1
1
Граф коммитов

3663 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
5295902ebe Fixes trac:1285:
* allow receive_queues to be specified in the INI file 
 * detect when multiple different receive_queues are specified and 
   gracefully abort 

However, accomplishing these goals ran into multiple difficulties. By 
putting receive_queues in the INI file: 

 1. we may not find the value until we've already traversed multiple HCAs 
 1. we may find multiple different receive_queues values

But since the openib btl initializes as it discovers each HCA/port/LID
(including the BSRQ data), if we find a new receive_queues value late
in the discovery process, then all the BSRQ data that was previously
initialized will likely be invalid. So I had to pull all the BSRQ
initialization out until after the rest of the discovery /
initialization process.

Additionally, note that if the user specifies the MCA parameter
btl_openib_receive_queues, it trumps whatever was in the INI file. So
in this case, there can never be a receive_queues conflict.  This
commit does the following (Jon wrote part of this, too):

 * adapt _ini.c to accept the "receive_queues" field in the file 
 * move 90% of _setup_qps() from _ini.c to _component.c 
 * move what was left of _setup_qps() into the main 
   _register_mca_params() function 
 * adapt init_one_hca() to detect conflicting receive_queues values 
   from the INI file 
 * after the _component.c loop calling init_one_hca(): 
   * call setup_qps() to parse the final receive_queues string value 
   * traverse all resulting btls and initialize their HCAs (if they
     weren't already): setup some lists and call prepare_hca_for_use()

I tested this code on a dual-HCA system where I artificially put in 
differing receive_queues values in the INI file for the two different 
types of HCAs that I have and it all seemed to work.

This commit was SVN r18450.

The following Trac tickets were found above:
  Ticket 1285 --> https://svn.open-mpi.org/trac/ompi/ticket/1285
2008-05-18 18:50:56 +00:00
Jeff Squyres
87d4201bdf From our faithful Debian package maintainers: remove some lint-quality
lines from the man pages.

This commit was SVN r18449.
2008-05-16 14:58:52 +00:00
Jeff Squyres
1cc663ebf6 Change this back to use opal_init_util() -- using orte_init() mucks
with the C++ memory allocator.  Let's not go there.

This commit was SVN r18447.
2008-05-16 14:18:56 +00:00
Jeff Squyres
caacaadb0a Minor shuffling of code: no need to query the GID in the iWARP case.
This commit was SVN r18446.
2008-05-16 03:36:48 +00:00
Jeff Squyres
9f1b5237fe Ensure to return an error rather than continue
This commit was SVN r18445.
2008-05-16 03:36:11 +00:00
Jeff Squyres
6546898f09 Minor style cleanups; nothing very important in this commit.
This commit was SVN r18444.
2008-05-16 03:28:20 +00:00
Jeff Squyres
5c91f53848 Fix a minor memory leak
This commit was SVN r18443.
2008-05-16 03:27:42 +00:00
Rolf vandeVaart
375406e1fa Remove the ignore files as decided at Tuesday's developers conference call. Now, hierarchical collectives will be compiled in but the priority is still at 0 requiring a user to set mca parameters to enable them.
This commit was SVN r18440.
2008-05-15 01:26:52 +00:00
Josh Hursey
35a2af28d1 Cleanup the CRCP Coord timing functionality. Provides a rough assessment of time each element of the algorithm is taking.
There are more details in the code regarding how to use this feature.

Also shift a few of the orte_output back to opal_output. I'm experiencing an odd problem with locks in the oob/tcp when using orte_output. I haven't had time to track it down yet.

This commit was SVN r18439.
2008-05-14 19:54:20 +00:00
Jeff Squyres
671f0c379d Remove a whole pile of orte/util/show_help.h's that I missed. :-(
This commit was SVN r18437.
2008-05-14 11:32:33 +00:00
Jeff Squyres
fb17097de4 Make ompi_info correctly display "filter" components
This commit was SVN r18435.
2008-05-13 20:56:20 +00:00
Jeff Squyres
e7ecd56bd2 This commit represents a bunch of work on a Mercurial side branch. As
such, the commit message back to the master SVN repository is fairly
long.

= ORTE Job-Level Output Messages =

Add two new interfaces that should be used for all new code throughout
the ORTE and OMPI layers (we already make the search-and-replace on
the existing ORTE / OMPI layers):

 * orte_output(): (and corresponding friends ORTE_OUTPUT,
   orte_output_verbose, etc.)  This function sends the output directly
   to the HNP for processing as part of a job-specific output
   channel.  It supports all the same outputs as opal_output()
   (syslog, file, stdout, stderr), but for stdout/stderr, the output
   is sent to the HNP for processing and output.  More on this below.
 * orte_show_help(): This function is a drop-in-replacement for
   opal_show_help(), with two differences in functionality:
   1. the rendered text help message output is sent to the HNP for
      display (rather than outputting directly into the process' stderr
      stream)
   1. the HNP detects duplicate help messages and does not display them
      (so that you don't see the same error message N times, once from
      each of your N MPI processes); instead, it counts "new" instances
      of the help message and displays a message every ~5 seconds when
      there are new ones ("I got X new copies of the help message...")

opal_show_help and opal_output still exist, but they only output in
the current process.  The intent for the new orte_* functions is that
they can apply job-level intelligence to the output.  As such, we
recommend that all new ORTE and OMPI code use the new orte_*
functions, not thei opal_* functions.

=== New code ===

For ORTE and OMPI programmers, here's what you need to do differently
in new code:

 * Do not include opal/util/show_help.h or opal/util/output.h.
   Instead, include orte/util/output.h (this one header file has
   declarations for both the orte_output() series of functions and
   orte_show_help()).
 * Effectively s/opal_output/orte_output/gi throughout your code.
   Note that orte_output_open() takes a slightly different argument
   list (as a way to pass data to the filtering stream -- see below),
   so you if explicitly call opal_output_open(), you'll need to
   slightly adapt to the new signature of orte_output_open().
 * Literally s/opal_show_help/orte_show_help/.  The function signature
   is identical.

=== Notes ===

 * orte_output'ing to stream 0 will do similar to what
   opal_output'ing did, so leaving a hard-coded "0" as the first
   argument is safe.
 * For systems that do not use ORTE's RML or the HNP, the effect of
   orte_output_* and orte_show_help will be identical to their opal
   counterparts (the additional information passed to
   orte_output_open() will be lost!).  Indeed, the orte_* functions
   simply become trivial wrappers to their opal_* counterparts.  Note
   that we have not tested this; the code is simple but it is quite
   possible that we mucked something up.

= Filter Framework =

Messages sent view the new orte_* functions described above and
messages output via the IOF on the HNP will now optionally be passed
through a new "filter" framework before being output to
stdout/stderr.  The "filter" OPAL MCA framework is intended to allow
preprocessing to messages before they are sent to their final
destinations.  The first component that was written in the filter
framework was to create an XML stream, segregating all the messages
into different XML tags, etc.  This will allow 3rd party tools to read
the stdout/stderr from the HNP and be able to know exactly what each
text message is (e.g., a help message, another OMPI infrastructure
message, stdout from the user process, stderr from the user process,
etc.).

Filtering is not active by default.  Filter components must be
specifically requested, such as:

{{{
$ mpirun --mca filter xml ...
}}}

There can only be one filter component active.

= New MCA Parameters =

The new functionality described above introduces two new MCA
parameters:

 * '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that
   help messages will be aggregated, as described above.  If set to 0,
   all help messages will be displayed, even if they are duplicates
   (i.e., the original behavior).
 * '''orte_base_show_output_recursions''': An MCA parameter to help
   debug one of the known issues, described below.  It is likely that
   this MCA parameter will disappear before v1.3 final.

= Known Issues =

 * The XML filter component is not complete.  The current output from
   this component is preliminary and not real XML.  A bit more work
   needs to be done to configure.m4 search for an appropriate XML
   library/link it in/use it at run time.
 * There are possible recursion loops in the orte_output() and
   orte_show_help() functions -- e.g., if RML send calls orte_output()
   or orte_show_help().  We have some ideas how to fix these, but
   figured that it was ok to commit before feature freeze with known
   issues.  The code currently contains sub-optimal workarounds so
   that this will not be a problem, but it would be good to actually
   solve the problem rather than have hackish workarounds before v1.3 final.

This commit was SVN r18434.
2008-05-13 20:00:55 +00:00
Jon Mason
125eb5a2ed Convert from the Linux ifaddrs to the OMPI ifaddrs, which should unbreak Solaris.
This commit was SVN r18433.
2008-05-13 18:34:22 +00:00
Jeff Squyres
d8e5608053 Remove all retransmission code; the IBCM kernel module handles all of
that for us.

This commit was SVN r18432.
2008-05-13 16:10:34 +00:00
Jon Mason
74bf1ae25f Fix compiler warnings
This commit was SVN r18431.
2008-05-13 16:01:58 +00:00
Jon Mason
4ead9442b5 Add in IDs for all Chelsio iWARP capable adapters
This commit was SVN r18428.
2008-05-12 21:59:03 +00:00
Jeff Squyres
6b26895ad4 A little style update -- constants on the left...
This commit was SVN r18426.
2008-05-12 12:05:16 +00:00
Jeff Squyres
16cde0e5fa Fix compile error on older OFED systems
This commit was SVN r18425.
2008-05-12 11:56:14 +00:00
Gleb Natapov
6844ff32ba Return OMPI_ERR_RESOURCE_BUSY from sm->btl_send() function if there is no place in cb. This will prevent OB1 from doing early completion of small sends.
This commit was SVN r18424.
2008-05-12 07:15:29 +00:00
Gleb Natapov
31d2797a2f If RDMA PUT is received before ACK and registration of memory fails don't
start sending fragment by copy in/out before ACK is received as we don't
know pointer to receive request yet.

Pipeline protocol sometimes doesn't send ACK though, so this case is still
broken.

This commit was SVN r18423.
2008-05-11 12:40:55 +00:00
Gleb Natapov
0827e537fa Don't include rdma/rdma_cma.h if !OMPI_HAVE_RDMACM.
This commit was SVN r18422.
2008-05-11 11:58:02 +00:00
Rainer Keller
4b89706dfe - Properly check for valid output parameters...
This commit was SVN r18419.
2008-05-09 08:39:24 +00:00
Jon Mason
99ab66e131 RDMACM code cleanup
This patch adds some much needed comments, reduces the amount of code
wrapping, and rearrges and removes redundant code.

This commit was SVN r18417.
2008-05-08 21:20:12 +00:00
Josh Hursey
da2f1c58e2 Some checkpoint/restart cleanup.
* Remove the opal_only option. This was suffering from bit rot, and no one uses it. It can be added back fairly easily if wanted.
 * Cleanup metadata interactions at the local level.
 * Touch up some of the INC funcitonality (fix typos and a minor ordering issue)

This commit was SVN r18416.
2008-05-08 18:47:47 +00:00
Jon Mason
88e5f2a339 Abstract iWARP subnet ID functions (sans build break)
The iWARP subnet ID determination should not be in the RDMACM cpc, as
it was in the preversion, as this violates the cpc abstract that is
present throughout the code.  Also, this patch uses the opal_list_t
data struct instead of using its own linked lists.

This attempt includes *iwarp.c and *iwarp.h

This commit was SVN r18414.
2008-05-08 14:38:14 +00:00
Jeff Squyres
60f39a30f6 Revert r18409; that commit broke the build because it forgot to add
the btl_openib_iwarp.c and btl_openib_iwarp.h files.

This commit was SVN r18410.

The following SVN revision numbers were found above:
  r18409 --> open-mpi/ompi@056bbb68c8
2008-05-08 00:22:21 +00:00
Jon Mason
056bbb68c8 Abstract iWARP subnet ID functions
The iWARP subnet ID determination should not be in the RDMACM cpc, as
it was in the preversion, as this violates the cpc abstract that is
present throughout the code.  Also, this patch uses the opal_list_t
data struct instead of using its own linked lists.

This commit was SVN r18409.
2008-05-07 23:59:43 +00:00
Ralph Castain
7c7b9b0486 Do a little cleanup on the opal graph class and opal carto framework to conform to OMPI naming conventions and avoid potential conflict with user applications - no change in functionality, passes carto test program
This commit was SVN r18407.
2008-05-07 19:33:49 +00:00
Jeff Squyres
e76d2dd518 This is an internal function; this error won't happen.
This commit was SVN r18406.
2008-05-07 19:00:34 +00:00
Jeff Squyres
157cea378f * A few fixes to make IP address and port number comparisons properly
* A few indenting and style fixes

This commit was SVN r18405.
2008-05-07 16:56:07 +00:00
Jeff Squyres
bfae8ea828 The comment wasn't long enough; I felt the need to make it longer (and
explain a little more ;-) ).

This commit was SVN r18404.
2008-05-07 16:53:05 +00:00
Shiqing Fan
19fe973095 The most important thing, otherwise it won't work properly.
This commit was SVN r18403.
2008-05-07 16:38:09 +00:00
Jeff Squyres
63abb3eb9b Clarify a comment / fix typos.
This commit was SVN r18402.
2008-05-07 14:51:36 +00:00
Shiqing Fan
897fe404c0 Get rid of the warning message from the compiler.
This commit was SVN r18401.
2008-05-07 14:31:42 +00:00
Shiqing Fan
8088ec8bce More for non-blocking communication.
This commit was SVN r18400.
2008-05-07 13:00:28 +00:00
Shiqing Fan
8393fb5d47 Use the new memchecker_call function for memory checking of non-blocking communication.
This commit was SVN r18399.
2008-05-07 12:28:51 +00:00
Shiqing Fan
aed20e213b Using a more general way for memchcker call, which is similar to the convertor call. The convertor call is dependent on structure convertor, but this is not available in some places. Now we are dependent only on datatype, which will have the same behavior as convertor, but more flexible.
This commit was SVN r18398.
2008-05-07 12:23:07 +00:00
Ralph Castain
ff70636024 Allgather_list needs its own tag to avoid conflicting with the allgather modex operation.
All spawned procs must decode the port of the spawning process so they can communicate in direct routed mode.

This fixes comm_spawn for all routing modes.

This commit was SVN r18395.
2008-05-07 03:03:56 +00:00
Rolf vandeVaart
0e32dd1022 Add MPI_Alltoallv to tuned collectives and add a pairwise implementation of MPI_Alltoallv. However, do not change the default behavior for now. The only way to use new pairwise implementation is via mca parameters.
This commit was SVN r18394.
2008-05-07 02:31:24 +00:00
Jon Mason
502d164908 Create subnet ID's for iWARP.
This enables subnet differientation for iWARP devices, and rearrange
initilization so that the services are available when they are needed.

This commit was SVN r18393.
2008-05-06 22:43:52 +00:00
Jon Mason
9c724128f8 Handle no IP Address in rdmacm more resiliently
If there is no IP Address, have rdmacm log the correct error and let
another cpc have a go at it.  This is being done by splitting off the
IP address checking logic for the modex message creation, and having
it log the correct error in the error case.

This commit was SVN r18392.
2008-05-06 22:31:29 +00:00
Jon Mason
46bfd42c09 Fix compile warnings in rdmacm
Fix some reported compiler warnings and make the code a little prettier.

This commit was SVN r18391.
2008-05-06 22:19:28 +00:00
Jon Mason
9066168cd1 Prevent iWARP qp flush errors.
For iWARP, the TCP connection is tied to the QP once the QP is in RTS.  
And destroying the QP is thus tied to connection teardown for iWARP.  
This is a key distinction from IB, I think.   Anyway, to destroy the 
connection in iWARP you must move the QP out of RTS, either into CLOSING 
for a nice graceful close, or to ERROR if you want to be rude.  In both 
cases, all pending non-completed SQ and RQ WRs must be flushed.

This patch ignores all flush errors reaped by the cq and removes an
earlier attempt to work around this in the rdmacm cpc.

This commit was SVN r18388.
2008-05-06 21:57:40 +00:00
Josh Hursey
9971bc9d95 Merge in the mca_base_select changes per RFC:
http://www.open-mpi.org/community/lists/devel/2008/04/3779.php

{{{
svn merge -r 18276:18380 https://svn.open-mpi.org/svn/ompi/tmp-public/jjh-mca-play .
}}}

Any components not in the trunk, but in one of the effected frameworks *must* be
updated. Contact the list, look at the RFC, or look at the diff for how to do this.

Sorry for the early commit of this, but I wanted to get it in today (per RFC) and
didn't know if I would have a chance later today.

This commit was SVN r18381.
2008-05-06 18:08:45 +00:00
Jeff Squyres
a06d4023b8 Oops -- missed one sys_errlist -> strerror().
This commit was SVN r18378.
2008-05-06 13:22:36 +00:00
Jeff Squyres
4154e587de strerror() is much better.
This commit was SVN r18376.
2008-05-05 21:06:07 +00:00
Shiqing Fan
f35a06119c Use memchecker_convertor_call function instead the old one. Move the function to the place that we can use convertor.
This commit was SVN r18370.
2008-05-05 13:57:27 +00:00
Jon Mason
a3bf503e01 Remove error on rdma cm
If there are multiple QP's, RDMACM will not send a message if the
qpnum != 0.  In doing so, it will log an error unecessarily.  This
removes that.

This commit was SVN r18363.
2008-05-02 20:12:01 +00:00
Jon Mason
3989981578 Enable support of num_proc > num_nodes
Add the logic to support using port numbers, instead of simply using
the IP address of the sending node to determine which endpoint to
connect.  Since each process calls the cpc query function, it will
generate its own port to listen on thus enablign this to work.

This commit was SVN r18362.
2008-05-02 16:20:28 +00:00
Jeff Squyres
ba5615a18f Merge in /tmp-public/cpc3 branch to trunk. oob/xoob still remains the
default CPC.

This commit was SVN r18356.
2008-05-02 11:52:33 +00:00