PML base will take care of the registration with the event library.
Otherwise, (and this apply for the CM case) the MTL are in charge of
registering their own progress function.
This commit was SVN r16415.
* Fix some missing includes in a few places.
* Add the cr_request() functionality to the BLCR CRS component.
We are now dependent upon the 0.6.* series of BLCR.
* Made the CR notification mechanism a registered function.
This way we can have an OPAL-only version and it can be replaced at
runtime with the ORTE version.
* Add a 'opal_cr_allow_opal_only' parameter that will enable OPAL-only
CR functionality when the user wants it. Default: Disabled.
* Fix the placement of a checkpoint request check in MPI_Init
* Pull the OPAL notification mechanism into the SnapC framework.
* We no longer fork/exec the 'opal-checkpoint' command for local
checkpointing, the Local coordinator in the orted does this directly.
* The Local and Application coordinator talk together bypassing the OPAL
notifiation mechanism.
* Optimized the Local <-> App Coordinator communication.
* Improved the structure used to track vpid_snapshots in the local coord.
* Fix a race condition in which an application under heavy communication load
may produce an inconsistent global checkpoint.
This commit was SVN r16389.
yesterday. This actually exposed a very, very long-standing bug where
part of the coll base was incorrectly checking the coll API version
against the MCA API version. When coll went to v1.1 (yesterday) and
was no longer the same as the MCA v1.0, the test started failing.
This commit fixes to check for v1.1 everywhere in the coll base, and
to ensure to check coll framework/API version numbers against coll
framework/API version numbers (vs. against the MCA API version
number).
This commit was SVN r16373.
The commit has been tested for C/R and Cray operations, and on Odin (SLURM, rsh) and RoadRunner (TM). I tried to update all environments, but obviously could not test them. I know that Windows needs some work, and have highlighted what is know to be needed in the odls process component.
This represents a lot of work by Brian, Tim P, Josh, and myself, with much advice from Jeff and others. For posterity, I have appended a copy of the email describing the work that was done:
As we have repeatedly noted, the modex operation in MPI_Init is the single greatest consumer of time during startup. To-date, we have executed that operation as an ORTE stage gate that held the process until a startup message containing all required modex (and OOB contact info - see #3 below) info could be sent to it. Each process would send its data to the HNP's registry, which assembled and sent the message when all processes had reported in.
In addition, ORTE had taken responsibility for monitoring process status as it progressed through a series of "stage gates". The process reported its status at each gate, and ORTE would then send a "release" message once all procs had reported in.
The incoming changes revamp these procedures in three ways:
1. eliminating the ORTE stage gate system and cleanly delineating responsibility between the OMPI and ORTE layers for MPI init/finalize. The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info. The allgather is implemented using the orte_grpcomm framework since the BTL's are not active at that point. At the moment, the grpcomm framework only has a "basic" component analogous to OMPI's "basic" coll framework - I would recommend that the MPI team create additional, more advanced components to improve performance of this step.
The other stage gates have been replaced by orte_grpcomm barrier functions. We tried to use MPI barriers instead (since the BTL's are active at that point), but - as we discussed on the telecon - these are not currently true barriers so the job would hang when we fell through while messages were still in process. Note that the grpcomm barrier doesn't actually resolve that problem, but Brian has pointed out that we are unlikely to ever see it violated. Again, you might want to spend a little time on an advanced barrier algorithm as the one in "basic" is very simplistic.
Summarizing this change: ORTE no longer tracks process state nor has direct responsibility for synchronizing jobs. This is now done via collective operations within the MPI layer, albeit using ORTE collective communication services. I -strongly- urge the MPI team to implement advanced collective algorithms to improve the performance of this critical procedure.
2. reducing the volume of data exchanged during modex. Data in the modex consisted of the process name, the name of the node where that process is located (expressed as a string), plus a string representation of all contact info. The nodename was required in order for the modex to determine if the process was local or not - in addition, some people like to have it to print pretty error messages when a connection failed.
The size of this data has been reduced in three ways:
(a) reducing the size of the process name itself. The process name consisted of two 32-bit fields for the jobid and vpid. This is far larger than any current system, or system likely to exist in the near future, can support. Accordingly, the default size of these fields has been reduced to 16-bits, which means you can have 32k procs in each of 32k jobs. Since the daemons must have a vpid, and we require one daemon/node, this also restricts the default configuration to 32k nodes.
To support any future "mega-clusters", a configuration option --enable-jumbo-apps has been added. This option increases the jobid and vpid field sizes to 32-bits. Someday, if necessary, someone can add yet another option to increase them to 64-bits, I suppose.
(b) replacing the string nodename with an integer nodeid. Since we have one daemon/node, the nodeid corresponds to the local daemon's vpid. This replaces an often lengthy string with only 2 (or at most 4) bytes, a substantial reduction.
(c) when the mca param requesting that nodenames be sent to support pretty error messages, a second mca param is now used to request FQDN - otherwise, the domain name is stripped (by default) from the message to save space. If someone wants to combine those into a single param somehow (perhaps with an argument?), they are welcome to do so - I didn't want to alter what people are already using.
While these may seem like small savings, they actually amount to a significant impact when aggregated across the entire modex operation. Since every proc must receive the modex data regardless of the collective used to send it, just reducing the size of the process name removes nearly 400MBytes of communication from a 32k proc job (admittedly, much of this comm may occur in parallel). So it does add up pretty quickly.
3. routing RML messages to reduce connections. The default messaging system remains point-to-point - i.e., each proc opens a socket to every proc it communicates with and sends its messages directly. A new option uses the orteds as routers - i.e., each proc only opens a single socket to its local orted. All messages are sent from the proc to the orted, which forwards the message to the orted on the node where the intended recipient proc is located - that orted then forwards the message to its local proc (the recipient). This greatly reduces the connection storm we have encountered during startup.
It also has the benefit of removing the sharing of every proc's OOB contact with every other proc. The orted routing tables are populated during launch since every orted gets a map of where every proc is being placed. Each proc, therefore, only needs to know the contact info for its local daemon, which is passed in via the environment when the proc is fork/exec'd by the daemon. This alone removes ~50 bytes/process of communication that was in the current STG1 startup message - so for our 32k proc job, this saves us roughly 32k*50 = 1.6MBytes sent to 32k procs = 51GBytes of messaging.
Note that you can use the new routing method by specifying -mca routed tree - if you so desire. This mode will become the default at some point in the future.
There are a few minor additional changes in the commit that I'll just note in passing:
* propagation of command line mca params to the orteds - fixes ticket #1073. See note there for details.
* requiring of "finalize" prior to "exit" for MPI procs - fixes ticket #1144. See note there for details.
* cleanup of some stale header files
This commit was SVN r16364.
Check if an exclusion string (i.e. '-mca btl ^sm) was provided; if so OFUD just disables itself.
This commit was SVN r16307.
The following Trac tickets were found above:
Ticket 1154 --> https://svn.open-mpi.org/trac/ompi/ticket/1154
Each one of them has a field to store QP type, but this is redundant.
Store qp type only in one structure (the component one).
This commit was SVN r16272.
is set to the cid of the communicator (unique id for each communicator).
Make sure each communicator have a group attached to it. The MPI_COMM_NULL
should have the MPI_GROUP_NULL as a group, in all circumstances.
This commit was SVN r16177.
executable has called MPI_Finalize(). It happens when removing the group
from each of the communicators, that MPI_COMM_NULL doesn't have a group.
Also fix the code from skipping over every other communicator when
freeing the groups.
This commit was SVN r16166.
meaning "infinite") is no longer larger than the minimum required
size. So put in an appropriate test to ensure that "infinite" was not
requested.
This commit was SVN r16142.
numbers for tuning.
Switch the bookmark_recv to be non-blocking. If this is blocking then for
process counts >= 32 slight process delays were causing cascading performance
delays in the protocol. This lead to checkpoints either taking about 3 sec or
45 sec (or more) for 64 procs due to the cascading delays. With the nonblocking
receive version this is no longer the case we get the speedup we expect for this
part of the protocol.
More tuning to come.
This commit was SVN r16137.
There is a reason that we use the internal type (ompi_file_errhandler_fn) instead of the MPI typedef. When building without MPI-IO support (--disable-mpi-io), the MPI type is not defined, but the internal type IS defined in order to try to keep binary compatibility for apps that don't use MPI-IO.
This commit was SVN r16136.
The following SVN revision numbers were found above:
r16130 --> open-mpi/ompi@cf5a38af5e
you'll get a helpful error message and the openib BTL will deactivate
itself.
This commit was SVN r16133.
The following Trac tickets were found above:
Ticket 1133 --> https://svn.open-mpi.org/trac/ompi/ticket/1133
NOTE: This build system does not work with the current autogen.sh. Modified one is under heavy testing to make sure it does not have side effects
This commit was SVN r16110.
simultaneously, but is doing it incorrectly. If the function is running already
for one communicator and it is called from another thread for other communicator
with lower cid the check comm->c_contextid != ompi_comm_lowest_cid()
will fail and the function will be executed for two different communicators by
two threads simultaneously. There is nothing in the algorithm that prevent it
from been running simultaneously for different communicators as far as I can see,
but ompi_comm_unregister_cid() assumes that it is always called for a communicator
with the lowest cid and this is not always the case. This patch removes bogus
lowest cid check and fix ompi_comm_register_cid() to properly remove cid from
the list.
This commit was SVN r16088.
off and bogus addresses to show up for the requests, which in turns causes
message queues not showing up when debugging a 64 bit app on a 32 bit
tvd and dll on only Solaris SPARC.
This commit was SVN r16052.
Basically revert this part of r16015.
This commit was SVN r16029.
The following SVN revision numbers were found above:
r16015 --> open-mpi/ompi@435e7d80e9
from showing up in the message queue graph. Tags are now casted to int
before the negative checks, since tags by the spec are stored as
mqs_tword_t, an unsigned long long.
This commit was SVN r16027.
The following SVN revision numbers were found above:
r15915 --> open-mpi/ompi@b9ea4c92e7
no more work associated with this request. No more outstanding completions or
packets and send scheduling isn't running in another thread.
This commit was SVN r16013.
the ompi_convertor_need_buffers function to only return 0 if the convertor
is homogeneous (which it never does on the trunk, but does to on v1.2, but
that's a different issue). Only enable the heterogeneous rdma code for
a btl if it supports it (via a flag), as some btls need some work for this
to work properly. Currently only TCP and OpenIB extensively tested
This commit was SVN r15990.
side too. Otherwise a content of the recvreq->req_rdma array is replaced later
without freeing previous content and refcount on registration in mpool become
wrong.
This commit was SVN r15978.
