WHAT: Merge the PMIx branch into the devel repo, creating a new
OPAL “lmix” framework to abstract PMI support for all RTEs.
Replace the ORTE daemon-level collectives with a new PMIx
server and update the ORTE grpcomm framework to support
server-to-server collectives
WHY: We’ve had problems dealing with variations in PMI implementations,
and need to extend the existing PMI definitions to meet exascale
requirements.
WHEN: Mon, Aug 25
WHERE: https://github.com/rhc54/ompi-svn-mirror.git
Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.
All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.
Accordingly, we have:
* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.
* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.
* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint
* removed the prior OMPI/OPAL modex code
* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.
* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand
This commit was SVN r32570.
The _strdup usage in opal/util/basename looks like it was a product of
Windows compatibility (see r11336), which we don't care about any
more. Further, opal/win32/win_compat.h, which we sitll maintain for
cygwin compatibility, #define's strdup to _strdup (which is what
Microsoft wants you to use).
So this old _strdup in opal/util/basename.c (and its corresponding
check in configure.ac) should just be removed.
This commit was SVN r32450.
The following SVN revision numbers were found above:
r11336 --> open-mpi/ompi@a28b025150
r32449 --> open-mpi/ompi@d5a3448b8b
_strdup is not part of any include file i could find on Solaris 10.
manually add the _strdup prototype if needed.
cmr=v1.8.2:reviewer=jsquyres
This commit was SVN r32449.
communication library should use to initialize itself.
Ralph will champion this change back with an RFC if there is a realistic
need/use case from the community.
This commit was SVN r32361.
The following SVN revision numbers were found above:
r32355 --> open-mpi/ompi@c903917f47
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
Two leaks are fixed by this commit:
- opal_dss.lookup_data_type returns an allocated string. Free it.
- opal_ifaddrtokindex was leaking a struct addrinfo. Ensure that is
released before returning.
cmr=v1.8.2:reviewer=rhc
This commit was SVN r31777.
code.
This commit fixes minor errors in the incorrectly-committed r31513
(new fd close-on-exec convenience function).
Refs trac:4550
This commit was SVN r31514.
The following SVN revision numbers were found above:
r31513 --> open-mpi/ompi@e1655ae68d
The following Trac tickets were found above:
Ticket 4550 --> https://svn.open-mpi.org/trac/ompi/ticket/4550
Paul Hargrove pointed out that Stevens tells us that we should
FD_GETFL before FD_SETFL. And so we shall.
Make a new convenience function to do this (opal_fd_set_cloexec()),
just so that we don't have to litter this 2-step process throughout
the code.
Refs trac:4550
This commit was SVN r31513.
The following Trac tickets were found above:
Ticket 4550 --> https://svn.open-mpi.org/trac/ompi/ticket/4550
* Include opal_stdint.h so that we have uin32_t
cmr=v1.7.5:ticket=trac:4298
This commit was SVN r30890.
The following Trac tickets were found above:
Ticket 4298 --> https://svn.open-mpi.org/trac/ompi/ticket/4298
1. Changed rng_buff_t --> opal_rng_buff_t
2. All global variables obey the prefix rule
3. Old code has been removed
4. Found a couple of unnecessary includes
Refs trac:4298
This commit was SVN r30807.
The following Trac tickets were found above:
Ticket 4298 --> https://svn.open-mpi.org/trac/ompi/ticket/4298
* Fix some typos in macro names.
* Add case for OS's that have statfs() but no struct statfs (!).
* Add case for NetBSD with struct statvfs.f_fstypename.
Many thanks to Paul Hargrove who developed the majority of this patch.
Reviewed by Jeff Squyres.
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r30255.
As noted by Paul Hargrove, the #if's surrounding the use of statfs()
and statvfs() in opal/util/path.c have apparently gotten stale (e.g.,
modern flavors of *BSD OSs no longer define __BSD). Changes:
* Add statfs and statvfs to the AC_CHECK_FUNCS in configure.ac
* Add a sanity check to ensure that we have at least one of statfs()
or statvfs(). Add a similar sanity check in opal/util/path.c, just
as defensive programming.
* Use AC_CHECK_MEMBERS in configure.ac to check for specific struct
statfs/struct statvfs members that we use in opal/util/path.c
* In path.c, add some #includes as listed on the OS man page for
statfs(2) (OS X 10.8.5/Mountain Lion)
* The previous code used statvfs() on Solaris and statfs() everywhere
else. Attempting to replicate this with behavior-based configure
testing led to fairly complicted if/else logic, so the new code
uses whichever of the two are available (i.e., it might actually
use both -- OS X 10.8.5 and RHEL 6.5 have both statfs() and
statvfs()). The rationale here is that we don't really care which
of the two functions report the answer; we'll take the answer
regardless of where it comes from. For example, if one function
returns a failure and the other does not, we'll use the results
from the successful function and ignore the failed one.
This new code seems to work on OS X and Linux. We'll have to see what
happens with MTT and future Paul Hargrove testing...
cmr=v1.7.4:reviewer=ompi-rm1.7:subject=Make statfs/statvfs more robust
This commit was SVN r30198.
configury/Makefile.am changes; this commit renames the internal
installdirs.h framework struct field names to match the configry macro
names:
* pkgdatdir -> ompidatadir
* pkglibdir -> ompilibdir
* pkgincludedir -> ompiincludedir
This commit was SVN r30145.
The following SVN revision numbers were found above:
r30140 --> open-mpi/ompi@8b778903d8
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.
and preventing access to potentially unaligned data.
Reviewed by Dave Goodell. Tested by Siegmarr Gross.
cmr=v1.7.4:reviewer=ompi-rm1.7:subject=fix SPARC SIGBUS in opal net code
This commit was SVN r29983.
The following Trac tickets were found above:
Ticket 3990 --> https://svn.open-mpi.org/trac/ompi/ticket/3990
Change static opal_setlimit() function to return its value in an OUT
parameter and return the usual int error code indicating success or
failure.
The OUT param and return code need to be separated because the OUT
param is an unsigned type, but opal_setlimit() was returning -1 upon
failure. Hence, the caller could not know that it had failed because
the return type was previously an unsigned type.
cmr=v1.7.4:reviewer=rhc:subject=Fix opal sys_limits.c signed/unsigned warnings
This commit was SVN r29685.
*** THIS RFC INCLUDES A MINOR CHANGE TO THE MPI-RTE INTERFACE ***
Note: during the course of this work, it was necessary to completely separate the MPI and RTE progress engines. There were multiple places in the MPI layer where ORTE_WAIT_FOR_COMPLETION was being used. A new OMPI_WAIT_FOR_COMPLETION macro was created (defined in ompi/mca/rte/rte.h) that simply cycles across opal_progress until the provided flag becomes false. Places where the MPI layer blocked waiting for RTE to complete an event have been modified to use this macro.
***************************************************************************************
I am reissuing this RFC because of the time that has passed since its original release. Since its initial release and review, I have debugged it further to ensure it fully supports tests like loop_spawn. It therefore seems ready for merge back to the trunk. Given its prior review, I have set the timeout for one week.
The code is in https://bitbucket.org/rhc/ompi-oob2
WHAT: Rewrite of ORTE OOB
WHY: Support asynchronous progress and a host of other features
WHEN: Wed, August 21
SYNOPSIS:
The current OOB has served us well, but a number of limitations have been identified over the years. Specifically:
* it is only progressed when called via opal_progress, which can lead to hangs or recursive calls into libevent (which is not supported by that code)
* we've had issues when multiple NICs are available as the code doesn't "shift" messages between transports - thus, all nodes had to be available via the same TCP interface.
* the OOB "unloads" incoming opal_buffer_t objects during the transmission, thus preventing use of OBJ_RETAIN in the code when repeatedly sending the same message to multiple recipients
* there is no failover mechanism across NICs - if the selected NIC (or its attached switch) fails, we are forced to abort
* only one transport (i.e., component) can be "active"
The revised OOB resolves these problems:
* async progress is used for all application processes, with the progress thread blocking in the event library
* each available TCP NIC is supported by its own TCP module. The ability to asynchronously progress each module independently is provided, but not enabled by default (a runtime MCA parameter turns it "on")
* multi-address TCP NICs (e.g., a NIC with both an IPv4 and IPv6 address, or with virtual interfaces) are supported - reachability is determined by comparing the contact info for a peer against all addresses within the range covered by the address/mask pairs for the NIC.
* a message that arrives on one TCP NIC is automatically shifted to whatever NIC that is connected to the next "hop" if that peer cannot be reached by the incoming NIC. If no TCP module will reach the peer, then the OOB attempts to send the message via all other available components - if none can reach the peer, then an "error" is reported back to the RML, which then calls the errmgr for instructions.
* opal_buffer_t now conforms to standard object rules re OBJ_RETAIN as we no longer "unload" the incoming object
* NIC failure is reported to the TCP component, which then tries to resend the message across any other available TCP NIC. If that doesn't work, then the message is given back to the OOB base to try using other components. If all that fails, then the error is reported to the RML, which reports to the errmgr for instructions
* obviously from the above, multiple OOB components (e.g., TCP and UD) can be active in parallel
* the matching code has been moved to the RML (and out of the OOB/TCP component) so it is independent of transport
* routing is done by the individual OOB modules (as opposed to the RML). Thus, both routed and non-routed transports can simultaneously be active
* all blocking send/recv APIs have been removed. Everything operates asynchronously.
KNOWN LIMITATIONS:
* although provision is made for component failover as described above, the code for doing so has not been fully implemented yet. At the moment, if all connections for a given peer fail, the errmgr is notified of a "lost connection", which by default results in termination of the job if it was a lifeline
* the IPv6 code is present and compiles, but is not complete. Since the current IPv6 support in the OOB doesn't work anyway, I don't consider this a blocker
* routing is performed at the individual module level, yet the active routed component is selected on a global basis. We probably should update that to reflect that different transports may need/choose to route in different ways
* obviously, not every error path has been tested nor necessarily covered
* determining abnormal termination is more challenging than in the old code as we now potentially have multiple ways of connecting to a process. Ideally, we would declare "connection failed" when *all* transports can no longer reach the process, but that requires some additional (possibly complex) code. For now, the code replicates the old behavior only somewhat modified - i.e., if a module sees its connection fail, it checks to see if it is a lifeline. If so, it notifies the errmgr that the lifeline is lost - otherwise, it notifies the errmgr that a non-lifeline connection was lost.
* reachability is determined solely on the basis of a shared subnet address/mask - more sophisticated algorithms (e.g., the one used in the tcp btl) are required to handle routing via gateways
* the RML needs to assign sequence numbers to each message on a per-peer basis. The receiving RML will then deliver messages in order, thus preventing out-of-order messaging in the case where messages travel across different transports or a message needs to be redirected/resent due to failure of a NIC
This commit was SVN r29058.
