fix: do not fail on blm allocation error, wait for some puts to complete and retry
fixed by Roman, reviewed by Mike/Alex
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30779.
- Move the ptrdiff_t tests up higher in configure.ac to be with the
rest of the type tests.
- Create new OMPI_FIND_MPI_AINT_COUNT_OFFSET for finding the
corresponding types of MPI_Aint, MPI_Count, and MPI_Offset.
Consolidate all the old C and Fortran tests into this new macro (and
.m4 file).
- Fix Fortran MPI_*_KIND tests that incorrectly keyed off assumed
types (e.g., int64_t) rather than whatever the corresponding C
MPI_Aint, MPI_Count, MPI_Offset types turned out to be.
- Add new logic to ensure that sizeof(MPI_Count) <= sizeof(size_t),
because our entire PML, BTL, and convertor infrastructure requires
this. As a side effect, just like MPI_Offset the same type of
MPI_Count (because MPI_Count has to be able to hold an MPI_Offset,
so we can't let MPI_Offset be larger than a MPI_Count).
This commit was SVN r30776.
The following Trac tickets were found above:
Ticket 4205 --> https://svn.open-mpi.org/trac/ompi/ticket/4205
This adds the code to actually checkpoint a process using CRIU
with the necessary variables to control the behaviour.
Right now only --np 1 is supported and --mca oob tcp.
Following parameters are supported:
* crs_criu_log: name of the log file
* crs_criu_log_level: verbosity level in the log file
* crs_criu_tcp_established: C/R established TCP connections
* crs_criu_shell_job: C/R shell jobs
* crs_criu_ext_unix_sk: allow external unix connections
* crs_criu_leave_running: leave tasks in running state after checkpoint
This commit was SVN r30772.
- MXM uses libtool versioning scheme which is enough, no need additional in OMPI
reviewed by yossi
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30768.
1. fix in oshmem scoll component: basic algorithms should
call basic collectives since their implementation
incompatible with others (fca, hcoll).
2. Set OPAL_EVLOOP_ONCE flag ON for libevent in the case
of yoda smpl. Otherwise there is possible deadlock in
atomic_basic_lock call
fixed by Val, Igor, reviewed by Miked
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30762.
The problem was with oshmem ring code, which cycles a constant amout of data through all the processes.
When the program would expect the memory to change it did not explicitly warrent a recv() call, thus
counting on the memory region to hold the new value when in fact it could be set before or after the
check, causing slower BTLs to pass and faster ones to fail. The fix changes the logic to anticipate
the next message rather then the current one, which would be a mistake.
Patch applied to both C and fortran90 version of the example code.
reviewd by miked
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30760.
- remove old, unused code
- rename mca param for oshmem preconnect to match mpi naming scheme.
fixed by Alex, reviewed by Mike
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30748.
With enabled fault tolerance code different functions
are selected during compilation. Most of the ft
code is #ifdef'd out. This #ifdef's more code out
so that compiler warnings like
warning: unused variable 'item' [-Wunused-variable]
opal_list_item_t *item;
are removed.
This commit was SVN r30747.
VERY tentatively schedule this for 1.7.5 - only to be applied if we see no troubles AND the branch is ready in advance.
cmr=v1.7.5:reviewer=rhc:subject=Add unix socket component to OOB
This commit was SVN r30742.
* Remove redundant/unnecessary uses of $2
* Change a bunch of logic from negative to positive
* Use OPAL_VAR_SCOPE_PUSH/POP to help reduce env var usage
* Only use "" in test statements with strings that require sanitization
* Removed redundant AC_MSG_WARN/ERROR. There's now only one check at
the bottom for whether the component is "good" or not. We'll
AC_MSG_WARN/ERROR in that one location.
Thanks to Jeff Squyres for this patch.
This commit was SVN r30739.
The gatekeeper script was not correctly respecting the locale specified
in the user's environment. So basically this scenario could (and did)
easily happen:
1. A committer writes a valid message in UTF-8 and runs `svn commit` with
a correct locale setting of `LANG=en_US.UTF-8`.
2. SVN transcodes that to UTF-8 for internal storage (a no-op in this
case).
3. The gatekeeper, also with `LANG=en_US.UTF-8` set, runs
`gkcommit.pl ...`. This breaks down into the following steps:
A. run `svn log --xml ...`, which SVN correctly transcodes from UTF-8
into the current locale, which happens to also be UTF-8
B. Perl reads this in and assumes this is a sequence of raw 8-bit
bytes in a "native" latin1-type encoding.
C. Perl's XML::Parser module spots the XML declaration stating the
content is UTF-8 encoded: `<?xml version="1.0" encoding="UTF-8"?>`.
Perl internally stores the parsed strings as proper Unicode
strings (UTF-8 encoded internally, but that's irrelevant here).
D. Perl writes out the commit message file in the _latin1_ encoding,
transcoding characters from internal UTF-8. This causes
characters like "ä" (Unicode code point: 0xe4, UTF-8 encoding:
0xc3 0xa4) to be encoded as a single byte: 0xe4.
This fix changes the behavior at steps 3A and 3D to transparently treat
the incoming/outgoing data as UTF-8 (assuming a UTF-8 locale is set in
the user's environment).
There can still be problems if either the committer or the gatekeeper
have locale settings that do not agree with the encoding that their
editor is producing, but such is i18n :(
Helpful references for anyone debugging this sort of issue in the
future:
* http://perldoc.perl.org/perllocale.html#Unicode-and-UTF-8
* http://perldoc.perl.org/perluniintro.html#Unicode-I%2fO
Refs trac:4217
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30709.
The following Trac tickets were found above:
Ticket 4217 --> https://svn.open-mpi.org/trac/ompi/ticket/4217
Optimization of the MPI_Dims_create function which omits the usage of pre
calculated prime numbers and factorize directly as discussed at the developer
list.
cmr=v1.7.5:ticket=4217:reviewer=jsquyres
This commit was SVN r30695.
The following Trac tickets were found above:
Ticket 4217 --> https://svn.open-mpi.org/trac/ompi/ticket/4217
