1
1
Граф коммитов

159 Коммитов

Автор SHA1 Сообщение Дата
Gilles Gouaillardet
352b05a552 rmaps: warn if oversubscribing when manually setting the number of hosts
This is a port of the v1.10 series one-off open-mpi/ompi-release@8c5ce45ab6
2015-12-28 10:38:57 +09:00
Ralph Castain
d97bc29102 Remove OPAL_HAVE_HWLOC qualifier and error out if --without-hwloc is given 2015-09-04 16:54:40 -07:00
Nathan Hjelm
4d92c9989e more c99 updates
This commit does two things. It removes checks for C99 required
headers (stdlib.h, string.h, signal.h, etc). Additionally it removes
definitions for required C99 types (intptr_t, int64_t, int32_t, etc).

Signed-off-by: Nathan Hjelm <hjelmn@me.com>
2015-06-25 10:14:13 -06:00
Ralph Castain
869041f770 Purge whitespace from the repo 2015-06-23 20:59:57 -07:00
Ralph Castain
869b2891c4 When doing comm-spawn, track the last object we bound to and ensure that we start the next job on the next object so we avoid overload situations when they aren't necessary 2015-06-17 09:20:08 -07:00
Nathan Hjelm
45e053dbce orte: use C99 subobject naming for component initialization
This commit helps future-proof orte components by initializing each
component member by name.

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-04-18 10:29:58 -06:00
Howard Pritchard
bf89131f9e add owner files to opa/ompi/orte mca directories
This commit adds an owner file in each of the component directories
for each framework.  This allows for a simple script to parse
the contents of the files and generate, among other things, tables
to be used on the project's wiki page.  Currently there are two
"fields" in the file, an owner and a status.  A tool to parse
the files and generate tables for the wiki page will be added
in a subsequent commit.
2015-02-22 15:10:23 -07:00
Ralph Castain
842aaf6167 Correctly end mapping oversubscribed nodes round-robin byslot
cmr=v1.8.3:reviewer=rhc

This commit was SVN r32616.
2014-08-27 16:15:18 +00:00
Ralph Castain
5bb5b22573 When a user asks for cpus/rank > 1 and only has one slot, we need to ensure we always map at least one process when they don't tell us -np
cmr=v1.8.2:reviewer=rhc:subject=correct num_procs in corner case

This commit was SVN r32142.
2014-07-04 17:00:35 +00:00
Ralph Castain
3f04d50cb0 Per the ticket, resolve our handling of overload conditions to provide a more consistent response. If we are overloaded (i.e., attempting to bind more processes to a location than the number of cpus under that location), then we consider the following conditions:
(a) default binding policy is in effect. In this case, we will emit a
warning and default to not binding unless the user provided the
"oversubscribe" or "overload" modifier to the "bind-to" option.

(b) user-specified binding policy is in effect. In this case, we will
error out unless the user provided the "oversubscribe" or "overload"
modifier to the "bind-to" option as we cannot meet the directive.

Either "bind-to" modifier (oversubscribe or overload) will be accepted for
now - in 1.9, we will deprecate the "overload" term in favor of
"oversubscribe".

Also added the ability to accept a --bind-to modifier without specifying the binding policy itself so a user can specify overload-allowed with the default policy.

Closes trac:4345

cmr=v1.8.2:reviewer=rhc:subject=resolve handling of overload conditions

This commit was SVN r32005.

The following Trac tickets were found above:
  Ticket 4345 --> https://svn.open-mpi.org/trac/ompi/ticket/4345
2014-06-14 15:38:32 +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
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
11faab1091 The final step of the RFC: convert the <foo>libdir and friends to fit their respective code areas, and equate them all at the top. Note that we can't entirely separate things as the opal_install_dirs framework can't handle separated locations for the various trees.
This commit was SVN r31679.
2014-05-08 02:01:35 +00:00
Ralph Castain
714cb8f573 Silence warnings
cmr=v1.8:reviewer=rhc

This commit was SVN r31248.
2014-03-27 14:16:54 +00:00
Ralph Castain
390645ac2a Per patch from Tetsuya Mishima, do a nicer job of warning the user that we need to map to a higher level to get the number of requested cpus/rank. Also, change the mapping policy to "byslot" when falling back to that option.
cmr=v1.8:reviewer=rhc

This commit was SVN r31196.
2014-03-24 15:47:29 +00:00
Ralph Castain
fc2dd6ac48 Per Jeff's request, add a more detailed comment as to why we are turning off the warning at this time.
Refs trac:4339

This commit was SVN r30948.

The following Trac tickets were found above:
  Ticket 4339 --> https://svn.open-mpi.org/trac/ompi/ticket/4339
2014-03-06 02:17:25 +00:00
Ralph Castain
a2b539c763 Per the telecon, silence the warning for 1.7.5 to give us time to consider a better permanent solution
Refs trac:4339

This commit was SVN r30941.

The following Trac tickets were found above:
  Ticket 4339 --> https://svn.open-mpi.org/trac/ompi/ticket/4339
2014-03-05 03:02:29 +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
88b0e0cc6d Allow the user to turn off the oversubscribed-binding warning if overload-allowed has been provided
Refs trac:4317

This commit was SVN r30892.

The following Trac tickets were found above:
  Ticket 4317 --> https://svn.open-mpi.org/trac/ompi/ticket/4317
2014-02-28 17:55:53 +00:00
Ralph Castain
4a645f0342 Add detection of oversubscription with binding requested - if binding requested to core or hwt, warn and do not bind or else we will hurt performance. Also, if no binding directive was given, turn off the default binding
Refs trac:4317

This commit was SVN r30888.

The following Trac tickets were found above:
  Ticket 4317 --> https://svn.open-mpi.org/trac/ompi/ticket/4317
2014-02-28 16:08:52 +00:00
Ralph Castain
8500247c7b Fix the by-obj mapper in the case where slots are not specified, and so we are in a perpetual oversubscribed state
cmr=v1.7.5:reviewer=rhc

This commit was SVN r30887.
2014-02-28 05:21:46 +00:00
Ralph Castain
a4c3d0a5a0 Add some more debug to the by-obj mapper
This commit was SVN r30884.
2014-02-28 02:52:53 +00:00
Ralph Castain
d109c523b9 Per patch from Tetsuya Mishima, complete the overhaul of the round-robin mappers
Refs trac:4296

This commit was SVN r30861.

The following Trac tickets were found above:
  Ticket 4296 --> https://svn.open-mpi.org/trac/ompi/ticket/4296
2014-02-27 00:43:53 +00:00
Ralph Castain
61a21e4f31 Based on Tetsuya's patch, with some changes, correct the case of map-by node where multiple cpus/rank are requested and result in a non-integer match with num slots. Also correct tests for binding policy given to use the proper macro.
Refs trac:4296

This commit was SVN r30857.

The following Trac tickets were found above:
  Ticket 4296 --> https://svn.open-mpi.org/trac/ompi/ticket/4296
2014-02-26 18:12:23 +00:00
Ralph Castain
b880aa46bd Update the map-by obj and map-by obj:span mappers to correct for errors in computing carryover across the nodes. Be a little less complex in the algorithm so it is easier to follow and debug.
Refs trac:4296

This commit was SVN r30826.

The following Trac tickets were found above:
  Ticket 4296 --> https://svn.open-mpi.org/trac/ompi/ticket/4296
2014-02-25 23:32:43 +00:00
Ralph Castain
c8112c1086 Loadbalancing across nodes (i.e., map-by node) wasn't working correctly - the algorithm relied on the nodes being defined in descending order of slots, or the numbe
r of slots remaing to be assigned being only one/node. Regardless, it didn't work for the case where nodes were defined in ascending order of slots.

Tetsuya's proposed patch didn't solve the problem for me, but it did correct the case where cpus/proc > 1. The final patch requires that we loop over the assignment
 algo until all procs are assigned or all nodes are filled - any remaining procs are then handled in the cleanup loop.

cmr=v1.7.5:reviewer=rhc:subject=fix map-by node for different cases

This commit was SVN r30798.
2014-02-22 16:39:41 +00:00
Ralph Castain
886fee9367 Properly set num_procs when np is not given, but cpus-per-proc is used. Thanks to Tetsuya Mishima for pointing it out
cmr=v1.7.4:reviewer=jsquyres

This commit was SVN r30389.
2014-01-23 05:01:07 +00:00
Ralph Castain
9fcb46d85a Correctly detect and handle oversubscription for comm_spawn
cmr=v1.7.4:reviewer=jsquyres:subject=Correctly detect and handle oversubscription for comm_spawn

This commit was SVN r30186.
2014-01-09 18:27:51 +00:00
Ralph Castain
fb650aed0c Fix how we transfer mapping directives to the job, ensuring that directives that can be given outside of a mapping policy (e.g., oversubscribe and no-use-local) are retained.
cmr=v1.7.4:reviewer=jsquyres:subject=Fix how we transfer mapping directives to the job

This commit was SVN r30155.
2014-01-08 04:25:43 +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
31248c0985 Correctly add support for the "env" MPI_Info key during comm_spawn, update the "map-by", "rank-by", and "bind-to" Info key behaviors to match the new mapping/ranking/binding system, and update all docs and comments to match.
Fix comm_spawn on a single host - with the new default mapping scheme, we were incorrectly computing the number of procs to put on the node.

Refs trac:4003

This commit was SVN r30033.

The following Trac tickets were found above:
  Ticket 4003 --> https://svn.open-mpi.org/trac/ompi/ticket/4003
2013-12-20 20:42:39 +00:00
Ralph Castain
53cd00fe16 By setting a default mapping/ranking/binding policy that wasn't "none", we introduced a problem for users of the Mac and any other machine where sockets aren't defined and/or binding is not supported. Fix that by checking to see if the user specified the failing policy - if not, then fall back to the old map/rank by slot and no binding.
Refs trac:3977

This commit was SVN r29933.

The following Trac tickets were found above:
  Ticket 3977 --> https://svn.open-mpi.org/trac/ompi/ticket/3977
2013-12-17 14:50:10 +00:00
Ralph Castain
8b6d117541 Per the OMPI devel conference that changed our default behaviors:
* default to bind-to core 
* map-by slot if np=2
* map-by socket (balance across sockets on each node) if np > 2
* map-by <obj> will imply rank-by <obj> by default (leave default binding as above) 

Fix a bug in the map-by <obj> mapper where we incorrectly compute the #procs to assign if the #slots > #procs

cmr=v1.7.4:reviewer=jsquyres:subject=Update default binding and mapping values

This commit was SVN r29919.
2013-12-15 17:25:54 +00:00
Ralph Castain
f2c49c6c19 Fix the map-by object mapper to handle cpus-per-proc by accounting for the request when computing the number of procs to put on each object. This ensures that the binding routine doesn't automatically overload the cores.
cmr=v1.7.4:reviewer=jsquyres

This commit was SVN r29843.
2013-12-08 16:59:25 +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
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
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
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
8d2fa3693b First cut at removing the native Windows support. Remove all the Windows-specific components, and the .windows files sprinkled around. Remove the Windows platform files and MTT scripts. Update the NEWS to point Windows users to the cygwin package.
This commit was SVN r28116.
2013-02-26 20:44:56 +00:00
Ralph Castain
2110fb7f95 Add some debug
This commit was SVN r27257.
2012-09-07 04:06:37 +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
95019cc310 Fix a few places where we weren't completely identifying hostfile-based operations against "localhost" entries. Tell the mapper base to be silent when we don't want errors announced because nodes aren't available for mapping (something it is okay if they are fully used). Fix an infinite loop in the file prepositioning code.
This commit was SVN r27210.
2012-08-31 21:28:49 +00:00
Ralph Castain
53b1a1c976 Cleanly error out when someone asks to map-to <object> if that object doesn't exist on a node.
This commit was SVN r26950.
2012-08-04 21:52:36 +00:00
Ralph Castain
61b09a132b Fix bynode mapping of multiple app-contexts
This commit was SVN r26949.
2012-08-03 21:45:40 +00:00
Ralph Castain
9bedb25dda Cleanup some compiler warnings, some of which are actual logic errors
This commit was SVN r26519.
2012-05-29 20:11:51 +00:00
Ralph Castain
bd8b4f7f1e Sorry for mid-day commit, but I had promised on the call to do this upon my return.
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.
2012-04-06 14:23:13 +00:00
Ralph Castain
f531b09a8d Correctly handle -host and -hostfile options. Ensure the initial vm launch constrains itself to the union of specified hosts if those options are given. Get oversubscribe set correctly for that case.
This commit was SVN r25648.
2011-12-14 20:01:15 +00:00
Ralph Castain
15facc4ba6 Fix comm_spawn yet again...add another test
This commit was SVN r25579.
2011-12-06 20:15:40 +00:00