1
1
Граф коммитов

61 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
9613b3176c Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP.
After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach.

I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive.

This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
George Bosilca
e361bcb64c Send optimizations.
1. The send path get shorter. The BTL is allowed to return > 0 to specify that the
   descriptor was pushed to the networks, and that the memory attached to it is 
   available again for the upper layer. The MCA_BTL_DES_SEND_ALWAYS_CALLBACK flag
   can be used by the PML to force the BTL to always trigger the callback.
   Unmodified BTL will continue to work as expected, as they will return OMPI_SUCCESS
   which force the PML to have exactly the same behavior as before. Some BTLs have
   been modified: self, sm, tcp, mx.
2. Add send immediate interface to BTL.
   The idea is to have a mechanism of allowing the BTL to take advantage of
   send optimizations such as the ability to deliver data "inline". Some
   network APIs such as Portals allow data to be sent using a "thin" event
   without packing data into a memory descriptor. This interface change
   allows the BTL to use such capabilities and allows for other optimizations
   in the future. All existing BTLs except for Portals and sm have this interface
   set to NULL.

This commit was SVN r18551.
2008-05-30 03:58:39 +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
George Bosilca
efa89bfa3f Revert r17857. The context should be set in one case ... when we call prepare_{src|dst}
without calling a get or put. So, just keep it here until a better solution is
found.

This commit was SVN r17872.

The following SVN revision numbers were found above:
  r17857 --> open-mpi/ompi@d460ccfbf9
2008-03-18 19:01:27 +00:00
George Bosilca
d460ccfbf9 No need to check for NULL there. The bml_btl is set correctly
on the upper level.

This commit was SVN r17857.
2008-03-18 03:02:31 +00:00
George Bosilca
39353ebb44 Cleanup.
This commit was SVN r17855.
2008-03-18 02:56:50 +00:00
George Bosilca
6310ce955c The first patch related to the Active Message stuff. So far, here is what we have:
- the registration array is now global instead of one by BTL.
- each framework have to declare the entries in the registration array reserved. Then
  it have to define the internal way of sharing (or not) these entries between all
  components. As an example, the PML will not share as there is only one active PML
  at any moment, while the BTLs will have to. The tag is 8 bits long, the first 3
  are reserved for the framework while the remaining 5 are use internally by each
  framework.
- The registration function is optional. If a BTL do not provide such function,
  nothing happens. However, in the case where such function is provided in the BTL
  structure, it will be called by the BML, when a tag is registered.

Now, it's time for the second step... Converting OB1 from a switch based PML to an
active message one.

This commit was SVN r17140.
2008-01-15 05:32:53 +00:00
Gleb Natapov
8b511b969d Introduce a new BTL parameter btl_rndv_eager_limit which determines size of a
first fragment of rendezvous protocol. Remove no longer used btl_min_send_size
parameter.

This commit was SVN r16969.
2007-12-16 08:35:17 +00:00
Gleb Natapov
666b282e7e Add mca_bml_base_send_status function. It returns ORTE_ERR_RESOURCE_BUSY if
packet was queued inside BTL. BTL should return this error if packet was queued
internally.

This commit was SVN r16904.
2007-12-09 14:12:38 +00:00
Gleb Natapov
e2e211f23b Add flags parameter to btl_alloc() and btl_prepare_src() functions. If BTL
knows at the time of allocation priority of a descriptor it may do some
optimizations.

This commit was SVN r16901.
2007-12-09 14:08:01 +00:00
Gleb Natapov
7364b7cf47 Add endpoint parameter to btl_alloc() function. Enables various optimizations
inside BTL.

This commit was SVN r16898.
2007-12-09 14:00:42 +00:00
Gleb Natapov
2d784752dd Remove descriptor caching form BML. With descriptor caching some optimizations
are impossible.

This commit was SVN r16897.
2007-12-09 13:58:17 +00:00
Jeff Squyres
3bc940ac27 Fix three things from r15474 (thanks to Brian for noticing):
* bml.h had a change that introduced a variable named "_order" to
   avoid a conflict with a local variable.  The namespace starting
   with _ belongs to the os/compiler/kernel/not us.  So we can't start
   symbols with _.  So I replaced it with arg_order, and also updated
   the threaded equivalent of the macro that was modified.
 * in btl_openib_proc.c, one opal_output accidentally had its string
   reverted from "ompi_modex_recv..." to
   "mca_pml_base_modex_recv....".  This was fixed.
 * The change to ompi/runtime/ompi_preconnect.c was entirely
   reverted; it was an artifact of debugging.

This commit was SVN r15475.

The following SVN revision numbers were found above:
  r15474 --> open-mpi/ompi@8ace07efed
2007-07-18 11:38:06 +00:00
Jeff Squyres
8ace07efed This commit brings in two major things:
1. Galen's fine-grain control of queue pair resources in the openib
   BTL.
1. Pasha's new implementation of asychronous HCA event handling.

Pasha's new implementation doesn't take much explanation, but the new
"multifrag" stuff does.  

Note that "svn merge" was not used to bring this new code from the
/tmp/ib_multifrag branch -- something Bad happened in the periodic
trunk pulls on that branch making an actual merge back to the trunk
effectively impossible (i.e., lots and lots of arbitrary conflicts and
artifical changes).  :-(

== Fine-grain control of queue pair resources ==

Galen's fine-grain control of queue pair resources to the OpenIB BTL
(thanks to Gleb for fixing broken code and providing additional
functionality, Pasha for finding broken code, and Jeff for doing all
the svn work and regression testing).

Prior to this commit, the OpenIB BTL created two queue pairs: one for
eager size fragments and one for max send size fragments.  When the
use of the shared receive queue (SRQ) was specified (via "-mca
btl_openib_use_srq 1"), these QPs would use a shared receive queue for
receive buffers instead of the default per-peer (PP) receive queues
and buffers.  One consequence of this design is that receive buffer
utilization (the size of the data received as a percentage of the
receive buffer used for the data) was quite poor for a number of
applications.

The new design allows multiple QPs to be specified at runtime.  Each
QP can be setup to use PP or SRQ receive buffers as well as giving
fine-grained control over receive buffer size, number of receive
buffers to post, when to replenish the receive queue (low water mark)
and for SRQ QPs, the number of outstanding sends can also be
specified.  The following is an example of the syntax to describe QPs
to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues:

{{{
-mca btl_openib_receive_queues \
     "P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32"
}}}

Each QP description is delimited by ";" (semicolon) with individual
fields of the QP description delimited by "," (comma).  The above
example therefore describes 4 QPs.

The first QP is:

    P,128,16,4

Meaning: per-peer receive buffer QPs are indicated by a starting field
of "P"; the first QP (shown above) is therefore a per-peer based QP.
The second field indicates the size of the receive buffer in bytes
(128 bytes).  The third field indicates the number of receive buffers
to allocate to the QP (16).  The fourth field indicates the low
watermark for receive buffers at which time the BTL will repost
receive buffers to the QP (4).

The second QP is:

    S,1024,256,128,32

Shared receive queue based QPs are indicated by a starting field of
"S"; the second QP (shown above) is therefore a shared receive queue
based QP.  The second, third and fourth fields are the same as in the
per-peer based QP.  The fifth field is the number of outstanding sends
that are allowed at a given time on the QP (32).  This provides a
"good enough" mechanism of flow control for some regular communication
patterns.

QPs MUST be specified in ascending receive buffer size order.  This
requirement may be removed prior to 1.3 release.

This commit was SVN r15474.
2007-07-18 01:15:59 +00:00
George Bosilca
752909c628 These are supposed to have a high probability of success.
This commit was SVN r15377.
2007-07-11 23:02:47 +00:00
Gleb Natapov
b88b7dedfe Rename btl_rdma_offset to btl_pipeline_send_length.
This commit was SVN r15153.
2007-06-21 07:12:40 +00:00
Galen Shipman
3401bd2b07 Add optional ordering to the BTL interface.
This is required to tighten up the BTL semantics. Ordering is not guaranteed,
but, if the BTL returns a order tag in a descriptor (other than
MCA_BTL_NO_ORDER) then we may request another descriptor that will obey
ordering w.r.t. to the other descriptor.


This will allow sane behavior for RDMA networks, where local completion of an
RDMA operation on the active side does not imply remote completion on the
passive side. If we send a FIN message after local completion and the FIN is
not ordered w.r.t. the RDMA operation then badness may occur as the passive
side may now try to deregister the memory and the RDMA operation may still be
pending on the passive side. 

Note that this has no impact on networks that don't suffer from this
limitation as the ORDER tag can simply always be specified as
MCA_BTL_NO_ORDER.

This commit was SVN r14768.
2007-05-24 19:51:26 +00:00
Gleb Natapov
3ebaff8dfe Implement new BTL parameters:
We eagerly send data up to btl_*_eager_limit with the match
Upon ACK of the MATCH we start using send/receives of size
btl_*_max_send_size up to the btl_*_rdma_pipeline_offset
After the btl_*_rdma_pipeline_offset we begin using RDMA writes of
size btl_*_rdma_pipeline_frag_size.

Now, on a per message basis we only use the above protocol if the
message is larger than btl_*_min_rdma_pipeline_size

btl_*_eager_limit - > same
btl_*_max_send_size -> same
btl_*_rdma_pipeline_offset -> btl_*_min_rdma_size
btl_*_rdma_pipeline_frag_size -> btl_*_max_rdma_size


btl_*_min_rdma_pipeline_size is new..

This patch also moves all BTL common parameters initialisation into
btl_base_mca.c file.

This commit was SVN r14681.
2007-05-17 07:54:27 +00:00
Rich Graham
ce35761683 make sure not to go out of bounds. element i+1 of bml_btls
is referenced, which for i-arr_size-1 is beyond the array dimentions.

This commit was SVN r14464.
2007-04-22 21:43:34 +00:00
Josh Hursey
dadca7da88 Merging in the jjhursey-ft-cr-stable branch (r13912 : HEAD).
This merge adds Checkpoint/Restart support to Open MPI. The initial
frameworks and components support a LAM/MPI-like implementation.

This commit follows the risk assessment presented to the Open MPI core
development group on Feb. 22, 2007.

This commit closes trac:158

More details to follow.

This commit was SVN r14051.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r13912

The following Trac tickets were found above:
  Ticket 158 --> https://svn.open-mpi.org/trac/ompi/ticket/158
2007-03-16 23:11:45 +00:00
George Bosilca
a02d1c7c8d No more warnings.
This commit was SVN r13382.
2007-01-31 04:27:41 +00:00
Rainer Keller
125ba1acfa - Reduce the amount of warnings with -Wshadow -- mainly due to
usage of index and abs in inline-fcts in header files.

This commit was SVN r13217.
2007-01-19 19:48:06 +00:00
Gleb Natapov
4c7dbd36c7 Balance RDMA operation in round robin fashion between all available RDMA BTLs.
OB1 always use first element from array of BTLs available for RDMA. The patch
change the array creation algorithm, it puts different BTL in the first element
in round robin fashion.

This commit was SVN r13174.
2007-01-18 09:15:18 +00:00
Gleb Natapov
190e7a27cd Merge with gleb-mpool branch. All RDMA components use same mpool now (rdma).
udapl/openib/vapi/gm mpools a deprecated. rdma mpool has parameter that allows
to limit its size mpool_rdma_rcache_size_limit (default is 0 - unlimited).

This commit was SVN r12878.
2006-12-17 12:26:41 +00:00
George Bosilca
06563b5dec Last set of explicit conversions. We are now close to the zero warnings on
all platforms. The only exceptions (and I will not deal with them
anytime soon) are on Windows:
- the write functions which require the length to be an int when it's
  a size_t on all UNIX variants.
- all iovec manipulation functions where the iov_len is again an int
  when it's a size_t on most of the UNIXes.
As these only happens on Windows, so I think we're set for now :)

This commit was SVN r12215.
2006-10-20 03:57:44 +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
Galen Shipman
3b49953ce2 Add error callback to the btl interface, this allows error to be delivered to
the upperlayer assynchronously although there are some issues with this.. such
as there are multiple consumers of the btl's.. who get's the

This commit was SVN r11232.
2006-08-16 20:21:38 +00:00
Brian Barrett
dd6fa1da2a * Fix for ticket #242, print a friendly error message if we can't reach
a particular peer.  Will now fail during MPI_INIT.  Printing of the
  error messages about no endpoints can be turned off.

This commit was SVN r11181.
2006-08-14 19:17:36 +00:00
Brian Barrett
24de93e2d4 * fix some compile errors with having OB1 direct called
This commit was SVN r11170.
2006-08-14 15:43:03 +00:00
Gleb Natapov
91f48f9a79 Merge with gleb-pml branch. Add out of resource handling support to PML layer.
If resource is not available request is added to one of the pending list and retried later.

This commit was SVN r10900.
2006-07-20 14:44:35 +00:00
Brian Barrett
47725c9b02 * Add new PML (CM) and network drivers (MTL) for high speed
interconnects that provide matching logic in the library.
  Currently includes support for MX and some support for
  Portals
* Fix overuse of proc_pml pointer on the ompi_proc structuer, 
  splitting into proc_pml for pml data and proc_bml for
  the BML endpoint data
* bug fixes in bsend init code, which wasn't being used by
  the OB1 or DR PMLs...

This commit was SVN r10642.
2006-07-04 01:20:20 +00:00
Galen Shipman
e6cd8db0e5 DR will now checksum on a per btl basis (see MCA_BTL_FLAGS_NEED_CSUM). We
still always send ACK's, teasing apart completion for ACK/no ACK looks like a
pain in the .. 

This commit was SVN r10530.
2006-06-27 20:23:47 +00:00
George Bosilca
837221831a Temporary solution for in-bound computation of the next BTL.
This commit was SVN r10016.
2006-05-22 23:28:40 +00:00
George Bosilca
e43fbd0082 Remove all useless variables. Minor cleanups.
This commit was SVN r10000.
2006-05-21 05:53:22 +00:00
Galen Shipman
9165882c07 fixes for failover...
This commit was SVN r9998.
2006-05-20 02:39:05 +00:00
Tim Woodall
fdd622544b added optional copy routine to allow "derived" class
of mca_bml_base_endpoint to copy state if an endpoint
is updated (e.g. btl deleted/added)

This commit was SVN r9814.
2006-05-04 15:19:12 +00:00
Galen Shipman
5271948ec0 --- opal object changes
add object size to opal class
no longer need the size when allocating a new object as this is stored in
the class structure

--- dr changes 
Previous rev. maintained state on the communicator used for acking duplicate
fragments, but the communicator may be destroyed prior to successfull
delivery of an ack to the peer. We must therefore maintain this state
globally on a per peer, not a per peer, per communicator basis. 
This requires that we use a global rank on the wire and translate this as
appropriate to a local rank within the communicator. 

This commit was SVN r9454.
2006-03-29 16:19:17 +00:00
Tim Woodall
c1bf71b1be - updated copyrights
- removed unused state
- starting to add support for btl failover

This commit was SVN r9431.
2006-03-27 22:48:12 +00:00
Galen Shipman
f609204cc5 disable reliability checking in bml
This commit was SVN r9392.
2006-03-23 17:50:20 +00:00
Tim Woodall
c1bec478c4 updates to reliability debug code
This commit was SVN r9390.
2006-03-23 17:00:20 +00:00
Galen Shipman
7ce7baff15 more bml work
This commit was SVN r9341.
2006-03-20 21:58:20 +00:00
Galen Shipman
5600932c2f fix misc warnings
This commit was SVN r9339.
2006-03-20 15:41:45 +00:00
Galen Shipman
15bdbd5ca1 add parameter names to cb func
This commit was SVN r9338.
2006-03-20 15:29:35 +00:00
Tim Woodall
bd870519fd - modified convertor copy_and_prepare routines to accept an addition
flag, new flags to be included when convertor is initialized
- modified pml/btl module defs and added stub functions for diagnostic
  output routines to dump state of queues / endpoints
- updates to data reliability pml

This commit was SVN r9329.
2006-03-17 18:46:48 +00:00
George Bosilca
8fb84e90ce It's already done in the send ... we don't have to initialize this
field several times.

This commit was SVN r9282.
2006-03-14 21:55:57 +00:00
Tim Woodall
c83b2fce4d resolve threading issue
This commit was SVN r9233.
2006-03-09 17:57:31 +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
Galen Shipman
44fe6c3896 allow pml pipeline to cache memory registrations
to enable this (off by default) use: 
-mca pml_ob1_leave_pinned_pipeline 1 
!!AND!!!
-mca mpool_use_mem_hooks 1 

This commit was SVN r8949.
2006-02-09 15:49:51 +00:00
George Bosilca
8d26696c06 Remove the local variable that shadow the real one.
This commit was SVN r8763.
2006-01-20 02:39:30 +00:00
George Bosilca
29c80875a8 As requested move back the alloc and return to macros instead of static inlined functions.
This commit was SVN r8762.
2006-01-19 23:58:04 +00:00