To resolve this situation, add the ability to specify a backend topology file that mpirun shall use for its mapping operations. Create a new "set_topology" function in opal hwloc to support it.
This commit was SVN r28682.
some relevant updates/new functionality in the opal/mca/hwloc and
orte/mca/rmaps bases. This work was mainly developed by Mellanox,
with a bunch of advice from Ralph Castain, and some minor advice from
Brice Goglin and Jeff Squyres.
Even though this is mainly Mellanox's work, Jeff is committing only
for logistical reasons (he holds the hg+svn combo tree, and can
therefore commit it directly back to SVN).
-----
Implemented distance-based mapping algorithm as a new "mindist"
component in the rmaps framework. It allows mapping processes by NUMA
due to PCI locality information as reported by the BIOS - from the
closest to device to furthest.
To use this algorithm, specify:
{{{mpirun --map-by dist:<device_name>}}}
where <device_name> can be mlx5_0, ib0, etc.
There are two modes provided:
1. bynode: load-balancing across nodes
1. byslot: go through slots sequentially (i.e., the first nodes are
more loaded)
These options are regulated by the optional ''span'' modifier; the
command line parameter looks like:
{{{mpirun --map-by dist:<device_name>,span}}}
So, for example, if there are 2 nodes, each with 8 cores, and we'd
like to run 10 processes, the mindist algorithm will place 8 processes
to the first node and 2 to the second by default. But if you want to
place 5 processes to each node, you can add a span modifier in your
command line to do that.
If there are two NUMA nodes on the node, each with 4 cores, and we run
6 processes, the mindist algorithm will try to find the NUMA closest
to the specified device, and if successful, it will place 4 processes
on that NUMA but leaving the remaining two to the next NUMA node.
You can also specify the number of cpus per MPI process. This option
is handled so that we map as many processes to the closest NUMA as we
can (number of available processors at the NUMA divided by number of
cpus per rank) and then go on with the next closest NUMA.
The default binding option for this mapping is bind-to-numa. It works
if you don't specify any binding policy. But if you specified binding
level that was "lower" than NUMA (i.e hwthread, core, socket) it would
bind to whatever level you specify.
This commit was SVN r28552.
* Use the hwloc logical index, not the os_index. Fixes problems with
opal_hwloc_base_cset2str() output (e.g., --report-bindings output)
on machines where the os_index is not tightly packed in the range
![0, n-1]
This commit was SVN r27394.
ompi/mca/sbgp/basesmsocket
orte/mca/rmaps/lama
Remove stale configure.params files from the sbgp framework as the OMPI build system no longer looks at those files.
This commit was SVN r27377.
Cannot start the data clearing at the root object level as the root object has a different struct attached to userdata.
This commit was SVN r27357.
The following Trac tickets were found above:
Ticket 3322 --> https://svn.open-mpi.org/trac/ompi/ticket/3322
This now results in the procs being bound within their assigned location. It also causes us to use only the 0th HT on a core unless --use-hwthread-cpus has been specified (in which case, we use all the HTs in a core). Bind to core binds you to all HTs regardless - the --use-hwthread-cpus only impacts the oversubscribed determination and when binding to HT.
cmr:v1.7
This commit was SVN r27342.
* NULL's out the hwloc_obj_t->userdata in
hwloc_base_util.c:free_object() and
hwloc_base_util.c:opal_hwloc_base_free_topology() after it has been
OBJ_RELEASE'd.
* Adds a userdata field to opal_hwloc_topo_data_t. This field will
be used in an upcoming rmaps component ("lama") to cache some
associated data during hardware tree traversals.
This commit was SVN r26938.
* opal_hwloc_base_cset2str(): Make a human-readable string of a
hwloc_cpuset_t (e.g., socket 2[core 3[hwt 1]])
* opal_hwloc_base_cset2mapstr(): Make a map-like string of a
hwloc_cpuset_t (e.g., [B./..])
This commit was SVN r26532.
* Remove paffinity, maffinity, and carto frameworks -- they've been
wholly replaced by hwloc.
* Move ompi_mpi_init() affinity-setting/checking code down to ORTE.
* Update sm, smcuda, wv, and openib components to no longer use carto.
Instead, use hwloc data. There are still optimizations possible in
the sm/smcuda BTLs (i.e., making multiple mpools). Also, the old
carto-based code found out how many NUMA nodes were ''available''
-- not how many were used ''in this job''. The new hwloc-using
code computes the same value -- it was not updated to calculate how
many NUMA nodes are used ''by this job.''
* Note that I cannot compile the smcuda and wv BTLs -- I ''think''
they're right, but they need to be verified by their owners.
* The openib component now does a bunch of stuff to figure out where
"near" OpenFabrics devices are. '''THIS IS A CHANGE IN DEFAULT
BEHAVIOR!!''' and still needs to be verified by OpenFabrics vendors
(I do not have a NUMA machine with an OpenFabrics device that is a
non-uniform distance from multiple different NUMA nodes).
* Completely rewrite the OMPI_Affinity_str() routine from the
"affinity" mpiext extension. This extension now understands
hyperthreads; the output format of it has changed a bit to reflect
this new information.
* Bunches of minor changes around the code base to update names/types
from maffinity/paffinity-based names to hwloc-based names.
* Add some helper functions into the hwloc base, mainly having to do
with the fact that we have the hwloc data reporting ''all''
topology information, but sometimes you really only want the
(online | available) data.
This commit was SVN r26391.
(http://www.open-mpi.org/community/lists/devel/2012/04/10905.php), set
opal_cache_line_size via hwloc data, if we have it.
opal_cache_line_size will be set to an hwloc-inspired value by the end
of orte_init(), but will always have a safe value to use (i.e., a
default value 128) -- even before opal_init() has completed.
Default to the same value of 128 that Open MPI has used for several
years if a) we have no hwloc data, or b) we weren't able to find L2
objects in the hwloc data.
This commit was SVN r26322.
Roll in the ORTE state machine. Remove last traces of opal_sos. Remove UTK epoch code.
Please see the various emails about the state machine change for details. I'll send something out later with more info on the new arch.
This commit was SVN r26242.
1. no binding support - indicated by a negative return code from get_cpubind
2. binding supported, but not bound - the bitset returned by get_cpubind is the same as the available cpuset
3. binding supported and bound - bitset from get_cpubind is a subset of available cpuset
4. only one cpu is available - in this case, get_cpubind matches the available cpuset, but we are effectively bound
This commit was SVN r25957.
https://svn.open-mpi.org/trac/ompi/wiki/ProcessPlacement
The wiki page is incomplete at the moment, but I hope to complete it over the next few days. I will provide updates on the devel list. As the wiki page states, the default and most commonly used options remain unchanged (except as noted below). New, esoteric and complex options have been added, but unless you are a true masochist, you are unlikely to use many of them beyond perhaps an initial curiosity-motivated experimentation.
In a nutshell, this commit revamps the map/rank/bind procedure to take into account topology info on the compute nodes. I have, for the most part, preserved the default behaviors, with three notable exceptions:
1. I have at long last bowed my head in submission to the system admin's of managed clusters. For years, they have complained about our default of allowing users to oversubscribe nodes - i.e., to run more processes on a node than allocated slots. Accordingly, I have modified the default behavior: if you are running off of hostfile/dash-host allocated nodes, then the default is to allow oversubscription. If you are running off of RM-allocated nodes, then the default is to NOT allow oversubscription. Flags to override these behaviors are provided, so this only affects the default behavior.
2. both cpus/rank and stride have been removed. The latter was demanded by those who didn't understand the purpose behind it - and I agreed as the users who requested it are no longer using it. The former was removed temporarily pending implementation.
3. vm launch is now the sole method for starting OMPI. It was just too darned hard to maintain multiple launch procedures - maybe someday, provided someone can demonstrate a reason to do so.
As Jeff stated, it is impossible to fully test a change of this size. I have tested it on Linux and Mac, covering all the default and simple options, singletons, and comm_spawn. That said, I'm sure others will find problems, so I'll be watching MTT results until this stabilizes.
This commit was SVN r25476.
Use hwloc to obtain the cpuset for each process during mpi_init, and share that info in the modex. As it arrives, use a new opal_hwloc_base utility function to parse the value against the local proc's cpuset and determine where they overlap. Cache the value in the pmap object as it may be referenced multiple times.
Thus, the return value from orte_ess.proc_get_locality is a 16-bit bitmask that describes the resources being shared with you. This bitmask can be tested using the macros in opal/mca/paffinity/paffinity.h
Locality is available for all procs, whether launched via mpirun or directly with an external launcher such as slurm or aprun.
This commit was SVN r25331.
maffinity_base_bind_failure_action MCA params to the hwloc base
(hwloc_base_alloc_polocy and hwloc_base_bind_failure_action). Since
these MCA parameters were never on a release branch, I'm just
moving/renaming them outright and not leaving aliases to the old
names.
Note that some upper layer needs to call
opal_hwloc_base_set_process_membind_policy() to set the
set-by-MCA-param process-wide memory affinity policy. We can't do
this automatically during hwloc_base_open() because, for reasons
described elsewhere, opal_hwloc_topology is not automatically filled
during hwloc_base_open() (in short: potential scalability issues when
launching many MPI processes simultaneously on a single machine, for
example).
This commit was SVN r25156.
