Bring Slurm PMI-1 component online
Bring the s2 component online
Little cleanup - let the various PMIx modules set the process name during init, and then just raise it up to the ORTE level. Required as the different PMI environments all pass the jobid in different ways.
Bring the OMPI pubsub/pmi component online
Get comm_spawn working again
Ensure we always provide a cpuset, even if it is NULL
pmix/cray: adjust cray pmix component for pmix
Make changes so cray pmix can work within the integrated
ompi/pmix framework.
Bring singletons back online. Implement the comm_spawn operation using pmix - not tested yet
Cleanup comm_spawn - procs now starting, error in connect_accept
Complete integration
We recognize that this means other users of OPAL will need to "wrap" the opal_process_name_t if they desire to abstract it in some fashion. This is regrettable, and we are looking at possible alternatives that might mitigate that requirement. Meantime, however, we have to put the needs of the OMPI community first, and are taking this step to restore hetero and SPARC support.
These two macros set the prefix for the OPAL and ORTE libraries,
respectively. Specifically, the OPAL library will be named
libPREFIXopen-pal.la and the ORTE library will be named
libPREFIXopen-rte.la.
These macros must be called, even if the prefix argument is empty.
The intent is that Open MPI will call these macros with an empty
prefix, but other projects (such as ORCM) will call these macros with
a non-empty prefix. For example, ORCM libraries can be named
liborcm-open-pal.la and liborcm-open-rte.la.
This scheme is necessary to allow running Open MPI applications under
systems that use their own versions of ORTE and OPAL. For example,
when running MPI applications under ORTE, if the ORTE and OPAL
libraries between OMPI and ORCM are not identical (which, because they
are released at different times, are likely to be different), we need
to ensure that the OMPI applications link against their ORTE and OPAL
libraries, but the ORCM executables link against their ORTE and OPAL
libraries.
the OPAL and ORTE libraries. This is required by projects such as ORCM
that have their own ORTE and OPAL libraries in order to avoid library
confusion. By renaming their version of the libraries, the OMPI
applications can correctly dynamically load the correct one for their
build."
This reverts commit 63f619f871.
WHAT: Merge the PMIx branch into the devel repo, creating a new
OPAL “lmix” framework to abstract PMI support for all RTEs.
Replace the ORTE daemon-level collectives with a new PMIx
server and update the ORTE grpcomm framework to support
server-to-server collectives
WHY: We’ve had problems dealing with variations in PMI implementations,
and need to extend the existing PMI definitions to meet exascale
requirements.
WHEN: Mon, Aug 25
WHERE: https://github.com/rhc54/ompi-svn-mirror.git
Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.
All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.
Accordingly, we have:
* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.
* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.
* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint
* removed the prior OMPI/OPAL modex code
* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.
* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand
This commit was SVN r32570.
also replase the OMPI_CAST_RTE_NAME macro with
an inline function if OPAL_ENABLE_DEBUG, so we can
get warnings from the compiler if ampersand is missing.
Thanks to Paul Hargrove for reporting the bugs
This commit was SVN r32408.
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
We have been getting several requests for new collectives that need to be inserted in various places of the MPI layer, all in support of either checkpoint/restart or various research efforts. Until now, this would require that the collective id's be generated at launch. which required modification
s to ORTE and other places. We chose not to make collectives reusable as the race conditions associated with resetting collective counters are daunti
ng.
This commit extends the collective system to allow self-generation of collective id's that the daemons need to support, thereby allowing developers to request any number of collectives for their work. There is one restriction: RTE collectives must occur at the process level - i.e., we don't curren
tly have a way of tagging the collective to a specific thread. From the comment in the code:
* In order to allow scalable
* generation of collective id's, they are formed as:
*
* top 32-bits are the jobid of the procs involved in
* the collective. For collectives across multiple jobs
* (e.g., in a connect_accept), the daemon jobid will
* be used as the id will be issued by mpirun. This
* won't cause problems because daemons don't use the
* collective_id
*
* bottom 32-bits are a rolling counter that recycles
* when the max is hit. The daemon will cleanup each
* collective upon completion, so this means a job can
* never have more than 2**32 collectives going on at
* a time. If someone needs more than that - they've got
* a problem.
*
* Note that this means (for now) that RTE-level collectives
* cannot be done by individual threads - they must be
* done at the overall process level. This is required as
* there is no guaranteed ordering for the collective id's,
* and all the participants must agree on the id of the
* collective they are executing. So if thread A on one
* process asks for a collective id before thread B does,
* but B asks before A on another process, the collectives will
* be mixed and not result in the expected behavior. We may
* find a way to relax this requirement in the future by
* adding a thread context id to the jobid field (maybe taking the
* lower 16-bits of that field).
This commit includes a test program (orte/test/mpi/coll_test.c) that cycles 100 times across barrier and modex collectives.
This commit was SVN r32203.
http://www.open-mpi.org/community/lists/devel/2014/04/14496.php
Revamp the opal database framework, including renaming it to "dstore" to reflect that it isn't a "database". Move the "db" framework to ORTE for now, soon to move to ORCM
This commit was SVN r31557.
This allows compilers to know that the code path(s) where
ompi_rte_abort() is invoked won't return (and therefore won't warn in
certain cases).
cmr=v1.8:reviewer=rhc
This commit was SVN r30891.
NOTE: launch performance will be absolutely awful if you do this with BTLs that aren't configured to modex_recv on first message!
Even with "modex on demand", we still have to do a barrier in place of the modex - we simply don't move any data around, which does reduce the time impact. The barrier is required to ensure that the other proc has in fact registered all its BTL info and therefore is prepared to hand over a complete data package. Otherwise, you may not get the info you need. In addition, the shared memory BTL can fail to properly rendezvous as it expects the barrier to be in place.
This behavior will *only* take effect under the following conditions:
1. launched via mpirun
2. #procs is greater than ompi_hostname_cutoff, which defaults to UINT32_MAX
3. mca param rte_orte_direct_modex is set to 1. At the moment, we are having problems getting this param to register properly, so only the first two conditions are in effect. Still, the bottom line is you have to *want* this behavior to get it.
The planned next evolution of this will be to make the direct modex be non-blocking - this will require two fixes:
1. if the remote proc doesn't have the required info, then let it delay its response until it does. This means we need a way for the MPI layer to tell the RTE "I am done entering modex data".
2. adjust the SM rendezvous logic to loop until the required file has been created
Creating a placeholder to bring this over to 1.7.5 when ready.
cmr=v1.7.5:reviewer=hjelmn:subject=Enable direct modex at scale
This commit was SVN r30259.
pkg{data,lib,includedir}, use our own ompi{data,lib,includedir}, which is
always set to {datadir,libdir,includedir}/openmpi. This will keep us from
having help files in prefix/share/open-rte when building without Open MPI,
but in prefix/share/openmpi when building with Open MPI.
This commit was SVN r30140.
* automatically retrieve the hostname (and all RTE info) for all procs during MPI_Init if nprocs < cutoff
* if nprocs > cutoff, retrieve the hostname (and all RTE info) for a proc upon the first call to modex_recv for that proc. This would provide the hostname for debugging purposes as we only report errors on messages, and so we must have called modex_recv to get the endpoint info
* BTLs are not to call modex_recv until they need the endpoint info for first message - i.e., not during add_procs so we don't call it for every process in the job, but only those with whom we communicate
My understanding is that only some BTLs have been modified to meet that third requirement, but those include the Cray ones where jobs are big enough that launch times were becoming an issue. Other BTLs would hopefully be modified as time went on and interest in using them at scale arose. Meantime, those BTLs would call modex_recv on every proc, and we would therefore be no worse than the prior behavior.
This commit revises the MPI-RTE interface to pass the ompi_proc_t instead of the ompi_process_name_t for the proc so that the hostname can be easily inserted. I have advised the ORNL folks of the change.
cmr=v1.7.4:reviewer=jsquyres:subject=Fix thread deadlock
This commit was SVN r29931.
The following SVN revision numbers were found above:
r29917 --> open-mpi/ompi@1a972e2c9d
This isn't being used yet - just enabling Nathan to do what he needs.
***** NOTE: any use of the OMPI_DB_GLOBAL_RANK database key must be protected by #ifdef OMPI_DB_GLOBAL_RANK as not all RTE's will define this key. *****
This commit was SVN r29708.
This change contains a non-mandatory modification
of the MPI-RTE interface. Anyone wishing to support
coprocessors such as the Xeon Phi may wish to add
the required definition and underlying support
****************************************************************
Add locality support for coprocessors such as the Intel Xeon Phi.
Detecting that we are on a coprocessor inside of a host node isn't straightforward. There are no good "hooks" provided for programmatically detecting that "we are on a coprocessor running its own OS", and the ORTE daemon just thinks it is on another node. However, in order to properly use the Phi's public interface for MPI transport, it is necessary that the daemon detect that it is colocated with procs on the host.
So we have to split the locality to separately record "on the same host" vs "on the same board". We already have the board-level locality flag, but not quite enough flexibility to handle this use-case. Thus, do the following:
1. add OPAL_PROC_ON_HOST flag to indicate we share a host, but not necessarily the same board
2. modify OPAL_PROC_ON_NODE to indicate we share both a host AND the same board. Note that we have to modify the OPAL_PROC_ON_LOCAL_NODE macro to explicitly check both conditions
3. add support in opal/mca/hwloc/base/hwloc_base_util.c for the host to check for coprocessors, and for daemons to check to see if they are on a coprocessor. The former is done via hwloc, but support for the latter is not yet provided by hwloc. So the code for detecting we are on a coprocessor currently is Xeon Phi specific - hopefully, we will find more generic methods in the future.
4. modify the orted and the hnp startup so they check for coprocessors and to see if they are on a coprocessor, and have the orteds pass that info back in their callback message. Automatically detect that coprocessors have been found and identify which coprocessors are on which hosts. Note that this algo isn't scalable at the moment - this will hopefully be improved over time.
5. modify the ompi proc locality detection function to look for coprocessor host info IF the OMPI_RTE_HOST_ID database key has been defined. RTE's that choose not to provide this support do not have to do anything - the associated code will simply be ignored.
6. include some cleanup of the hwloc open/close code so it conforms to how we did things in other frameworks (e.g., having a single "frame" file instead of open/close). Also, fix the locality flags - e.g., being on the same node means you must also be on the same cluster/cu, so ensure those flags are also set.
cmr:v1.7.4:reviewer=hjelmn
This commit was SVN r29435.
Fix two problems that surfaced when using direct launch under SLURM:
1. locally store our own data because some BTLs want to retrieve
it during add_procs rather than use what they have internally
2. cleanup MPI_Abort so it correctly passes the error status all
the way down to the actual exit. When someone implemented the
"abort_peers" API, they left out the error status. So we lost
it at that point and *always* exited with a status of 1. This
forces a change to the API to include the status.
cmr:v1.7.3:reviewer=jsquyres:subject=Fix MPI_Abort and modex_recv for direct launch
This commit was SVN r29405.
Create a new required key in the OMPI layer for retrieving a "node id" from the database. ALL RTE'S MUST DEFINE THIS KEY. This allows us to compute locality in the MPI layer, which is necessary when we do things like intercomm_create.
cmr:v1.7.4:reviewer=rhc:subject=Cleanup handling of modex data
This commit was SVN r29274.
*** 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.
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.
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.
ompi_show_help, because opal_show_help is replaced with an
aggregating version when using ORTE, so there's no reason to
directly call orte_show_help.
This commit was SVN r28051.
