1
1
Граф коммитов

625 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
8f1b9b463e Fix shared memory operations - need to pass the local topology and cpusets of all local peers so we can properly compute relative locality for them. Also need to set default locality to "on node" in case where cpusets are not passed because procs are not bound.
This commit was SVN r32577.
2014-08-22 05:17:51 +00:00
Ralph Castain
aec5cd08bd Per the PMIx RFC:
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.
2014-08-21 18:56:47 +00:00
Gilles Gouaillardet
f24699623f check-help-strings cleanup
This commit was SVN r32495.
2014-08-11 03:25:22 +00:00
Ralph Castain
daeb9b6c4f Some more cleanups. Remove direct references to ORTE by changing OMPI_CAST_ORTE_NAME -> OMPI_CAST_RTE_NAME. Ensure that ORTE tools (mpirun, orted, tools) set the OPAL proc structure fields so OPAL knows what is going on and uses the correct print functions (still need to fix the problem for non-MPI apps). Properly return uint32_t from the opal utilities instead of int32_t as that is what the ORTE process name fields contain.
Thanks to Gilles for pointing out some of the discrepancies.

This commit was SVN r32398.
2014-08-01 14:44:11 +00:00
Ralph Castain
6c5e592785 Revert r32222, r32210, and r32203 as they created a problem when daemon collectives did not involve app procs on every node. Instead, modify the ompi/mca/rte/orte/rte_orte.h to add a new function that allows apps to request new daemon collective ids for use in barrier and modex operations. This will only appear in ORTE-based installations, but it is only being used by a couple of researchers at the moment.
Update the orte/test/mpi/coll_test.c test to show the revised example.

This commit was SVN r32234.

The following SVN revision numbers were found above:
  r32203 --> open-mpi/ompi@a523dba41d
  r32210 --> open-mpi/ompi@2ce11ed5c4
  r32222 --> open-mpi/ompi@d55f16db50
2014-07-15 03:48:00 +00:00
Ralph Castain
a523dba41d NOTE: this modifies the MPI-RTE interface
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.
2014-07-10 18:53:12 +00:00
Ralph Castain
356e7ea904 Move all collective id's into the attributes and let the job pack/unpack take care of them instead of singling them out. Add the envars just prior to forking the children instead of into the launch message itself. Remove a few #if CR as the attributes functionality can handle this condition now.
This commit was SVN r32133.
2014-07-03 15:58:13 +00:00
George Bosilca
2883adcdf3 Remove useless variables.
This commit was SVN r32123.
2014-07-03 00:30:54 +00:00
Ralph Castain
5216bd5558 Multiple sigchld reports can occur within a single event callback, so have to reap them until none remain. Also, need to ensure the daemon is flagged as alive prior to calling wait_cb
Refs trac:4717

This commit was SVN r32020.

The following Trac tickets were found above:
  Ticket 4717 --> https://svn.open-mpi.org/trac/ompi/ticket/4717
2014-06-17 18:46:40 +00:00
Ralph Castain
42bf7466fc This isn't as big a change as it appears - a change in one place caused a whole bunch of files to require updated #include's due to some arcane linkage. Rework the orte_wait code to reflect the introduction of the state machine. If we are in cleanup mode and just want to kill all our local children, then there is no reason to be polite about it as that introduces *very* long delays at scale. Just kill the procs and move on.
Refs trac:4717

This commit was SVN r32019.

The following Trac tickets were found above:
  Ticket 4717 --> https://svn.open-mpi.org/trac/ompi/ticket/4717
2014-06-17 17:57:51 +00:00
Ralph Castain
f1978fba7c Cleanup a set of typos on the orte_get_attribute call
This commit was SVN r31942.
2014-06-03 20:36:38 +00:00
Ralph Castain
742c0d2284 Fix typo that would cause a segfault if orte_startup_timeout was set
This commit was SVN r31929.
2014-06-02 15:59:18 +00:00
Ralph Castain
8736a1c138 Per RFC:
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.
2014-06-01 16:14:10 +00:00
Ralph Castain
1107f9099e Per the RFC issued here:
http://www.open-mpi.org/community/lists/devel/2014/05/14827.php

Refactor PMI support

This commit was SVN r31907.
2014-06-01 04:28:17 +00:00
Gilles Gouaillardet
5b9364fc12 Fix a memory leak in orte_register_params()
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.
2014-05-15 10:31:19 +00:00
Ralph Castain
aaae4841e9 Flush the show_help system on our way out - this also restores the opal_show_help function pointer to the OPAL layer for any subsequent processing.
cmr=v1.8.2:reviewer=jsquyres

This commit was SVN r31685.
2014-05-08 14:37:47 +00:00
Ralph Castain
5602156a1c Use the correct abstraction layer name for the data dirs
This commit was SVN r31684.
2014-05-08 14:32:24 +00:00
Ralph Castain
60c554e097 Ugh - protect that --display-devel print with some NULL checks
This commit was SVN r31604.
2014-05-02 14:28:45 +00:00
Ralph Castain
c7f55be387 Per a user request, add binding info to the simple --diplay-map option
This commit was SVN r31603.
2014-05-02 14:25:59 +00:00
Ralph Castain
c4c9bc1573 As per the RFC:
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.
2014-04-29 21:49:23 +00:00
Ralph Castain
50c30d62ca Repair builds without hwloc
cmr=v1.7.5:reviewer=jsquyres

This commit was SVN r30940.
2014-03-05 02:48:15 +00:00
Ralph Castain
0ac97761cc Now that we are binding by default, the issue of #slots and what to do when oversubscribed has become a bit more complicated. This isn't a problem in managed environments as we are always provided an accurate assignment for the #slots, or when -host is used to define the allocation since we automatically assume one slot for every time a node is named.
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.
2014-03-03 16:46:37 +00:00
Ralph Castain
c3df744a3b Shift the orte_db_localrank key to the opal level. Add the job and proc-level session directory names to the database using opal_db keys.
This commit was SVN r30746.
2014-02-17 01:40:56 +00:00
Ralph Castain
509d5d82b0 Add some verbage requested by Jeff, change the param level to something...?
Refs trac:4275

This commit was SVN r30736.

The following Trac tickets were found above:
  Ticket 4275 --> https://svn.open-mpi.org/trac/ompi/ticket/4275
2014-02-15 15:11:05 +00:00
Ralph Castain
449cd8f3d7 Update a couple of fields, add a scheduler field to proc_info
This commit was SVN r30718.
2014-02-13 23:30:04 +00:00
Ralph Castain
1d8c061687 Fix a race condition that could result in assert failures during finalize. Ensure we shutdown the orte progress thread prior to finalizing the rml/oob frameworks so that no async operations are executing during destruct of the base-level lists and objects.
cmr=v1.7.5:reviewer=jsquyres:subject=fix race condition in finalize

This commit was SVN r30641.
2014-02-08 22:04:19 +00:00
Adrian Reber
fde1040d2f Use unique collective ids for the checkpoint/restart code
This commit was SVN r30552.
2014-02-04 14:03:05 +00:00
Ralph Castain
193cceb483 Okay, since a certain other RM out there made a fuss about being able to lock their daemons to specified cores, offer the same option here. The MCA param orte_daemon_cores can be used to specify which core(s) you want the orte daemons to use. This will have no bearing on the application procs - unbound will remain unbound, and binding directives will be applied to the apps.
Yippee skippee...

This commit was SVN r30513.
2014-01-30 23:50:14 +00:00
Ralph Castain
80497d73cf Need to mark the daemon as alive so that exit commands are properly routed during abnormal terminations. Also, remove stale references to the "selected oob component" as we no longer require only one component be selected
cmr=v1.7.4:reviewer=jsquyres

This commit was SVN r30162.
2014-01-08 22:35:48 +00:00
Brian Barrett
8b778903d8 Fix longstanding issue with our multi-project support. Rather than using
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.
2014-01-07 22:11:15 +00:00
Ralph Castain
9c768df8b8 Resolve an unexpected behavior in hostfile allocations. Now that we filter allocations to determine what will be used for mapping, let the initial global pool be the union of nodes from all sources (default hostfile, hostfiles, and dash-hosts). Each app will filter down to only those specified for it using its own hostfile and dash-host options.
cmr=v1.7.4:reviewer=jsquyres:subject=Resolve an unexpected behavior in hostfile allocations

This commit was SVN r30040.
2013-12-21 01:38:27 +00:00
Ralph Castain
71b52fe861 Ensure that comm_spawn'd procs get user-specified forwarded envars
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.
2013-12-20 14:47:35 +00:00
Ralph Castain
d44e4a311f Per request from Dave Goodell, add support for MPIEXEC_TIMEOUT - if set in the environment, terminate the job after the specified number of seconds has passed. Equivalent to MPICH functionality.
cmr=v1.7.4:reviewer=dgoodell:subject=add support for MPIEXEC_TIMEOUT

This commit was SVN r29831.
2013-12-07 01:58:32 +00:00
Ralph Castain
7480beb7f0 Per request from Nathan, add an offset value to the job struct so we can construct a "global rank" that spans multiple jobs during dynamic launch operations. Store a new ORTE_DB_GLOBAL_RANK value for each process in the database, and ensure that we share our own value during connect_accept so both sides can see it.
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.
2013-11-14 17:01:43 +00:00
Ralph Castain
f1e510154c Revise the launch timeout detection so we don't mistakenly declare "failed to start". Recognize that timeout is at the per-job level, and define the timeout param as a total value instead of seconds/daemon as it otherwise can get to be an enormous (and useless) number.
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.
2013-11-11 23:50:40 +00:00
Ralph Castain
e35ad23176 Correctly compute usage for dynamic spawns when binding is invoked. Ensure we correctly account for existing process usage on each node when computing bindings during dynamic spawns.
cmr=v1.7.4:reviewer=hjelmn:subject=Correctly compute usage for dynamic spawns when binding is invoked

This commit was SVN r29649.
2013-11-10 00:38:01 +00:00
Ralph Castain
604970a1a2 Initialize orte_coprocessors hash table to NULL. Delay coprocessor detection on HNP until after node topology final definition in case rmaps changes it. Minor spacing change.
Refs trac:3847

This commit was SVN r29504.

The following Trac tickets were found above:
  Ticket 3847 --> https://svn.open-mpi.org/trac/ompi/ticket/3847
2013-10-24 00:08:47 +00:00
Ralph Castain
b12167abef Per a good suggestion from Jeff, make the coprocessor mapping more scalable by using a hash table to cache the coprocessor list, and then do a single pass thru the nodes at the end to assign hostid's.
Refs trac:3847

This commit was SVN r29439.

The following Trac tickets were found above:
  Ticket 3847 --> https://svn.open-mpi.org/trac/ompi/ticket/3847
2013-10-14 22:01:48 +00:00
Ralph Castain
24c811805f ****************************************************************
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.
2013-10-14 16:52:58 +00:00
Ralph Castain
f4f2287958 Singletons currently start out by spawning an HNP - this is required solely in the cases where the singleton subsequently calls MPI_Comm_spawn or publishes port info without support from an external orte-server. In all other cases, the HNP is of no value and can actually be a detriment by creating additional overhead on the node. This is particularly concerning for async operations where processes may begin as singletons and then dynamically wireup to perform pt2pt communications.
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.
2013-10-04 02:58:26 +00:00
Ralph Castain
d565a76814 Do some cleanup of the way we handle modex data. Identify data that needs to be shared with peers in my job vs data that needs to be shared with non-peers - no point in sharing extra data. When we share data with some process(es) from another job, we cannot know in advance what info they have or lack, so we have to share everything just in case. This limits the optimization we can do for things like comm_spawn.
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.
2013-09-27 00:37:49 +00:00
Ralph Castain
a200e4f865 As per the RFC, bring in the ORTE async progress code and the rewrite of OOB:
*** 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.
2013-08-22 16:37:40 +00:00
Ralph Castain
16c5b30a1f Since the calls to "PMI get" scale by number of procs (not nodes), it makes more sense to have the MCA param be the cutoff based on number of procs. Also, it occurred to me that this shouldn't impact the nidmap process as that is built and circulated when we launch via mpirun, not during direct launch.
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
2013-08-22 03:40:26 +00:00
Ralph Castain
45e695928f As per the email discussion, revise the sparse handling of hostnames so that we avoid potential infinite loops while allowing large-scale users to improve their startup time:
* 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.
2013-08-20 18:59:36 +00:00
Ralph Castain
bebe852057 Add new info key for publish that allows user to designate that the port is to be unique - i.e., to return an error if that service has already been published. Default is to overwrite
This commit was SVN r29028.
2013-08-14 04:21:17 +00:00
Nathan Hjelm
841ed962f6 fix MCA variable and component system leaks
cmr=v1.7.3:reviewer=rhc

This commit was SVN r29011.
2013-08-09 19:50:28 +00:00
Nathan Hjelm
ebbb32120a MCA/base: variable system updates
- Use an enumerator to handle bool values.

 - Fix a leak in the variable enumerator.

 - Fix a leak in an orte parameter.

This commit was SVN r28949.
2013-07-25 15:42:01 +00:00
Ralph Castain
563bf60fb8 Fix an ordering problem that crept in due to the change in MCA param system. One MCA param would set a value, and then we did a hard reset of that value before testing another MCA param, thus removing a critical value for proper operation of the first param.
cmr:v1.7.3:reviewer=brbarret

This commit was SVN r28788.
2013-07-14 16:22:13 +00:00
Jeff Squyres
b9ca8e3cd1 Tweaked the help message a bit (this is the end result of iterating on
the message in email between Mike, Ralph, Jeff).

Add this to CMR #3642 and #3643.

This commit was SVN r28662.
2013-06-20 13:19:23 +00:00
Ralph Castain
13665bffe8 Per an off-list discussion, it appears possible for a system to report failure when executing getpwuid. There are several reasons for this error to occur, most notably if the system uses a network-based authentication protocol (e.g., NIS) and that sytem gets overwhelmed when we launch on a lot of nodes.
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.
2013-06-20 04:30:42 +00:00
Jeff Squyres
089c632cce Remove a bunch of dead code: gcc 4.7 warns of set-but-unused
variables.  So get rid of them.

This commit was SVN r28538.
2013-05-17 21:45:49 +00:00
Ralph Castain
93ba4247f8 remove extra paren when --without-hwloc
This commit was SVN r28530.
2013-05-15 21:31:45 +00:00
Ralph Castain
5296099ecb Fix the cpus-per-rank when binding to hwthreads. Add cpus-per-rank to diag printout
Thanks to Elena for reporting the problem

This commit was SVN r28508.
2013-05-14 20:17:50 +00:00
Ralph Castain
27e3e382d5 No need for ORTE tools to use orte progress thread
This commit was SVN r28445.
2013-05-04 21:13:20 +00:00
Nathan Hjelm
bccf8c657a Per RFC add initial support for the MPI 3.0 tools interface.
Current MPI_T support:
  - Full cvar interface.
  - Full categories interface.
  - No pvar support at this time.

This commit was SVN r28376.
2013-04-24 15:59:23 +00:00
Ralph Castain
45af6cf59e The move of the orte_db framework to opal required that we create an opaque opal_identifier_t type as OPAL cannot know anything about the ORTE process name. However, passing a value down to opal and then having the db components reference it causes alignment issues on Solaris Sparc platforms. So pass the pointer instead and do the old "memcpy" trick to avoid the problem.
This commit was SVN r28308.
2013-04-08 23:34:16 +00:00
Ralph Castain
1b5b9afa85 Silence warnings
This commit was SVN r28244.
2013-03-27 21:56:46 +00:00
Nathan Hjelm
9d4a26f47d Update OMPI frameworks to use the MCA framework system.
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.
2013-03-27 21:17:31 +00:00
Nathan Hjelm
c041156f60 Update ORTE frameworks to use the MCA framework system.
This commit was SVN r28240.
2013-03-27 21:14:43 +00:00
Nathan Hjelm
cf377db823 MCA/base: Add new MCA variable system
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.
2013-03-27 21:09:41 +00:00
Ralph Castain
317915225c Finish the binding cleanup by removing the no-longer-used binding level scheme. This proved to be fallible as there is no guarantee that the hierarchy it used matched physical reality of the machine (e.g., is L3 "above" the socket or not). Still have to complete the ppr update, but get the rest of it correct.
This commit was SVN r28223.
2013-03-26 20:09:49 +00:00
Ralph Castain
6ee32767d4 Restore the cpus-per-proc option for byslot and bynode mapping. Remove the bind_idx (which recorded the index of the hwloc object where the proc was bound) as this would no longer be unique, and just use the bitmap as the standard reference for location. Update the relative locality computation to take bitmaps as its argument.
This commit was SVN r28219.
2013-03-26 18:27:50 +00:00
Ralph Castain
147c6ff9e7 Clean out the cruft leftover from the use_common_ports experiment
cmr:v1.7

This commit was SVN r28184.
2013-03-20 15:07:43 +00:00
Ralph Castain
a4b6fb241f Remove all remaining vestiges of the Windows integration
This commit was SVN r28137.
2013-02-28 17:31:47 +00:00
Ralph Castain
cf9796accd Remove the old configure option for disabling full rte support - we now use the OMPI rte framework for such purposes
This commit was SVN r28134.
2013-02-28 01:35:55 +00:00
Ralph Castain
bd9265c560 Per the meeting on moving the BTLs to OPAL, move the ORTE database "db" framework to OPAL so the relocated BTLs can access it. Because the data is indexed by process, this requires that we define a new "opal_identifier_t" that corresponds to the orte_process_name_t struct. In order to support multiple run-times, this is defined in opal/mca/db/db_types.h as a uint64_t without identifying the meaning of any part of that data.
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.
2013-02-26 17:50:04 +00:00
Ralph Castain
c0b670bea8 I guess some profiling tools and debuggers require that the argv[0] of each rank be unique so they can create a filename based on that value. For those obscure cases, provide an mpirun cmd line option that indexes each argv[0] by rank
This commit was SVN r28064.
2013-02-15 20:20:49 +00:00
Ralph Castain
a591fbf06f Add initial support for dynamic allocations. At this time, only Slurm supports the new capability, which will be included in an upcoming release.
Add hooks for supporting dynamic allocation and deallocation to support application-driven requests and fault recovery operations.

This commit was SVN r27879.
2013-01-20 00:33:42 +00:00
Ralph Castain
c96cc2d5a0 In order to properly connect to debuggers like STAT, we need to get the hostname in its unstripped version for the MPIR_proctab. Unfortunately, we need a stripped version for Cray's alps launcher. So when we are stripping the hostname prefix, retain alias hostnames and add the ability to specify an alias to use in the proctab.
This commit was SVN r27863.
2013-01-18 05:00:05 +00:00
Ralph Castain
97ee683275 Track parentage of procs
This commit was SVN r27758.
2013-01-08 04:41:12 +00:00
Nathan Hjelm
6a9ab9b221 Change orte_startup_timeout to be in seconds and remove the 10 second maximum
This commit was SVN r27741.
2013-01-03 23:56:34 +00:00
Ralph Castain
81a8e21939 Need to have the event thread running during init/finalize, but we still have a problem with cleanup - so comment out the event_base_free for now.
This commit was SVN r27738.
2013-01-03 02:16:57 +00:00
Ralph Castain
64da742d5f Remove the orte_finalize_event variable - no longer needed
This commit was SVN r27722.
2012-12-25 19:33:20 +00:00
Ralph Castain
cada035f38 Fix the segfault problem in the orteds - turns out it only occurred with progress threads enabled. Ensure the thread gets started at the right time (at the end of init), although the event base gets created earlier. Remove the finalize event as we can instead use the loopbreak call to exit the event loop.
This commit was SVN r27721.
2012-12-25 19:30:18 +00:00
Ralph Castain
c8e34813b6 THIS IS A TEMPORARY FIX - do not finalize opal as the parameter system has been broken and will segfault when finalized.
THIS PATCH MUST BE REMOVED WHEN THE PARAMETER SYSTEM HAS BEEN FIXED.

This commit was SVN r27720.
2012-12-24 18:42:19 +00:00
Ralph Castain
e11f32038a Add an MCA param to retain all aliases based on IP addrs for node names so that procs can look them up by interface, if desired. If the param is set, pass aliases around to all daemons and procs for local use
This commit was SVN r27619.
2012-11-16 04:04:29 +00:00
Ralph Castain
da6428a822 Add an MCA param to help debug the ORTE progress thread
This commit was SVN r27614.
2012-11-15 15:54:38 +00:00
Ralph Castain
5241925b62 Add the dfs to ompi_info
This commit was SVN r27613.
2012-11-15 15:54:07 +00:00
Ralph Castain
fefec03e78 Enable all ORTE tools to use progress threads if they are enabled
This commit was SVN r27593.
2012-11-12 02:54:09 +00:00
Ralph Castain
bd887f7f56 Add a new "test" component to the DFS that treats all files as remote in order to test the app-to-daemon interactions on a single machine. Set a global param to indicate we are using staged execution. Add a param to indicate it is okay for non-MPI processes to execute without finalizing. Cleanup file map load and fetch operations.
This commit was SVN r27587.
2012-11-10 14:09:12 +00:00
Nathan Hjelm
a754674fd7 Per the specification for putenv (http://pubs.opengroup.org/onlinepubs/009604599/functions/putenv.html) the string given to putenv becomes part of the environment. The string must not be changed or freed.
cmr:v1.7

This commit was SVN r27578.
2012-11-09 16:33:14 +00:00
Ralph Castain
3812979315 Remove stale file - we removed the size functions awhile back
This commit was SVN r27551.
2012-11-01 03:36:51 +00:00
Ralph Castain
a080de188f Enable orterun to directly support staged execution, treating each app as a separate job. Support transfer of file maps when support exists.
This commit was SVN r27516.
2012-10-29 23:11:30 +00:00
Ralph Castain
4e52a15e70 Provide for sync on seek and close DFS operations. Eliminate an unnecessary wake-up timer when using ORTE progress thread
This commit was SVN r27500.
2012-10-26 15:49:04 +00:00
Ralph Castain
35e5e5b512 Set the orte_event_base to the opal_event_base in ompi_info - we aren't doing anything with progress threads anyway
This commit was SVN r27488.
2012-10-25 22:36:08 +00:00
Ralph Castain
79e36413c2 There was some discussion of this at an earlier time, but we never got around to doing it - so make orte behave more like a regular library, counting the number of times init is called, and executing finalize when all those are exhausted.
This commit was SVN r27484.
2012-10-25 18:39:37 +00:00
Ralph Castain
4028ce7a5d Silence warnings by making types match
This commit was SVN r27446.
2012-10-14 03:45:28 +00:00
Ralph Castain
285a3b168d Add an ability to specify the max number of simultaneous procs/node for an application when operating in staged mode. Change some debug statements from OPAL_OUTPUT_VERBOSE to opal_output_verbose so they are available in optimized builds.
This commit was SVN r27445.
2012-10-14 03:31:32 +00:00
Jeff Squyres
fb2e543a57 Refs trac:3275.
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
2012-09-11 20:47:24 +00:00
Ralph Castain
a0ffeb205a Add an orted component for staged operations and rename the staged component to "staged_hnp".
This commit was SVN r27305.
2012-09-11 20:35:46 +00:00
Ralph Castain
d772e0fc3d Add an option to treat dash-host specifications as "requested, but not required". So-called "soft" location requests can allow an application to execute even if the ideal allocation isn't available.
This commit was SVN r27242.
2012-09-05 18:42:09 +00:00
Ralph Castain
fde83a44ab This confusion has been around for awhile, caused by a long-ago decision to track slots allocated to a specific job as opposed to allocated to the overall mpirun instance. We eliminated that quite a while ago, but never consolidated the "slots_alloc" and "slots" fields in orte_node_t. As a result, confusion has grown in the code base as to which field to look at and/or update.
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.
2012-09-05 01:30:39 +00:00
Ralph Castain
bae5dab916 If (and only if) a user requests, set the default number of slots on any node to the number of objects of the specified type. This *only* takes effect in an unmanaged environment - i.e., if an external resource manager assigns us a number of slots, then that is what we use. However, if we are using a hostfile, then the user may or may not have given us a value for the number of slots on each node.
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.
2012-09-04 20:58:26 +00:00
Ralph Castain
11de735e8a Complete the revamp of hostfile support in non-managed environments. Working at the app level, ensure that we utilize only those nodes specified for that app, but fall back to the default hostfile (if available) for those with no specification, further falling back to the local host if the default hostfile is not present or is empty.
This commit was SVN r27230.
2012-09-04 16:34:05 +00:00
Ralph Castain
1b659de132 Get staged execution working on multi-node setups. Improve efficiency by only remapping if all procs not yet mapped in the job.
This commit was SVN r27181.
2012-08-29 20:35:52 +00:00
Ralph Castain
98580c117b Introduce staged execution. If you don't have adequate resources to run everything without oversubscribing, don't want to oversubscribe, and aren't using MPI, then staged execution lets you (a) run as many procs as there are available resources, and (b) start additional procs as others complete and free up resources. Adds a new mapper as well as a new state machine.
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.
2012-08-28 21:20:17 +00:00
Ralph Castain
e0c39c94e8 Complete the cleanup of the preload files system. Remove the dest_dir option as moving things to arbitrary locations - especially absolute paths - can prove disastrous. Remove the preload_libs option as these can be treated as just files. Cleanup some of the pack/unpack code as the dss handles NULL strings just fine. Deal a little better with absolute paths, noting that tar now strips the leading '/' for us (showing my age as it didn't used to do so).
Remove the odls_base_state.c file as that code is now covered by the new broadcast form of preload_files.

This commit was SVN r27127.
2012-08-24 02:28:29 +00:00
Ralph Castain
b4a544ad2a Per discussion with Josh, use the --preload-xxx cmd line options to broadcast files to all nodes. Add --set-cwd-to-session-dir option to start procs in their session directories. Add OMPI_FILE_LOCATION envar to tell procs where their prepositioned files went.
This commit was SVN r27125.
2012-08-23 21:28:05 +00:00
Ralph Castain
e4d82b8912 Turn off the common port by default by now until we get rollup working properly on ALL platforms
This commit was SVN r27060.
2012-08-15 22:13:04 +00:00
Ralph Castain
cb48fd52d4 Implement the MPI_Info part of MPI-3 Ticket 313. Add an MPI_info object MPI_INFO_GET_ENV that contains a number of run-time related pieces of info. This includes all the required ones in the ticket, plus a few that specifically address recent user questions:
"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.
2012-08-12 01:28:23 +00:00