being stripped causing the login node to be used as a compute node by
mpirun.
cmr=v1.7.3:reviewer=rhc
This commit was SVN r28970.
George and I were talking about ORTE's error handling the other day in regards to the right way to deal with errors in the updated OOB. Specifically, it seemed a bad idea for a library such as ORTE to be aborting the job on its own prerogative. If we lose a connection or cannot send a message, then we really should just report it upwards and let the application and/or upper layers decide what to do about it.
The current code base only allows a single error callback to exist, which seemed unduly limiting. So, based on the conversation, I've modified the errmgr interface to provide a mechanism for registering any number of error handlers (this replaces the current "set_fault_callback" API). When an error occurs, these handlers will be called in order until one responds that the error has been "resolved" - i.e., no further action is required - by returning OMPI_SUCCESS. The default MPI layer error handler is specified to go "last" and calls mpi_abort, so the current "abort" behavior is preserved unless other error handlers are registered.
In the register_callback function, I provide an "order" param so you can specify "this callback must come first" or "this callback must come last". Seemed to me that we will probably have different code areas registering callbacks, and one might require it go first (the default "abort" will always require it go last). So you can append and prepend, or go first. Note that only one registration can declare itself "first" or "last", and since the default "abort" callback automatically takes "last", that one isn't available. :-)
The errhandler callback function passes an opal_pointer_array of structs, each of which contains the name of the proc involved (which can be yourself for internal errors) and the error code. This is a change from the current fault callback which returned an opal_pointer_array of just process names. Rationale is that you might need to see the cause of the error to decide what action to take. I realize that isn't a requirement for remote procs, but remember that we will use the SAME interface to report RTE errors internal to the proc itself. In those cases, you really do need to see the error code. It is legal to pass a NULL for the pointer array (e.g., when reporting an internal failure without error code), so handlers must be prepared for that possibility. If people find that too burdensome, we can remove it.
Should we ever decide to create a separate callback path for internal errors vs remote process failures, or if we decide to do something different based on experience, then we can adjust this API.
This commit was SVN r28852.
All builds since r28682 configured with '--without-hwloc' fail at "make"
time without this fix.
Reviewed by rhc@
This commit was SVN r28769.
The following SVN revision numbers were found above:
r28682 --> open-mpi/ompi@446e33a5d8
To resolve this situation, add the ability to specify a backend topology file that mpirun shall use for its mapping operations. Create a new "set_topology" function in opal hwloc to support it.
This commit was SVN r28682.
- orte_debugger_init_after_spawn was not being called for debuggers that
use the MPIR_attach_fifo to co-locate debugger daemons.
- MPIR_Breakpoint was not getting called if a debugger reattached. Add
a job state (ORTE_JOB_STATE_DEBUGGER_DETACH) to reset mpir_breakpoint_fired
to false when a debugger detaches to ensure MPIR_Breakpoint is called if
another debugger attaches. Tested with STAT 2.0/launchmon 1.0.
cmr:v1.7
This commit was SVN r28665.
There is no good way to recover from this scenario, and from past experience, using the user's name in the session directory (as opposed to the uid) is very helpful when things go wrong. So print a help message when this happens (it is extremely rare, but has happened at least once now) and return an error.
cmr:v1.7.3,reviewer=jsquyres
cmr:v1.6.5,reviewer=jsquyres
This commit was SVN r28658.
some relevant updates/new functionality in the opal/mca/hwloc and
orte/mca/rmaps bases. This work was mainly developed by Mellanox,
with a bunch of advice from Ralph Castain, and some minor advice from
Brice Goglin and Jeff Squyres.
Even though this is mainly Mellanox's work, Jeff is committing only
for logistical reasons (he holds the hg+svn combo tree, and can
therefore commit it directly back to SVN).
-----
Implemented distance-based mapping algorithm as a new "mindist"
component in the rmaps framework. It allows mapping processes by NUMA
due to PCI locality information as reported by the BIOS - from the
closest to device to furthest.
To use this algorithm, specify:
{{{mpirun --map-by dist:<device_name>}}}
where <device_name> can be mlx5_0, ib0, etc.
There are two modes provided:
1. bynode: load-balancing across nodes
1. byslot: go through slots sequentially (i.e., the first nodes are
more loaded)
These options are regulated by the optional ''span'' modifier; the
command line parameter looks like:
{{{mpirun --map-by dist:<device_name>,span}}}
So, for example, if there are 2 nodes, each with 8 cores, and we'd
like to run 10 processes, the mindist algorithm will place 8 processes
to the first node and 2 to the second by default. But if you want to
place 5 processes to each node, you can add a span modifier in your
command line to do that.
If there are two NUMA nodes on the node, each with 4 cores, and we run
6 processes, the mindist algorithm will try to find the NUMA closest
to the specified device, and if successful, it will place 4 processes
on that NUMA but leaving the remaining two to the next NUMA node.
You can also specify the number of cpus per MPI process. This option
is handled so that we map as many processes to the closest NUMA as we
can (number of available processors at the NUMA divided by number of
cpus per rank) and then go on with the next closest NUMA.
The default binding option for this mapping is bind-to-numa. It works
if you don't specify any binding policy. But if you specified binding
level that was "lower" than NUMA (i.e hwthread, core, socket) it would
bind to whatever level you specify.
This commit was SVN r28552.
functions will now show_help() their own error messages if something
goes wrong (per r28470).
This commit was SVN r28471.
The following SVN revision numbers were found above:
r28470 --> open-mpi/ompi@2ff95a7739
many, many MTT timeouts when running jobs under SLURM: send the right
command at the end to cause remote orteds to shut down.
This commit was SVN r28438.
Provide some nice error messages if we fail to set the limits. Since the user had to specifically request we set the limit, treat failure as an error-out situation.
This commit was SVN r28288.
Notes:
- This commit also eliminates the need for an available components list in use
in several frameworks. None of the code in question was making use of the
priority field of the priority component list item so these extra lists were
removed.
- Cleaned up selection code in several frameworks to sort lists using opal_list_sort.
- Cleans up the ompi/orte-info functions. Expose the functions that construct the
list of params so they can be used elsewhere.
patches for mtl/portals4 from brian
missed a few output variables in openib
This commit was SVN r28241.
Features:
- Support for an override parameter file (openmpi-mca-param-override.conf).
Variable values in this file can not be overridden by any file or environment
value.
- Support for boolean, unsigned, and unsigned long long variables.
- Support for true/false values.
- Support for enumerations on integer variables.
- Support for MPIT scope, verbosity, and binding.
- Support for command line source.
- Support for setting variable source via the environment using
OMPI_MCA_SOURCE_<var name>=source (either command or file:filename)
- Cleaner API.
- Support for variable groups (equivalent to MPIT categories).
Notes:
- Variables must be created with a backing store (char **, int *, or bool *)
that must live at least as long as the variable.
- Creating a variable with the MCA_BASE_VAR_FLAG_SETTABLE enables the use of
mca_base_var_set_value() to change the value.
- String values are duplicated when the variable is registered. It is up to
the caller to free the original value if necessary. The new value will be
freed by the mca_base_var system and must not be freed by the user.
- Variables with constant scope may not be settable.
- Variable groups (and all associated variables) are deregistered when the
component is closed or the component repository item is freed. This
prevents a segmentation fault from accessing a variable after its component
is unloaded.
- After some discussion we decided we should remove the automatic registration
of component priority variables. Few component actually made use of this
feature.
- The enumerator interface was updated to be general enough to handle
future uses of the interface.
- The code to generate ompi_info output has been moved into the MCA variable
system. See mca_base_var_dump().
opal: update core and components to mca_base_var system
orte: update core and components to mca_base_var system
ompi: update core and components to mca_base_var system
This commit also modifies the rmaps framework. The following variables were
moved from ppr and lama: rmaps_base_pernode, rmaps_base_n_pernode,
rmaps_base_n_persocket. Both lama and ppr create synonyms for these variables.
This commit was SVN r28236.
\0-terminated so that strlen() and strstr() can be used without fear.
Also fix some insignificant mem leaks (which is somewhat moot, because
as soon as we leave those error conditions, the process will be
terminating, but what the heck, might as well fix these while I was in
the file for the \0-termination issue...).
This commit was SVN r28199.
A few changes were required to support this move:
1. the PMI component used to identify rte-related data (e.g., host name, bind level) and package them as a unit to reduce the number of PMI keys. This code was moved up to the ORTE layer as the OPAL layer has no understanding of these concepts. In addition, the component locally stored data based on process jobid/vpid - this could no longer be supported (see below for the solution).
2. the hash component was updated to use the new opal_identifier_t instead of orte_process_name_t as its index for storing data in the hash tables. Previously, we did a hash on the vpid and stored the data in a 32-bit hash table. In the revised system, we don't see a separate "vpid" field - we only have a 64-bit opaque value. The orte_process_name_t hash turned out to do nothing useful, so we now store the data in a 64-bit hash table. Preliminary tests didn't show any identifiable change in behavior or performance, but we'll have to see if a move back to the 32-bit table is required at some later time.
3. the db framework was a "select one" system. However, since the PMI component could no longer use its internal storage system, the framework has now been changed to a "select many" mode of operation. This allows the hash component to handle all internal storage, while the PMI component only handles pushing/pulling things from the PMI system. This was something we had planned for some time - when fetching data, we first check internal storage to see if we already have it, and then automatically go to the global system to look for it if we don't. Accordingly, the framework was provided with a custom query function used during "select" that lets you seperately specify the "store" and "fetch" ordering.
4. the ORTE grpcomm and ess/pmi components, and the nidmap code, were updated to work with the new db framework and to specify internal/global storage options.
No changes were made to the MPI layer, except for modifying the ORTE component of the OMPI/rte framework to support the new db framework.
This commit was SVN r28112.
* Add a little more description of what rankfiles are
* Update that we use logical numbering for socket:core notation
* Mention +nX notation
This commit was SVN r28067.
* Clean up ${includedir} and ${libdir} for script wrapper compilers
* Update script wrapper compilers to work like the C wrapper compilers w.r.t static and dynamic linking
* Remove the ORTE script wrapper compilers since they didn't support the ${includedir} stuff and Ralph said they weren't used anymore.
This commit was SVN r28052.
flags, and mca flags are kept seperate until the very end. The main configure
wrapper flags should now be modified by using the OPAL_WRAPPER_FLAGS_ADD
macro. MCA components should either let <framework>_<component>_{LIBS,LDFLAGS}
be copied over OR set <framework>_<component>_WRAPPER_EXTRA_{LIBS,LDFLAGS}.
The situations in which WRAPPER CPPFLAGS can be set by MCA components was
made very small to match the one use case where it makes sense.
This commit was SVN r27950.
Add hooks for supporting dynamic allocation and deallocation to support application-driven requests and fault recovery operations.
This commit was SVN r27879.
config/ directory. We split them apart a while ago in the hopes that
it would simplify things, but it didn't really (e.g., because there
were still some ompi/opal .m4 files in the top-level config/
directory, resulting in developer confusion where any given m4 macro
was defined).
So this commit consolidates them back into the top-level directory for
simplicity.
There's still (at least) two changes that would be nice to make:
1. Split any generated .m4 file (e.g., autogen-generated .m4 files)
into a separate directory somewhere so that a top-level -Iconfig/
will only get our explicitly defined macros, not the autogen stuff
(e.g., with libevent2019 needing to get the visibility macro, but
NOT all the autogen-generated inclusion of component configure.m4
files).
1. Change configure to be of the form:
{{{
# ...a small amount of preamble/setup...
OPAL_SETUP
m4_ifdef([project_orte], [ORTE_SETUP])
m4_ifdef([project_ompi], [OMPI_SETUP])
# ...a small amount of finishing stuff...
}}}
I doubt we'll ever get anything as clean as that, but that would be
the goal to shoot for.
This commit was SVN r27704.
Fix bug reported by FreyGuy19713: in cases where HNP node has multiple entries in a hostfile or other allocation, we need to track the total slots allocated to that node.
This commit was SVN r27673.
The following Trac tickets were found above:
Ticket 3429 --> https://svn.open-mpi.org/trac/ompi/ticket/3429
* Add some comments in the *-wrapper-data-txt.in files just so that
someone doesn't forget in the future why we link in what we do in
the MPI and ORTE wrapper compilers.
* Update ompi_wrapper_script.in to match the new behavior.
* Update orte_wrapper_script.in to support --openmpi:linkall (which
is a no-op in this case)
This commit was SVN r27672.
The following Trac tickets were found above:
Ticket 3422 --> https://svn.open-mpi.org/trac/ompi/ticket/3422
additional functionality. Rationale (refs trac:3422):
* Normal MPI applications only ever use the MPI API. Hence, -lmpi is
sufficient (they'll never directly call ORTE or OPAL
functions). This is arguably the most common case.
* That being said, we do have some test programs (e.g., those in
orte/test/mpi) that call MPI functions but also call ORTE/OPAL
functions. I've also written the occasional MPI test program that
calls opal_output, for example (there even might be a few tests in
the IBM test suite that directly call ORTE/OPAL functions).
* Even though this is not a common case, these applications should
also compile/link with mpicc.
* So we should add a --openmpi:linkall option that will also link
in whatever is necessary to call ORTE/OPAL functions
* Yes, we could hard-code "-lopen-rte -lopen-pal" in Makefiles, but
we do reserve the right to change those library names and/or add
others someday, so it's better to abstract out the names and let
the wrapper supply whatever is necessary.
* ORTE programs, however, are different. They almost always call OPAL
functions (e.g., if they want to send a message, they must use the
OPAL DSS). As such, it seems like the ORTE programs should always
link in OPAL.
Therefore:
* Add undocumented --openmpi:linkall flag to the wrapper compilers.
See the comment in opal_wrapper.c for an explanation of what it
does. This flag is only intended for Open MPI developers -- not
end users. That's why it's undocumented.
* Update orte/test/mpi/Makefile.am to add --openmpi:linkall
* Make ortecc/ortec++'s wrapper data text files always explicitly
link in libopen-pal
This commit was SVN r27670.
The following SVN revision numbers were found above:
r27668 --> open-mpi/ompi@cf845897aa
The following Trac tickets were found above:
Ticket 3422 --> https://svn.open-mpi.org/trac/ompi/ticket/3422
1. Restore libopen-pal.la, libopen-rte.la, and libmpi.la to be
separate entities (i.e., don't have libopen-rte.la include
libopen-pal.la, and don't have libmpi.la include libopen-pal.la).
Yay!
1. Consequently, make the wrapper compilers look for flags indicating
that the user wants to compile statically (currently: -static,
!--static, -Bstatic, and "-Wl," in front of all of those). If it
is, follow a 6-way matrix for determinining which libraries to
list on the underlying command line.
1. To support that, add the name of a token static and dynamic
library to look for in each of the wrapper compiler data files.
1. Fix a long-standing typo in the opalcc wrapper data file.
This commit was SVN r27662.
Reasoning: The old behavior was a little confusing. mca_base_components_open does not open an output stream so it is a little unexpected that mca_base_components_close does. To add to this several frameworks (that don't use mca_base_components_close) failed to close their output in the framework close function and others closed their output a second time. This change is an improvement to the symantics of mca_base_components_open/close as they are now symetric in their functionality.
This commit was SVN r27570.
It appears the problem was not with the command line parser but the rsh plm. I don't know why this problem was not occuring before the command line parser changes but it appears to be resolved now.
This commit was SVN r27527.
The following SVN revision numbers were found above:
r27451 --> open-mpi/ompi@d59034e6ef
r27456 --> open-mpi/ompi@ecdbf34937
ompi/mca/sbgp/basesmsocket
orte/mca/rmaps/lama
Remove stale configure.params files from the sbgp framework as the OMPI build system no longer looks at those files.
This commit was SVN r27377.
debruijn when launching fewer processes than are actually available within an
allocation. When this is fixed, please revert this change.
This commit was SVN r27376.
This now results in the procs being bound within their assigned location. It also causes us to use only the 0th HT on a core unless --use-hwthread-cpus has been specified (in which case, we use all the HTs in a core). Bind to core binds you to all HTs regardless - the --use-hwthread-cpus only impacts the oversubscribed determination and when binding to HT.
cmr:v1.7
This commit was SVN r27342.
As a secondary cleanup, the HNP doesn't need to update its nidmap during an xcast as it already has an up-to-date picture of the situation. So just dump that data and move along.
This commit was SVN r27318.
We ran into a case where the OMPI SVN trunk grew a new acceptable MCA
parameter value, but this new value was not accepted on the v1.6
branch (hwloc_base_mem_bind_failure_action -- on the trunk it accepts
the value "silent", but on the older v1.6 branch, it doesn't). If you
set "hwloc_base_mem_bind_failure_action=silent" in the default MCA
params file and then accidentally ran with the v1.6 branch, every OMPI
executable (including ompi_info) just failed because hwloc_base_open()
would say "hey, 'silent' is not a valid value for
hwloc_base_mem_bind_failure_action!". Kaboom.
The only problem is that it didn't give you any indication of where
this value was being set. Quite maddening, from a user perspective.
So we changed the ompi_info handles this case. If any framework open
function return OMPI_ERR_BAD_PARAM (either because its base MCA params
got a bad value or because one of its component register/open
functions return OMPI_ERR_BAD_PARAM), ompi_info will stop, print out
a warning that it received and error, and then dump out the parameters
that it has received so far in the framework that had a problem.
At a minimum, this will show the user the MCA param that had an error
(it's usually the last one), and ''where it was set from'' (so that
they can go fix it).
We updated ompi_info to check for O???_ERR_BAD_PARAM from each from
the framework opens. Also updated the doxygen docs in mca.h for this
O???_BAD_PARAM behavior. And we noticed that mca.h had MCA_SUCCESS
and MCA_ERR_??? codes. Why? I think we used them in exactly one
place in the code base (mca_base_components_open.c). So we deleted
those and just used the normal OPAL_* codes instead.
While we were doing this, we also cleaned up a little memory
management during ompi_info/orte-info/opal-info finalization.
Valgrind still reports a truckload of memory still in use at ompi_info
termination, but they mostly look to be components not freeing
memory/resources properly (and outside the scope of this fix).
This commit was SVN r27306.
The following Trac tickets were found above:
Ticket 3275 --> https://svn.open-mpi.org/trac/ompi/ticket/3275
If orte_sstore_base_global_snapshot_ref is null, then it will default appropriately when it is used. When prelaunching we always specify this parameter, but if we are not prelaunching it is possible to allow this to be null and it will initialize when used. However we setup the prelaunching variable in both situtations and in the latter that would result in a NULL reference. This patch protects that code segment.
This commit was SVN r27289.
So (finally) consolidate these two fields into one "slots" field. Add a field in orte_job_t to indicate when all the procs for a job will be launched together, so that staged operations can know when MPI operations are allowed.
This commit was SVN r27239.
For those nodes (and *only* those nodes) where the user does *not* specify a slot count, we will set the number of slots according to their direction: either to the number of cores, numas, sockets, or hwthreads. Otherwise, the slot count is set to 1.
Note that the default behavior remains unchanged: in the absence of any value for #slots, and in the absence of any directive to set #slots, we will set #slots=1.
This commit was SVN r27236.
1. if a hostfile is given, then add the nodes found in that hostfile to our list - i.e., the resulting allocation contains the UNION of all nodes specified in hostfiles from across all apps.
2. any app that has no hostfile but has a dash-host, will have those nodes added to the list
3. any app that fails to have a hostfile or a dash-host will be given the default hostfile, if we have it
Each app will subsequently be filtered using their hostfile and/or dash-host data to ensure that the app only has access to the hosts it specified
Note that any relative node syntax found in the hostfiles or dash-host data will generate an error in this scenario, so only non-relative syntax can be present
This commit was SVN r27223.
First revision of the Locatation Aware Mapping Algorithm (LAMA) RMAPS
component. This component is used to effect many different types of
regular of process/processor affinity patterns. Although quite
flexible in the patterns that it provides, it is ''not'' a
fully-arbitrary, rankfile-like solution for process/processor
affinity.
Inspiried by !BlueGene-like network specifications, LAMA has a core
algorithm that is quite good at specifying regular patterns in
multiple "dimensions" (where "dimensions" are expressed in terms of
different hardware elements: processor hardware threads, cores,
sockets, ...etc.). The LAMA core algorithm is described here:
http://www.open-mpi.org/papers/cluster-2011-lama/
= LAMA Usage Levels =
LAMA allows specifying affinity multiple different ways:
1. None: Speciying no affinity options to mpirun results in exactly
the same behavior as today: no affinity is used.
1. Simple: Using the mpirun options "--bind-to <WIDTH>" and "--map-to
<LEVEL>" to indicate how "wide" each process should be bound
(i.e., bind to a processor core, or to a processor socket, etc.)
and how to lay out the processes (i.e., round robin by cores,
sockets, etc.).
1. Expert: Using four new MCA parameters to effect process mapping
and binding to processors. These options are a bit complex, and
are not for the faint at heart, but offer a high degree of
(regular pattern) flexibility (each of these are described more
fully below):
* rmaps_lama_map: a sequence of characters describing how to lay
out processes
* rmaps_lama_bind: a sequence of characters describing the
resources to bind to each process
* rmaps_lama_mppr: a sequence of characters describing the maximum
number of processes to allow per resource (i.e., a specific
definition of "oversubscription")
* rmaps_lama_ordering: once all processes are in place, how to
order the ranks in MPI_COMM_WORLD
We anticipate that most users will utilize the "None" and "Simple"
levels of affinity, and they continue to work just as they do with the
v1.6 series and SVN trunk.
The Expert level was designed for two purposes:
1. To provide a precise definition for the "Simple" level (i.e.,
every
--bind-to/--map-by option in the "Simple" level has a
corresponding
precise specification in the "Expert" level)
1. As modern computing platforms become more complex, we simply
cannot predict what application developers will need in terms of
processor affinity. LAMA is an attempt to provide a highly
flexible mechanism that allows applications to utilize a variety
of complex, unique affinity patterns beyond the common "bind to
core" and "bind to socket" patterns.
= LAMA Simple Level =
The "Simple" level is pretty much the same as what Open MPI has
offered for years. It supports the same --bind-to and --map-by
options that Open MPI has supported for a while, but expands their
scope a bit.
Specifically, the following options are available for both --bind-to
and --map-by:
* slot
* hwthread
* core
* l1cache
* l2cache
* l3cache
* socket
* numa
* board
* node
= LAMA Expert Level =
The "Expert" level requires some explanation. I'll repeat my
disclaimer here: the LAMA Expert level is not for the meek. It is
flexible, but complex. '''Most users won't need the Expert level.'''
LAMA works in three phases: mapping, binding, and ordering. Each is
described below.
== Expert: Mapping ==
Processes are paired with sets of resources. For example, each
process may be paired with a single processor core. Or each process
may be paired with an entire processor socket. LAMA performs this
mapping, obeying the Max Processes Per Resource ("MPPR", pronounced
"mipper") limits. More on MPPR, below.
Mapping can be performed across multiple hardware levels:
* h: Hardware thread
* c: Processor core
* s: Processor socket
* L1: L1 cache
* L2: L2 cache
* L3: L3 cache
* N: NUMA node
* b: Processor board
* n: Server node
If the act of mapping is that of pairing MPI processes to the
resources that have been allocated to a job, one can easily imagine
looping through all the resources and assigning processes to them.
But to effect different process process layout patterns across those
resources, one may want to loop over those resources ''in a different
order.'' That is, if the above-mentioned nine hardware resources
(hardware thread, processor core, etc.) can be thought of as an
nine-dimensional space, you can imagine nine nested loops to traverse
all of them. And you can imagine that changing the order of nesting
would change the traversal pattern.
LAMA accepts a sequence of tokens representing the above-mentioned
nine hardware resources to specify the order of looping when mapping
resources to processes.
For example, consider a "simple" traversal: csL1L2L3Nbnh. Reading
that sequence of letters from left-to-right, it specifies mapping by
processor core, processor socket, L1 cache, L2 cache, L3 cache, NUMA
node, processor board, server node, and finally hardware thread.
Wait... what? That string specifies resources from "smallest" to
"largest" -- with the exception of hardware threads. Why are they
tacked on to the end?
In short, this string of letters means "map by round robin by core" --
(indeed, it exactly corresponds to the Simple level "--map-by core").
Specifically, LAMA traverses the string from left-to-right and maps
processes to all the resources indicated by that token (e.g., "c" for
processor core). When there are no more resources indicated by that
token, it goes on to the next token.
Hence, in this case, LAMA will map the first process to the first
core, then it will map the second process to the second core, and so
on.
Once all the cores are exhausted, LAMA effectively ignores all the
other letters until "h" (because all the other resources are made up
of cores; when cores are exhausted, those resources are exhausted,
too).
If there are still more processes to be mapped, LAMA will then
traverse all the hyperthreads -- meaning that the next process will be
mapped to the second hyperthread on the first core. And the next
process will be mapped to the second hyperthread on the second core.
And so on.
Keep in mind that the cores involved may span many server nodes; we're
not just talking about the cores (etc.) in a single machine.
As another example, the sequence "sL1L2L3Nbnch" is exactly equivalent
to "--map-by socket" (i.e., LAMA maps the first process to the first
socket, the second process to the second socket, and so on).
The sequence of letter can be combined in many, many different ways to
produce many different regular mapping patterns.
=== Max Processes Per Resource (MPPR) ===
The MPPR is an expression that precisely defines the maximum number of
processes that can be mapped to any single resource. In effect, it
defines the concept of "oversubscription." Specifically, traditional
HPC wisdom is that "oversubscription" is when there is more than one
MPI process per processor core.
This conventional defintion is expressed in a MPPR string of "1:c"
(one process per core).
But what if your MPI processes are multi-threaded, and they need
multiple processes per core? You'd need a different description of
"oversubscription" in this case. Perhaps you want to have one MPI
process per socket. This would be expressed in a MPPR string of
"1:s".
The general form of an individual MPPR specification is an integer
follow by a colon, followed by any of the tokens from mapping can be
used in the MPPR specification. For example "1:c" is pronounced "one
process per core."
Multiple MPPR specifications can be strung together into a
comma-delimited list, too. All of these MPPR values and then taken
into account when mapping. Here's some examples:
* 1:c -- allow, at most, one process per processor core (i.e., don't
schedule by hyperthread)
* 1:s -- allow, at most, one process per processor socket (e.g.,
that process may be multithreaded, or wants exclusive use of the
socket's caches)
* 1:s,2:n -- only allow one process per processor socket, but, at
most, two processes per server node (e.g., if the two MPI processes
will consume all the RAM on the server node, even if there are more
processor cores available)
If mapping all processes to resources would exceed a MPPR limit, this
job is ruled to be oversubscribed. If --oversubscribe was specified
on the mpirun command line, the job continues. Otherwise, LAMA will
abort the job.
Additionally, if --oversubscribe is specified, LAMA will endlessly
cycle through the mapping token string untill all processes have been
mapped.
== Expert: Binding ==
Once processes have been paired with resources during the Mapping
stage, they are optionally bound to a (potentially different) set of
resources. For example, processes may be mapped round robin by
processor socket, but bound to an individual processor core.
To be clear: if binding is not used, then mapping is effectively
reduced to "counting how many processes end up on each server node."
Without binding, there's no enforcement that a process will stay where
LAMA thinks it was placed.
With binding, however, processes are bound to a set of hardware
threads. The number of threads to which the process is bound is
sometimes referred to as the "binding width". For example, if a
process is bound to all the hardware threads in a processor socket,
its "width" is the processor socket.
(note that we specifically do not say that the hardware threads are
sequential, even if they are all within a single resource such as a
processor core or socket. BIOS ordering of hardware threads can be
wonky; so we only refer to "sets of hardware threads")
Bindings are expressed as an integer and a token from the mapping
string. For example "1s" means "bind each process to one processor
socket" (there is no ":" in the binding string because the ":" is
pronounced as "per" when reading the MPPR string).
Note that it only makes sense to bind processes to a single resource
specification (unlike the MPPR specification, where multiple limits
can be specified).
== Expert: Ordering ==
Finally, processes are assigned a rank in MPI_COMM_WORLD. LAMA
currently offers two ordering modes: sequential or natural:
* Sequential: if you laid out all the hardware resources in a single
line, and then overlaid all the MPI processes on top of them, they
are ordered from 0 to (N-1) from left-to-right.
* Natural: the ordering of ranks follows the mapping ordering. For
example, consider a server node with two processor sockets, each
containing four cores. The command line "mpirun -np 8 --bind-to
core --map-by socket --order n a.out" would result in MCW ranks
that look like this: [0 2 4 6] [1 3 5 7].
= Execution =
At this point, the job is fully mapped, optionally bound, and its
ranks in MPI_COMM_WORLD are ordered. It now starts its execution.
= Final Notes =
Note that at this point, lama is not the default mapper. It must be
activiated with "--mca rmaps lama". We'll continue to do further
testing and comparitive analysis with the current set of ORTE mappers.
Also, note that the LAMA algorithm can handle heterogeneity between
hardware resources (e.g., an MPI job spanning server nodes with
differing numbers of processor sockets). For lack of a longer
explanation (this commit message already long enough!), LAMA considers
each server node individually during mapping and binding.
See the LAMA paper for more details:
http://www.open-mpi.org/papers/cluster-2011-lama/
This commit was SVN r27206.
Remove some stale configure.m4's we no longer need.
Optimize the nidmaps a bit by only sending info that has changed each time, instead of sending a complete copy of everything. Makes no difference for the typical MPI job - only impacts things like staged execution where we are sending multiple (possibly many) launch messages.
This commit was SVN r27165.
following:
* Provides a fixed number of resource slots (i.e., "hotel rooms").
* Allows one thing to occupy a resource slot at a time (i.e., each
hotel room can have an occupant check in to that room).
* Resource slots can be vacated at any time (i.e., occupants can
voluntarily check out of their hotel room).
* Resource slots can be occupied for a specific maximum amount of
time. If that time expires, the occupant is forcibly evicted and
the upper layer is notified via (libevent) callback (i.e., the maid
will kick an occupant of out of their room when their reservation
is over).
This class can be to be used for things like retransmission schemes
for unreliable transports. For example, a message sent on an
unreliable transport can be checked in to a hotel room. If an ACK for
that message is received, the message can be checked out. But if the
ACK is never received, the message will eventually be evicted from its
room and the upper layer will be notified that the message failed to
check out in time (i.e., that an ACK for that message was not received
in time).
Code using this class is currently being developed off-trunk, but will
be coming to SVN soon.
This commit was SVN r27067.
