This is closely related to Platform-MPI's old -prot feature.
The long-format of the tables it prints could look like this:
> Host 0 [myhost001] ranks 0 - 1
> Host 1 [myhost002] ranks 2 - 3
> Host 2 [myhost003] ranks 4
> Host 3 [myhost004] ranks 5
> Host 4 [myhost005] ranks 6
> Host 5 [myhost006] ranks 7
> Host 6 [myhost007] ranks 8
> Host 7 [myhost008] ranks 9
> Host 8 [myhost009] ranks 10
>
> host | 0 1 2 3 4 5 6 7 8
> ======|==============================================
> 0 : sm tcp tcp tcp tcp tcp tcp tcp tcp
> 1 : tcp sm tcp tcp tcp tcp tcp tcp tcp
> 2 : tcp tcp self tcp tcp tcp tcp tcp tcp
> 3 : tcp tcp tcp self tcp tcp tcp tcp tcp
> 4 : tcp tcp tcp tcp self tcp tcp tcp tcp
> 5 : tcp tcp tcp tcp tcp self tcp tcp tcp
> 6 : tcp tcp tcp tcp tcp tcp self tcp tcp
> 7 : tcp tcp tcp tcp tcp tcp tcp self tcp
> 8 : tcp tcp tcp tcp tcp tcp tcp tcp self
>
> Connection summary:
> on-host: all connections are sm or self
> off-host: all connections are tcp
In this example hosts 0 and 1 had multiple ranks so "sm" was more
meaningful than "self" to identify how the ranks on the host are
talking to each other. While host 2..8 were one rank per host so
"self" was more meaningful as their btl.
Above a certain number of hosts (12 by default) the above table gets too big
so we shrink to a more abbreviated looking table that has the same data:
> host | 0 1 2 3 4 8
> ======|====================
> 0 : A C C C C C C C C
> 1 : C A C C C C C C C
> 2 : C C B C C C C C C
> 3 : C C C B C C C C C
> 4 : C C C C B C C C C
> 5 : C C C C C B C C C
> 6 : C C C C C C B C C
> 7 : C C C C C C C B C
> 8 : C C C C C C C C B
> key: A == sm
> key: B == self
> key: C == tcp
Then above 36 hosts we stop printing the 2d table entirely and just print the
summary:
> Connection summary:
> on-host: all connections are sm or self
> off-host: all connections are tcp
The options to control it are
-mca comm_method 1 : print the above table at the end of MPI_Init
-mca comm_method 2 : print the above table at the beginning of MPI_Finalize
-mca comm_method_max <n> : number of hosts <n> for which to print a full size 2d
-mca comm_method_brief 1 : only print summary output, no 2d table
-mca comm_method_fakefile <filename> : for debugging only
* printing at init vs finalize:
The most important difference between these two is that when printing the table
during MPI_Init(), we send extra messages to make sure all hosts are connected to
each other. So the table ends up working against the idea of on-demand connections
(although it's only forcing the n^2 connections in the number of hosts, not the
total ranks). If printing at MPI_Finalize() we don't create any connections that
aren't already connected, so the table is more likely to have "n/a" entries if
some hosts never connected to each other.
* how many hosts <n> for which to print a full size 2d table
The option -mca comm_method_max <n> can be used to specify a number of hosts <n>
(default 12) that controls at what host-count the unabbreviated / abbreviated
2d tables get printed:
1 - n : full size 2d table
n+1 - 3n : shortened 2d table
3n+1 - inf : summary only, no 2d table
* brief
The option -mca comm_method_brief 1 can be used to skip the printing of the 2d
table and only show the short summary
* fakefile
This is a debugging option that allows easeir testing of all the printout
routines by letting all the detected communication methods between the hosts
be overridden by fake data from a file.
The source of the information used in the table is the .mca_component_name
In the case of BTLs, the module always had a .btl_component linking back to the
component. The vars mca_pml_base_selected_component and ompi_mtl_base_selected_component
offer similar functionality for pml/mtl.
So with the ability to identify the component, we can then access
the component name with code like this
mca_pml_base_selected_component.pmlm_version.mca_component_name
See the three lookup_{pml,mtl,btl}_name() functions in hook_comm_method_fns.c,
and their use in comm_method() to parse the strings and produce an integer
to represent the connection type being used.
Signed-off-by: Mark Allen <markalle@us.ibm.com>
This is based on a bug reported on the mailing list using a netcdf testcase.
The problem occurs if processes are using a custom file view, but on some
of them it appears as if the default file view is being used. Because of that,
the simple-grouping option lead to different number of aggregators used on different
processes, and ultimately to a deadlock. This patch fixes the problem by not using
the file_view size anymore for the calculation in the simple-grouping option,
but the contiguous chunk size (which is identical on all processes).
Fixes issue #7109
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
zero-size derived datatypes are now flagged as OPAL_DATATYPE_FLAG_CONTIGUOUS
so update mca_pml_ucx_init_datatype() to correctly handle them.
Since 'size' is a 'size_t', the assertion can simply be removed.
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
Change the ncounts argument to MPI_Count and use
MPI_Status_set_elements_x for enabling read/write operations beyond
the 2GB limit.
Thanks to Richard Warren from the HDF5 group for reporting the issue
and providing the suggested fix for romio.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
individual read/write operations exceeding 2GB fail in ompio
due to improper conversions from size_t to int in two different
locations. This commit fixes an issue reported by Richard Warren
from the HDF5 group.
Fixes Issue #397
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
one off patch for v4.0.x. for some reason commit on master
didn't have this problem.
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
(cherry picked from commit 5f3dbdb5c8a94a4f426ecca1a3a91c83035f956c)
Note that this commit is actually a cherry-pick from the v4.0.x
branch. This is the opposite direction than what we nornmally do: we
usually commit to master first and then cherry-pick to the release
branches (vs. the other way around).
As is probably evident from the original commit message above, through
a comedy of errors, this commit was actually applied to the v4.0.x
branch first and then cherry-picked back to master (i.e., the problem
*did* exist in the original master commit
3aca4af548a3d781b6b52f89f4d6c7e66d379609, but it was not recongized at
the time).
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
INTERNAL: STL-59403
The OFI (libfabric) MTL does not respect the maximum message size
parameter that OFI provides in the fi_info data.
This patch adds this missing max_msg_size field to the mca_ofi_module_t
structure and adds a length check to the low-level send routines.
Change-Id: I05aa71d332f2df897133b30c28bf37d98f061996
Signed-off-by: Michael Heinz <michael.william.heinz@intel.com>
Reviewed-by: Adam Goldman <adam.goldman@intel.com>
Reviewed-by: Brendan Cunningham <brendan.cunningham@intel.com>
I'm restoring the info function pointers to the IO module
but allowing the function pointers to be NULL (eg in ompio).
And letting romio321 set its function pointers for those
routines.
This means the info system uses the new OMPI-level info
system for most things, but skips it and uses the pre-existing
romio info system just for the romio module.
It's possible to convert romio, but I went a ways down that
path and found it kind of convoluted. Having pointers from
the lower level ADIO_File back to the higher level ompi_file_t
wasn't too bad, but I got stuck trying to figure out where/how
to register the infosubscribe_subscribe callbacks vs the way
initial k/v values are scattered around the romio code currently.
Signed-off-by: Mark Allen <markalle@us.ibm.com>
open-mpi/ompi@0fe756d416 Introduced
a bug in coll/hcoll component. The ompi_requests allocated by
libhcoll would be treated as coll_base_nbc_request during
ompi_coll_base_retain_<> call. Afterwards this would lead to a
segv in the request cleanup.
Fix: since libhcoll interface does not distinguish between the
blocling/non-blocking requests use coll_base_nbc_request all the
time and initialize it properly in
coll/hcoll/get_coll_handle(). It is still within 2 cache lines.
Signed-off-by: Valentin Petrov <valentinp@mellanox.com>
Within the shuffle iteration, the aggregators have to set a displacement array needed to receive data from other processes. The array had 1 extra element. We adjust the displacement index to match the number of elements.
Signed-off-by: raafatfeki <fekiraafat@gmail.com>
Within the shuffle iteration, the aggregators have to set a displacement array needed to receive data from other processes. The array had 1 extra element. We adjust the displacement index to match the number of elements.
Signed-off-by: raafatfeki <fekiraafat@gmail.com>
a non blocking collective might return ompi_request_null, so we should not
retain anything in that case.
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
Since ompi_coll_base_nbc_request_t is to be used in an
opal_free_list_t, it must be returned into a "clean" state.
So cleanup some data in the callback completion subroutines.
This fixes a regression introduced in open-mpi/ompi@0fe756d416
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
base ompi_coll_libnbc_request_t on top of ompi_coll_base_nbc_request_t
to correctly support the retention of datatypes/operators
This fixes a regression introduced in open-mpi/ompi@0fe756d416
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
The PSM MTL for Intel's TrueScale Infiniband HCAs is not being actively
maintained and should be removed from the master branch.
Fixes issue: #6877
Signed-off-by: Michael Heinz <michael.william.heinz@intel.com:
Use linear with sync alltoall algorithm for certain message/comm size
ranges. Does not affect default fixed decision, unless HPCX (with its
custom parameters) is used or corresponding mca is set.
Signed-off-by: Mikhail Brinskii <mikhailb@mellanox.com>
MPI standard states a user MPI_Op and/or user MPI_Datatype can be free'd
after a call to a non blocking collective and before the non-blocking
collective completes.
Retain user (only) MPI_Op and MPI_Datatype when the non blocking call is
invoked, and set a request callback so they are free'd when the MPI_Request
completes.
Thanks Thomas Ponweiser for reporting this
Fixesopen-mpi/ompi#2151Fixesopen-mpi/ompi#1304
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
To avoid fully initializing the osc/ucx component for MPI application
that are not using One-Sided functionality, the initialization happens
at the first MPI window creation.
This commit ensures atomicity of global state modifications.
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
In common_ompi_aggregators calc_cost routine:
do not cast the real division to an int intermediately.
This patch removes the obsolete int variable c and assigns
the result of the P_a/P_x division directly to n_as.
With the intermediate int c variable, n_as gets 0 if P_a < P_x,
resulting in a division by 0 when computing n_s.
Signed-off-by: Harald Klimach <harald.klimach@uni-siegen.de>
