This commit fixes a race that can occur when two threads are in the
ugni progress function at the same time. This race occurs when one
thread calls GNI_PostDataProbeById then goes to sleep then another
thread calls GNI_PostDataProbeById then GNI_EpPostDataWaitById before
the other thread wakes up. If this happens the first thread will print
a warning on GNI_EpPostDataWaitById about no matching post.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit fixes two issues that can occur during a connection:
- Re-entry to connection progress from modex lookup. Added an
additional endpoint state that will keep the code from re-entering
the common endpoint create.
- Fixed a race between a process posting a directed datagram through
a send and a connection being progressed through opal_progress().
The progress code was not obtaining the endpoint lock before
attempting to update the endpoint. To limit the amount of code
changed for 2.0.1 this commit makes the endpoint lock recursive. In
a future update this may be changed.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Fixes PR https://github.com/open-mpi/ompi/pull/1687
The code that sets OPAL_HAVE_WORKING_EVENTOPS for internal libevent
was executed even if the external libevent component was configured.
As the result libevent progress wasn't called in opal_progress which
for example caused ring_c to hang when pml/ob1 was used.
Architecture is set by the ompi layer *after* job startup, so the key cannot
have the "pmix" prefix since optimizations in open-mpi/ompi@01a653d50a
otherwise architecture cannot be retrieved
This commits changed rand(3) and family in libevent to use internal
random function provided in opal to prevent pertubing user's random seed.
Fixesopen-mpi/ompi#1877
On Cray, PR #1846 introduced a double free
situation which led to all kinds of random memory
corruption problems.
This commit fixes this problem.
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
configury command line is quoted and made available via the OPAL_CONFIGURE_CLI macro.
it can be retrieved via {orte-info,ompi_info,oshmem_info} -c, or
{orte-info,ompi_info,oshmem_info} --all --parseable | grep ^config:cli:
This commit expands the OPAL_THREAD macros to include 32- and 64-bit
atomic swap. Additionally, macro declararations have been updated to
include both OPAL_THREAD_* and OPAL_ATOMIC_*. Before this commit the
former was used with add and the later with cmpset.
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
This commit adds opal_using_threads() protection around the atomic
operation in OBJ_RETAIN/OBJ_RELEASE. This resolves the performance
issues seen when running psm with MPI_THREAD_SINGLE.
To avoid issues with header dependencies opal_using_threads() has been
moved to a new header (thread_usage.h). The OPAL_THREAD_ADD* and
OPAL_THREAD_CMPSET* macros have also been relocated to this header.
This commit is cherry-picked off a fix that was submitted for the v1.8
release series but never applied to master. This fixes part of the
problem reported by @nysal in #1902.
(cherry picked from commit open-mpi/ompi-release@ce91307918)
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
The max inline send size on a queue pair is not available until after
the endpoint is connected. Before this commit the send flags
(including the inline flag) were set before this value was
initialized. This commit moves setting the send_flags down to
mca_btl_openib_put_internal which is only called after the endpoint is
connected. This fixes a bug when using osc/rdma.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit fixes a bug in the pmix2x client code where a loop
variable is not correctly incremented. This was leading to hangs and
crashes when creating intercommunicators. Also fixed two double
increments in other loops.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Blocking fence is used in yalla del proc. Native pmix exposes this functionality.
We need to expose it for SLURM's s1/s2 components as well.
Also this commit fixes uninitialized `rc` in fencenb's of both
components.
Thanks Jeff for the guidance
Fixesopen-mpi/ompi#1683
note:
in order to keep this commit easy to review, some AS_IF([...]) were replaced with
AS_IF([false], ...) or AS_IF_([true], ...)
these will be removed and re-idented in a subsequent commit
pmix cannot be built on alpine linux because of some missing includes.
uid_t and gid_t are defined in unistd.h or sys/types.h, and unistd.h
is not indirectly pulled under alpine linux, so do it manually.
Thanks N.L.K Nguyen for the report
(back-ported from upstream pmix/master@c8d55350a9)
This commit fixes a long standing bug in rdmacm. It is required that
the thread that calls mca_btl_openib_endpoint_cpc_complete holds the
endpoint lock. This was not the case for rdmacm. This causes debug
builds to abort. This change also required changing
mca_btl_openib_endpoint_send_cts to require the endpoint lock to be
held when calling.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit is an attempt to fix a hang in finalize of rdmacm. This fixes
a path where no rdmacm client is found for an endpoint.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit fixes a segmentation fault that occurs if a device can be
initialized but not used. In this case the devices_count is not equal
to the number of usable devices in the devices pointer array.
Thanks to @artpol84 for tracking this down.
Fixesopen-mpi/ompi#1823
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit fixes a race condition discovered by @artpol84. The race
happens when a signalling thread decrements the sync count to 0 then
goes to sleep. If the waiting thread runs and detects the count == 0
before going to sleep on the condition variable it will destroy the
condition variable while the signalling thread is potentially still
processing the completion. The fix is to add a non-atomic member to
the sync structure that indicates another process is handling
completion. Since the member will only be set to false by the
initiating thread and the completing thread the variable does not need
to be protected. When destoying a condition variable the waiting
thread needs to wait until the singalling thread is finished.
Thanks to @artpol84 for tracking this down.
Fixes#1813
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit adds another check to the low-priority callback
conditional that short-circuits the atomic-add if there are no
low-priority callbacks. This should improve performance in the common
case.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
The OPAL_ENABLE_MULTI_THREADS macro is always defined as 1. This was
causing us to always use the multi-thread path for synchronization
objects. The code has been updated to use the opal_using_threads()
function. When MPI_THREAD_MULTIPLE support is disabled at build time
(2.x only) this function is a macro evaluating to false so the
compiler will optimize out the MT-path in this case. The
OPAL_ATOMIC_ADD_32 macro has been removed and replaced by the existing
OPAL_THREAD_ADD32 macro.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
The way the gni btl is currently coded,
it will run completely out of gas on KNL at
123 processes/node. Since there are bound to be
those who try to run a MPI process/hyperthread
on KNL nodes, the fma sharing mode needs to be requested.
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
This commit fixes a compile error on 32-bit platforms. The
low-priority call counter was always using 64-bit atomics which will
not work if 64-bit atomic math is not available. Updated to use 32-bit
instead.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Add PMIx 2.0
Remove PMIx 1.1.4
Cleanup copying of component
Add missing file
Touchup a typo in the Makefile.am
Update the pmix ext114 component
Minor cleanups and resync to master
Update to latest PMIx 2.x
Update to the PMIx event notification branch latest changes
Per discussion on https://github.com/open-mpi/ompi/pull/1767 (and some
subsequent phone calls and off-issue email discussions), the PSM
library is hijacking signal handlers by default. Specifically: unless
the environment variables `IPATH_NO_BACKTRACE=1` (for PSM / Intel
TrueScale) is set, the library constructor for this library will
hijack various signal handlers for the purpose of invoking its own
error reporting mechanisms.
This may be a bit *surprising*, but is not a *problem*, per se. The
real problem is that older versions of at least the PSM library do not
unregister these signal handlers upon being unloaded from memory.
Hence, a segv can actually result in a double segv (i.e., the original
segv and then another segv when the now-non-existent signal handler is
invoked).
This PSM signal hijacking subverts Open MPI's own signal reporting
mechanism, which may be a bit surprising for some users (particularly
those who do not have Intel TrueScale). As such, we disable it by
default so that Open MPI's own error-reporting mechanisms are used.
Additionally, there is a typo in the library destructor for the PSM2
library that may cause problems in the unloading of its signal
handlers. This problem can be avoided by setting `HFI_NO_BACKTRACE=1`
(for PSM2 / Intel OmniPath).
This is further compounded by the fact that the PSM / PSM2 libraries
can be loaded by the OFI MTL and the usNIC BTL (because they are
loaded by libfabric), even when there is no Intel networking hardware
present. Having the PSM/PSM2 libraries behave this way when no Intel
hardware is present is clearly undesirable (and is likely to be fixed
in future releases of the PSM/PSM2 libraries).
This commit sets the following two environment variables to disable
this behavior from the PSM/PSM2 libraries (if they are not already
set):
* IPATH_NO_BACKTRACE=1
* HFI_NO_BACKTRACE=1
If the user has set these variables before invoking Open MPI, we will
not override their values (i.e., their preferences will be honored).
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
This commit adds the opal_atomic_swap_32 and opal_atomic_swap_64
functions. This should improve the performance of btl/vader.
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
The rdma_disconnect function specifies that both the server and client
should call rdma_disconnect. The code was not calling rdma_disconnect
on an endpoint if the event came before the endpoint finalization.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Before dynamic add_procs the openib_btl_size_queues was called exactly
once for non-dynamic jobs. Now the function is called on each new
connection so the calculation was wrong. Re-wrote the function to
correctly calculate the CQ size and only attempt to adjust the CQ if
the requested size has changed. This fixes a bug when using the openib
btl on psm2 hardware that is caused by the time needed to resize a
CQ. The overhead was causing udcm to timeout and fail.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit improves the CMA detection when the installed glibc doesn't
have support for CMA. In this case we need to verify that the syscall
numbers in opal/include/opal/sys/cma.h are valid for the architecture.
This verification is done by attempting to use CMA while including the
internal header.
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
Compiler implementations are free to include support for atomics that
use locks. Unfortunately lock-free and lock atomics do not mix. Older
versions of llvm on OS X use locks to provide
__atomic_compare_exchange on 128-bit values but are lock-free on
64-bit values. This screws up our lifo implementation which mixes
64-bit and 128-bit atomics on the same values to improve
performance. This commit adds a configure-time check if 128-bit
atomics are lock free. If they are not then the 128-bit __atomic CAS
is disabled and we check for the __sync version as a fallback.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
clang 7.0 with the picky option on is extremely verbose, and complains
about almost everything. Trying to make him happy, at least regarding
the datatype engine.
This commit fixes a bug in opal progress registration that can cause
crashes when a progress function is registered while another thread is
in opal_progress(). Before this commit realloc is used to allocate
more space for progress functions but it is possible for a thread in
opal_progress() to try to read from the array that is freed by realloc
before the array is re-assigned when realloc returns. To prevent this
race use malloc + memcpy to fill the new array and atomically swap out
the old and new array pointers.
Per suggestion we now allocate a default of 8 slots for callbacks and
double the current number when we run out of space.
This commit also fixes leaking the callbacks_lp array.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
* atomic: add support for __atomic builtins
This commit adds support for the gcc __atomic builtins. The __sync
builtins are deprecated and have been replaced by these atomics. In
addition, the new atomics support atomic exchange which was not
supported by __sync.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
* atomic: add support for transactional memory
This commit adds support for using transactional memory when using
opal atomic locks. This feature is enabled if the __HLE__ feature is
available and the gcc builtin atomics are in use.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This fixes https://github.com/open-mpi/ompi/issues/1732: i.e., the
case where the outer project has its own check for
<valgrind/valgrind.h>, but also supplements CPPFLAGS (to find
Valgrind's header files) before doing that check.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
Ideally, we would tell OMPI to disable autoconf's caching of our
valgrind check result so that its check gets the right result after
adding CPPFLAGS. Not sure if we can do that.
For now, just disable our Valgrind code in embedded mode.
This will keep the x86 backend enabled under Valgrind but
it will auto-disable itself when finding identical APIC ids anyway
(because CPUID returns same outputs for all PUs).
Signed-off-by: Brice Goglin <Brice.Goglin@inria.fr>
Fixesopen-mpi/ompi#1732
(cherry picked from commit open-mpi/hwloc@8b44fb1c81)
This commit fixes a programming error when using an aries nic. The
documentation of ugni shows that only the local alignment restriction
for get was lifted on aries. There is still a remote address alignment
restriction.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit fixes a programming error when using an aries nic. The
documentation of ugni shows that only the local alignment restriction
for get was lifted on aries. There is still a remote address alignment
restriction.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit adds support for Cray Aries atomic operations. This
includes 32-bit and floating point support.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit add support for more atomic operations and type. The
operations added are logical and, logical or, logical xor, swap, min,
and max. New types are 32-bit int by using the
MCA_BTL_ATOMIC_FLAG_32BIT flag, 64-bit float by using the
MCA_BTL_ATOMIC_FLAG_FLOAT flag, and 32-bit float by using both
flags. Floating point numbers are supported by packing the number in
as an int64_t or int32_t. We will update the btl interface in the
future to make this less confusing.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Before dynamic add_procs support was committed to master we called
add_procs with every proc in the job. The XRC code in the openib btl
was taking advantage of this and setting the number of work queue
entries (WQE) based on all the procs on a remote node. Since that is
no longer the case we can not simply increment the sd_wqe field on the
queue pair. To fix the issue a new field has been added to the xrc
queue pair structure to keep track of how many wqes there are total on
the queue pair. If a new endpoint is added that increases the number
of wqes and the xrc queue pair is already connected the code will
attempt to modify the number of wqes on the queue pair. A failure is
ignored because all that will happen is the number of active send work
requests on an XRC queue pair will be more limited.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
The original VADER_MAX_ADDRESS was tunned for x86_64 platforms only.
For non x86_64 platforms we can use XPMEM_MAXADDR_SIZE.
Signed-off-by: Pavel Shamis (Pasha) <pasharesearch@gmail.com>
This commit reduces the overhead of calling the ugni progress
function. It does the following:
- Check for new connections once every eight calls.
- Do not call remote smsg progress unless we are connected to at
least one remote peer.
- Do not call rdma progress unless at least one rdma fragment is
outstanding.
- Check endpoint wait list size before obtaining a lock.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit reduces the default exclusivity so that btl/scif is not
used for send/recv over other shared memory transports.
Fixesopen-mpi/ompi#1712
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Our checks and the ones of libevent are somewhat flawed.
If adding multiple "-framework" to CXXFLAGS or CFLAGS, we strip
the keyword from the command-line, not good.
libevent however assumes plain gcc without testing properly
that the compiler supports -Wno-deprecated-declarations.
* Remodel the request.
Added the wait sync primitive and integrate it into the PML and MTL
infrastructure. The multi-threaded requests are now significantly
less heavy and less noisy (only the threads associated with completed
requests are signaled).
* Fix the condition to release the request.
The OPAL_CMA_NEED_SYSCALL_DEFS is always defined/set to 0 or 1. Therefore
instead of checking if the macro is defined, we have to look at the value
itself.
Signed-off-by: Pavel Shamis (Pasha) <pasharesearch@gmail.com>
This commit changes the behavior of bml/r2 from conditionally
registering btl progress functions to always registering progress
functions. Any progress function beloning to a btl that is not yet in
use is registered as low-priority. As soon as a proc is added that
will make use of the btl is is re-registered normally.
This works around an issue with some btls. In order to progress a
first message from an unknown peer both ugni and openib need to have
their progress functions called. If either btl is not in use after the
first call to add_procs the callback was never happening. This commit
ensures the btl progress function is called at some point but the
number of progress callbacks is reduced from normal to ensure lower
overhead when a btl is not used. The current ratio is 1 low priority
progress callback for every 8 calls to opal_progress().
Fixesopen-mpi/ompi#1676
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Take another shot at untangling the spaghetti
orterun: fix for command line parsing
orte-submit calls opal_init_util () before parsing out MCA command line
options (-mca, -am, etc). This prevents mpirun from setting opal MCA
variables for some frameworks as well as the MCA base. This is because
when a framework is opened all of its variables are set to read-only.
Eventually we want to lift this restriction on some MCA variables but
since -mca is affected we must parse out the MCA command line options
before opal_init_util(). This commit fixes the bug by adding a new
option to opal_cmd_line_parse (ignore unknown option) so orte-submit
can pre-parse the command line for MCA options.
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
Minor cleanups to avoid releasing/recreating the cmd line
Remove contrib/windows/
Merge hwlocXYZ/hwloc/README-ompi.txt back into hwlocXYZ/README-ompi.txt instead of having both.
Add README.txt in new automake-required directory contrib/systemd/
Keep the following patches applied since they are not in 1.11.3
linux: actually enable libudev based on the result of AC_CHECK_LIB
(cherry picked from open-mpi/hwloc@9549fd59af)
configure: check the actual may_alias syntax that we use
(cherry picked from open-mpi/hwloc@0ab7af5e90)
This commit fixes several bugs in the registration cache code:
- Fix a programming error in the grdma invalidation function that can
cause an infinite loop if more than 100 registrations are
associated with a munmapped region. This happens because the
mca_rcache_base_vma_find_all function returns the same 100
registrations on each call. This has been fixed by adding an
iterate function to the vma tree interface.
- Always obtain the vma lock when needed. This is required because
there may be other threads in the system even if
opal_using_threads() is false. Additionally, since it is safe to do
so (the vma lock is recursive) the vma interface has been made
thread safe.
- Avoid calling free() while holding a lock. This avoids race
conditions with locks held outside the Open MPI code.
Fixesopen-mpi/ompi#1654.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Update external as well
Revise the change: we still need the MPI_Barrier in MPI_Finalize when we use a blocking fence, but do use the "lazy" wait for completion. Replace the direct logic in MPI_Init with a cleaner macro
WRAPPER_EXTRA flags are checked *before* the POST_CONFIG macro is
invoked. So set them in the main CONFIG macro.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
This commit adds an additional check for 64-bit atomic support for __sync
builtins. If 64-bit support is not available the opal_atomic_*_64 atomics
are disabled.
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
xlc 13.1.0 crashes because of our may_alias attributes in nolibxml.c
on Power7. libxml.c and nolibxml.c are the only may_alias users for now,
so change our configure check to match the actual code using it.
Thanks to Paul Hargrove for reporting and debugging the issue,
and providing the patch.
https://www.open-mpi.org/community/lists/devel/2016/05/18918.php
(cherry picked from open-mpi/hwloc@0ab7af5e90)
Per discussion on the mailing list and with IBM, remove the AIX timer
code (since AIX is no longer supported).
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
