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.
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/2014/05/14822.php
Revamp the ORTE global data structures to reduce memory footprint and add new features. Add ability to control/set cpu frequency, though this can only be done if the sys admin has setup the system to support it (or you run as root).
This commit was SVN r31916.
mca_base_var_register (..., MCA_BASE_VAR_TYPE_STRING, ...)
will dup() the orte_set_slots string, so there is no need
to do this in the first place.
cmr=v1.8.2:reviewer=rhc
This commit was SVN r31773.
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.
The problem arises when a hostfile is used, and the user provides host names without specifying the slots= paramater. In these cases, we assign slots=1, but automatically allow oversubscription since that number isn't confirmed. We then provide a separate parameter by which the user can direct that we assign the number of slots based on the sensed hardware - e.g., by telling us to set the #slots equal to the #cores on each node. However, this has been set to "off" by default.
In order to make this a little less complex for the user, set the default such that we automatically set #slots equal to #cores (or #hwt's if use_hwthreads_as_cpus has been set) only for those cases where the user provides names in a hostfile but does not provide slot information.
Also cleanup some a couple of issues in the mapping/binding system:
* ensure we only override the binding directive if we are oversubscribed *and* overload is not allowed
* ensure that the MPI procs don't attempt to bind themselves if they are launched by an orted as any binding directive (no matter what it was) would have been serviced by the orted on launch
* minor cleanup to the warning message when oversubscribed and binding was requested
cmr=v1.7.5:reviewer=rhc:subject=update mapping/binding system
This commit was SVN r30909.
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.
Thanks to Tim Miller for reporting the regression from the 1.6 series
cmr=v1.7.4:reviewer=jsquyres:subject=Ensure that comm_spawn'd procs get user-specified forwarded envars
This commit was SVN r30012.
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.
Resolves problems in loop_spawn where the timer was incorrectly firing and killing the overall job.
cmr=v1.7.4:reviewer=hjelmn
This commit was SVN r29661.
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.
So we now allow singletons to start on their own, only spawning an HNP when initiating an operation that actually requires it.
cmr:v1.7.4:reviewer=jsquyres
This commit was SVN r29354.
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.
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.
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.
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 hooks for supporting dynamic allocation and deallocation to support application-driven requests and fault recovery operations.
This commit was SVN r27879.
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
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.
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.
"num_app_ctx" - the number of app_contexts in the job
"first_rank" - the MPI rank of the first process in each app_context
"np" - the number of procs in each app_context
Still need clarification on the MPI_Init portion of the ticket. Specifically, does the ticket call for returning an error is someone calls MPI_Init more than once in a program? We set a flag to tell us that we have been initialized, but currently never check it.
This commit was SVN r27005.
