WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
Let's not make the move to OPAL any harder than it has to be; this
commit can wait until after the BTL move.
This commit was SVN r32316.
The following SVN revision numbers were found above:
r32315 --> open-mpi/ompi@7b7ed8ed97
CMR'ing just to (try to) keep the differences between trunk and v1.8
branch (somewhat) small.
Reviewed by Dave Goodell
cmr=v1.8.3:reviewer=ompi-rm1.8
This commit was SVN r32315.
Previously, we were only checking connectivity upon first ''send'' to
a peer. But this ignores the case where the first communication to a
peer is actually an ACK -- i.e., we successfully received something
from the peer and we need to send an ACK back. So we need to verify
that the ACK will actually get there.
Specifically, certain asymmetric routing cases can lead to a hang if
we don't check the connectivity in both directions. E.g., if the
sender is able to get traffic to the receiver, but the receiver is
unable to get traffic back to the sender because it made a different
routing decision than the sender.
In this case, the connectivity checker from the sender could succeed
(because the connectivity checker will ACK along the same path in
which the ping was received), but sending a BTL ACK could fail
(because the BTL ACK will be sent back along the path chosen by the
graph algorithm, which, in an erroneous asymmetric routing scenario,
may be different/wrong).
Hence, we want to trigger the connectivity checker at the first
communication from A->B, which may either be a BTL send or an ACK.
Reviewed by Dave Goodell.
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32309.
- Portals4/OSC was unable to acquire an exclusive lock due to an invalid
local address in the atomic operation. This caused the reported hang.
- After fixing the hang, the test continued to fail because
ompi_datatype_is_contiguous_memory_layout() reports that MPI_EMPTY (the
origin datatype) is noncontiguous and Portals4/OSC does not support
noncontiguous datatypes at this time. However, in this case the origin
count is zero so contiguous/noncontiguous is irrelevant. Now we skip
the contiguous check if the count is zero.
cmr=v1.8.3:reviewer=regrant:subject=Fix for "Portals4/MTL hangs in c_get_accumulate test"
This commit was SVN r32295.
The following Trac tickets were found above:
Ticket 4662 --> https://svn.open-mpi.org/trac/ompi/ticket/4662
QA ran across the case where the user can't write to the target
directory for the connectivity map file. In this case, we silently
continued. They requested that we at least warn in this case.
Fixes Cisco bug CSCup62821
Reviewed by Dave Goodell
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32283.
Description:
This mod fixes a regression in the ugni btl eager get
path introduced in changeset 32196.
References:4800
Closes:4800
cmr=v1.8.2:reviewer=hjelmn
This commit was SVN r32264.
The logic was mishandling the case of a newer kernel and an older
libusnic_verbs. Simplify usnic_transport() to return constants in the
2 known cases (not a usNIC device and the TRANSPORT_USNIC_UDP case),
and call the magic probe in all other cases.
Reviewed-by: Dave Goodell <dgoodell@cisco.com>
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32260.
If we don't explicitly declare that (a == NULL && b == NULL) is
equivalent to qsort, we could end up with wonky sorting order. I.e.,
it's *possible* that some NULLs could end up in the middle of the
array.
Regardless of whether it will ever happen in practice, it makes the
code more clear to also handle the "both are NULL" case.
Also fix the 2-spacing indents.
Reviewed by Dave Goodell.
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32259.
The wrong descriptor field was used when calculating the size received when
using the RDMA rendevous protcol.
This commit was SVN r32232.
The following SVN revision numbers were found above:
r32196 --> open-mpi/ompi@a14e0f10d4
Handle OMPI_REQUEST_NOOP in MPI_Startall rather than PML
cmr=v1.8.2:reviewer=bosilca:ticket=4764
This commit was SVN r32213.
The following Trac tickets were found above:
Ticket 4764 --> https://svn.open-mpi.org/trac/ompi/ticket/4764
The connectivity map output routine needs to handle the case where
entries in the endpoints array are NULL (e.g., if one process has 2
endpoints and another process has only 1 endpoint).
Fixes Cisco bug CSCup83649.
cmr=v1.8.2
This commit was SVN r32211.
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.
mca_btl_base_segment_t and replace them with des_local and des_remote
This change also updates the BTL version to 3.0.0. This commit does
not represent the final version of BTL 3.0.0. More changes are coming.
In making this change I updated all of the BTLs as well as BTL user's
to use the new structure members. Please evaluate your component to
ensure the changes are correct.
RFC text:
This is the first of several BTL interface changes I am proposing for
the 1.9/2.0 release series.
What: Change naming of btl descriptor members. I propose we change
des_src and des_dst (and their associated counts) to be des_local and
des_remote. For receive callbacks the des_local member will be used to
communicate the segment information to the callback. The proposed change
will include updating all of the doxygen in btl.h as well as updating
all BTLs and BTL users to use the new naming scheme.
Why: My btl usage makes use of both put and get operations on the same
descriptor. With the current naming scheme I need to ensure that there
is consistency beteen the segments described in des_src and des_dst
depending on whether a put or get operation is executed. Additionally,
the current naming prevents BTLs that do not require prepare/RMA matched
operations (do not set MCA_BTL_FLAGS_RDMA_MATCHED) from executing
multiple simultaneous put AND get operations. At the moment the
descriptor can only be used with one or the other. The naming change
makes it easier for BTL users to setup/modify descriptors for RMA
operations as the local segment and remote segment are always in the
same member field. The only issue I forsee with this change is that it
will require a little more work to move BTL fixes to the 1.8 release
series.
This commit was SVN r32196.
Description: This mod fixes two name conflicts between the ugni and scif btls.
References:4771
Closes:4771
cmr=v1.8.2:reviewer=hjelmn
This commit was SVN r32183.
new flag to ompi_info that allows a user to print all MCA variables of a specific type.
--type version_string
This command will print all MCA variables of type version_string.
This feature was developed by Elena Shipunova and was reviewed by Josh Ladd.
This commit was SVN r32166.
This commit adds a check to see if the target is in an access epoch. If
not we return OMPI_ERR_RMA_SYNC. This fixes test_start3 in the onesided
test suite. The cost of this extra check is 1 byte/peer for the boolean
flag indicating that the peer is in an access epoch.
I also fixed a problem where mupliple unexpected post messages are not
correctly handled.
cmr=v1.8.2:reviewer=jsquyres
This commit was SVN r32160.
If the btl_usnic_connectivity_map MCA param is set to a non-NULL
value, then each MPI process will output a file named
<prefix>-<hostname>.pid<pid>.job<jobid>.mcwrank<MCW rank>.txt. Its
contents will detail which usNIC device(s) (and therefore which
link(s)) are being used to communicate with each peer MPI process.
Here is a sample output file (named
mpi005.pid26071.job1640759297.mcwrank0.txt):
{{{
device=usnic_0,interface=eth4,ip=10.10.0.5/16,mac=24:57:20:05:20:00,mtu=9000
device=usnic_1,interface=eth5,ip=10.2.0.5/16,mac=24:57:20:05:21:00,mtu=9000
device=usnic_2,interface=eth6,ip=10.3.0.5/16,mac=24:57:20:05:50:00,mtu=9000
peer=1,hostname=mpi006,device=usnic_0@peer_ip=10.10.0.6/16@peer_mac=24:57:20:06:20:00,device=usnic_1@peer_ip=10.2.0.6/16@peer_mac=24:57:20:06:21:00,device=usnic_2@peer_ip=10.3.0.6/16@peer_mac=24:57:20:06:50:00
peer=2,hostname=mpi007,device=usnic_0@peer_ip=10.10.0.7/16@peer_mac=24:57:20:07:20:00,device=usnic_1@peer_ip=10.2.0.7/16@peer_mac=24:57:20:07:21:00,device=usnic_2@peer_ip=10.3.0.7/16@peer_mac=24:57:20:07:50:00
peer=3,hostname=mpi008,device=usnic_0@peer_ip=10.10.0.8/16@peer_mac=24:57:20:08:20:00,device=usnic_1@peer_ip=10.2.0.8/16@peer_mac=24:57:20:08:21:00,device=usnic_2@peer_ip=10.3.0.8/16@peer_mac=24:57:20:08:50:00
}}}
Reviewed by Reese Faucette
cmr=v1.8.2
This commit was SVN r32156.
This corner case is now handled in the pml so the same code
is invoked for both MPI_Start and MPI_Startall.
This also correctly report an error if MPI_Startall is invoked twice
on a MPI_PROC_NULL persistent request.
This commit was SVN r32139.
ibv_create_ah() can also return EHOSTUNREACH, which means that there
is no route to the peer. Treat that as a non-fatal warning.
Reviewed by Reese Faucette.
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32135.
There's no need for the port number (since usNIC has no port numbers),
and make the wording the same as other help messages.
Reviewed by Reese Faucette.
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32134.
no need to #include <math.h> ...
cmr=v1.8.2:reviewer=miked:ticket=4759
This commit was SVN r32121.
The following Trac tickets were found above:
Ticket 4759 --> https://svn.open-mpi.org/trac/ompi/ticket/4759
The distances as returned by hwloc_get_whole_distance_matrix_by_type are typ float.
This patch handle all distances as float.
cmr=v1.8.2:reviewer=miked
This commit was SVN r32120.
