1
1
Граф коммитов

20 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
213b5d5c6e Per long threads on the mailing list and much confusion discussion
about linkers, have all OPAL, ORTE, and OMPI components '''not'' link
against the OPAL, ORTE, or OMPI libraries.

See ttp://www.open-mpi.org/community/lists/users/2007/10/4220.php for
details (or https://svn.open-mpi.org/trac/ompi/wiki/Linkers for a
better-formatted version of the same info).

This commit was SVN r16968.
2007-12-15 13:32:02 +00:00
Ralph Castain
54b2cf747e These changes were mostly captured in a prior RFC (except for #2 below) and are aimed specifically at improving startup performance and setting up the remaining modifications described in that RFC.
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 The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info.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.
2007-10-05 19:48:23 +00:00
Brian Barrett
39a6057fc6 A number of improvements / changes to the RML/OOB layers:
* General TCP cleanup for OPAL / ORTE
  * Simplifying the OOB by moving much of the logic into the RML
  * Allowing the OOB RML component to do routing of messages
  * Adding a component framework for handling routing tables
  * Moving the xcast functionality from the OOB base to its own framework

Includes merge from tmp/bwb-oob-rml-merge revisions:

    r15506, r15507, r15508, r15510, r15511, r15512, r15513

This commit was SVN r15528.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r15506
  r15507
  r15508
  r15510
  r15511
  r15512
  r15513
2007-07-20 01:34:02 +00:00
Josh Hursey
6cdfefad87 Fix portals BTL and cnos RML.
Both were failing due to interface changes that were never 
applied to them properly.

This commit was SVN r15082.
2007-06-14 18:49:41 +00:00
Ralph Castain
4fff584a68 Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.

Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.

Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.

With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.

Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".

This commit was SVN r14711.
2007-05-21 18:31:28 +00:00
Rich Graham
5359cee937 declare undeclared function, so that the code will compile.
This commit was SVN r14625.
2007-05-09 04:47:40 +00:00
Ralph Castain
5f94d6d791 Fix the cnos rml to match revised xcast API
This commit was SVN r14478.
2007-04-23 19:07:44 +00:00
Jeff Squyres
51f286d737 Just like r14289 on the ORTE trunk:
Per discussions with Brian and Ralph, make a slight correction in
where components are installed. Use $pkglibdir, not $libdir/openmpi,
so that when compiled in the orte trunk, components are installed to
the right directory (because the component search patch is checking
$pkglibdir).

This commit was SVN r14345.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r14289
2007-04-12 11:19:42 +00:00
Brian Barrett
a34e67d743 Remove unneeded PARAM_INIT_FILE variable in configure.params files used by
components that use configure.m4 for configuration or are always built. 
The macro has not been needed since moving to configure types other than
configure.stub

Fixes trac:590

This commit was SVN r13031.

The following Trac tickets were found above:
  Ticket 590 --> https://svn.open-mpi.org/trac/ompi/ticket/590
2007-01-08 03:44:22 +00:00
Brian Barrett
6f8b366acb Rename liborte to libopen-rte and libopal to libopen-pal per telecon today
and bug #632.

Refs trac:632

This commit was SVN r12762.

The following Trac tickets were found above:
  Ticket 632 --> https://svn.open-mpi.org/trac/ompi/ticket/632
2006-12-05 18:27:24 +00:00
George Bosilca
6afa4c6c64 Windows friendly version. We have to split the OMPI_DECLSPEC in at least 3
different macros, one for each project. Therefore, now we have OPAL_DECLSPEC,
ORTE_DECLSPEC and OMPI_DECLSPEC. Please use them based on the sub-project.

This commit was SVN r11270.
2006-08-20 15:54:04 +00:00
Brian Barrett
1d3132a725 * some pending Red Storm related updates to ORTE
This commit was SVN r9128.
2006-02-23 04:55:39 +00:00
Brian Barrett
566a050c23 Next step in the project split, mainly source code re-arranging
- move files out of toplevel include/ and etc/, moving it into the
    sub-projects
  - rather than including config headers with <project>/include, 
    have them as <project>
  - require all headers to be included with a project prefix, with
    the exception of the config headers ({opal,orte,ompi}_config.h
    mpi.h, and mpif.h)

This commit was SVN r8985.
2006-02-12 01:33:29 +00:00
Jeff Squyres
42ec26e640 Update the copyright notices for IU and UTK.
This commit was SVN r7999.
2005-11-05 19:57:48 +00:00
Andrew Friedley
555ae37255 Add lib{opal,orte,mpi}.la to appropriate LIBADD's, some whitespace cleanup as well.
This commit was SVN r7477.
2005-09-22 12:28:54 +00:00
Brian Barrett
93e28ebe74 * hack up rml_cnos to work with last round of orte changes
* updates to the red storm configure setup
* fix missing header if no timer components are found

This commit was SVN r7402.
2005-09-16 02:25:41 +00:00
Brian Barrett
ed56e743b7 * update configure.ac to use the modern version of AC_INIT and
AM_INIT_AUTOMAKE, instead of the deprecated version.
* Work around dumbness in modern AC_INIT that requires the version
  number to be set at autoconf time (instead of at configure time, as
  it was before).  Set the version number, minus the subversion r number,
  at autoconf time.  Override the internal variables to include the r
  number (if needed) at configure time.  Basically, the right thing
  should always happen.  The only place it might not is the version
  reported as part of configure --help will not have an r number.
* Since AM_INIT_AUTOMAKE taks a list of options, no need to specify
  them in all the Makefile.am files.
* Addes support for subdir-objects, meaning that object files are put
  in the directory containing source files, even if the Makefile.am is
  in another directory.  This should start making it feasible to
  reduce the number of Makefile.am files we have in the tree, which
  will greatly reduce the time to run autogen and configure.

This commit was SVN r7211.
2005-09-07 05:54:53 +00:00
Brian Barrett
2852772b32 * add a bunch of svn:ignored files
* Add Portals UTCP reference sds for when we are using the portals
  reference implementation without the ORTE starters (when we want to
  pretend like we're on Red Storm, only with a debugger and valgrind and
  possibly even a printf that actually works...)
* Add super-secret --with flag to cnos rml to enable the cnos rml but
  disable cnos_barrier (for use with portals utcp reference implementation)

This commit was SVN r6642.
2005-07-28 06:23:34 +00:00
Brian Barrett
93ddb4bf73 * some fixups for the cnos components
This commit was SVN r6637.
2005-07-28 00:11:09 +00:00
Brian Barrett
6aa464b67e More changes from Red Storm port
- only call sched_yield if it exists
  - don't fail out if modex doens't work in ob1
  - bunch of fixes for Portals BTL
  - add cnos rml component
  - add NULL gpr component (should only be used if replica AND proxy
    fail to load)  

This commit was SVN r6629.
2005-07-27 23:07:14 +00:00