Cisco v1.6 git commit 913ec6c and upstream trunk r29593 (segfault fix)
introduced a performance regression by inadvertently disabling the
`module_recv_buffers` functionality. With those changes in place, the
`btl_usnic_recv.c` logic would end up mallocing a buffer that should
have otherwise come from a `module_recv_buffers` pool. It also resulted
in a small, bounded memory leak (128 buffers at each power-of-two size
interval).
The new version just places the buffer after the free list item with a
flexible array member. I bumped the pool to allocate all 128 elements
up front because the deferred allocation was modestly impacting IMB
Sendrecv performance at a few sizes.
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29631.
The following SVN revision numbers were found above:
r29593 --> open-mpi/ompi@1ed9b8ff43
Only use Portals on communicators with more than one rank
Fix computation of number of children when using the hypercube tree
This commit was SVN r29616.
Without this commit, if you run IMB pingpong between two nodes with only
one usnic selected (e.g., via `--mca btl_usnic_if_include usnic_0`) then
the run will seem fine but will segfault at MPI_Finalize time.
This behavior has happened since Cisco v1.6 git commit ec7ddf8, upstream
trunk r29484, and upstream v1.7 r29507.
Root cause was that the free list element was being used as the recv
buffer instead of the data buffer associated with the element. So the
reassembly code would stomp all over the free list element, which would
cause the destructor to explode when the free list attempted to clean up
all of its elements. This surprisingly did not cause any other problems
until now.
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29593.
The following SVN revision numbers were found above:
r29484 --> open-mpi/ompi@a6ed232a10
r29507 --> open-mpi/ompi@790d269ce8
If we need to use a convertor, go back to stashing that convertor in the
frag and populating segments "on the fly" (in
ompi_btl_usnic_module_progress_sends). Previously we would pack into a
chain of chunk segments at prepare_src time, unnecessarily consuming
additional memory.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29592.
This makes it a little easier to see what's happening with callbacks to
the PML.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29591.
This includes suppressing picky-mode warnings about __VA_ARGS__, which
we know are supported by any compilers we care about.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29590.
Ensure that they never are touched by checking in their destructors.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29589.
Let imagine that we have two btls in btl_openib_component_init() both points to the same openib_btl->device and as a result have the same openib_btl->device->endpoints array.
Finalization phase calls twice mca_btl_openib_finalize()->mca_btl_openib_finalize_resources().
mca_btl_openib_finalize_resources() frees endpoint related btl. But the second call of mca_btl_openib_finalize_resources() checks endpoint that is released by previus call.
fixed by Igor, reviewed by miked/vasily
cmr=v1.7.4:reviewer=ompi-gk1.7
This commit was SVN r29563.
This commit moves all the module stats into their own struct so that
the stats only need to appear as a single line in the module_t
definition, and then moves all the logic for reporting the stats into
btl_usnic_stats.c|h.
Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities
(i.e., not bound to any particular MPI handle), and are marked as
READONLY and CONTINUOUS. They currently all default to verbose level
5 ("Application tuner / detailed", according to
https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels).
Most of the statistics are counters, but a small number are high
watermark values. Due to how counters are reported via MPI_T, none of
the counters are exported through MPI_T if the MCA param
btl_usnic_stats_relative=1 (i.e., the module resets the stats back to
zero at a given frequency).
When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it
will return a count that is equal to the number of active usnic BTL
modules. The values returned for any given pvar (e.g.,
num_total_sends) are an array containing one value for each active
usnic BTL module. The ordering of values in the array is both
consistent across all usnic pvars and stable throughout a single job:
array slot 0 corresponds to module X, array slot 1 corresponds to
module Y, etc.
Mapping which array slot corresponds to which underlying Linux usnic_X
device works as follows:
* The btl_usnic_devices MPI_T state pvar is associated with a
btl_usnic_device MPI_T enum, and be obtained via
MPI_T_pvar_get_info().
* If all usNIC pvars are of length N, the values [0,N) in the
btl_usnic_device enum are associated with strings of the
corresponding underlying Linux device.
For exampe, to look up which Linux device is reported in all usNIC
pvars' array slot 1, look up the int value 1 in the btl_usnic_devices
enum. Its corresponding string value is underlying Linux device name
(e.g., "usnic_1").
cmr=v1.7.4:subject="usnic BTL MPI_T pvars"
This commit was SVN r29545.
r29479.
This fixes some issues reported awhile ago in the openib btl. There
are a couple more unchecked mallocs but they are a bit more difficult
to fix since they are in void functions (btl_openib_endpoint.c).
Refs trac:2401.
cmr=v1.7.4:reviewer=miked
This commit was SVN r29543.
The following SVN revision numbers were found above:
r29479 --> open-mpi/ompi@d6ead2a3a5
The following Trac tickets were found above:
Ticket 2401 --> https://svn.open-mpi.org/trac/ompi/ticket/2401
and tuned to correctly handle 0 recvcounts.
Tested with the reproducer from #1550.
Refs trac:1559
This commit was SVN r29542.
The following Trac tickets were found above:
Ticket 1559 --> https://svn.open-mpi.org/trac/ompi/ticket/1559
Due to deallocation ordering (and an entirely missed deallocation), we
were leaking modest amounts of memory inside libusnic_verbs.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
This commit was SVN r29485.
- some free lists simply were not being OBJ_DESTRUCTed, so they never
freed their internal memory
- channel->recv_segs.ctx was being assigned in a way that got clobbered
by ompi_free_list_init_new, so the cleanup code that relied on it
being set never ran
- numerous other ".ctx" assignments were similarly ineffectual and were
not being consumed, so I deleted them
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
This commit was SVN r29484.
This new routine can be called in exceptional situations, either
conditionally in BTL code or from a debugger, to help with debugging in
cases where MSGDEBUG1/2 or stats logging are impractical but more detail
is needed.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
This commit was SVN r29483.
Pull the bulk of the functionality out into a new routine,
ompi_btl_usnic_print_stats, which can be used in other debugging
contexts. This also lets us eliminate the module->final_stats state
tracking.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
This commit was SVN r29482.
Follow the convention established by the ompi/mca/common/sm tree and
prefix both the "install" and "no install" versions of the build with
"lib" so that Automake doesn't complain. Differentiate the two by
adding a "_noinst" suffix to the "no install" version.
This commit was SVN r29462.
This change contains a non-mandatory modification
of the MPI-RTE interface. Anyone wishing to support
coprocessors such as the Xeon Phi may wish to add
the required definition and underlying support
****************************************************************
Add locality support for coprocessors such as the Intel Xeon Phi.
Detecting that we are on a coprocessor inside of a host node isn't straightforward. There are no good "hooks" provided for programmatically detecting that "we are on a coprocessor running its own OS", and the ORTE daemon just thinks it is on another node. However, in order to properly use the Phi's public interface for MPI transport, it is necessary that the daemon detect that it is colocated with procs on the host.
So we have to split the locality to separately record "on the same host" vs "on the same board". We already have the board-level locality flag, but not quite enough flexibility to handle this use-case. Thus, do the following:
1. add OPAL_PROC_ON_HOST flag to indicate we share a host, but not necessarily the same board
2. modify OPAL_PROC_ON_NODE to indicate we share both a host AND the same board. Note that we have to modify the OPAL_PROC_ON_LOCAL_NODE macro to explicitly check both conditions
3. add support in opal/mca/hwloc/base/hwloc_base_util.c for the host to check for coprocessors, and for daemons to check to see if they are on a coprocessor. The former is done via hwloc, but support for the latter is not yet provided by hwloc. So the code for detecting we are on a coprocessor currently is Xeon Phi specific - hopefully, we will find more generic methods in the future.
4. modify the orted and the hnp startup so they check for coprocessors and to see if they are on a coprocessor, and have the orteds pass that info back in their callback message. Automatically detect that coprocessors have been found and identify which coprocessors are on which hosts. Note that this algo isn't scalable at the moment - this will hopefully be improved over time.
5. modify the ompi proc locality detection function to look for coprocessor host info IF the OMPI_RTE_HOST_ID database key has been defined. RTE's that choose not to provide this support do not have to do anything - the associated code will simply be ignored.
6. include some cleanup of the hwloc open/close code so it conforms to how we did things in other frameworks (e.g., having a single "frame" file instead of open/close). Also, fix the locality flags - e.g., being on the same node means you must also be on the same cluster/cu, so ensure those flags are also set.
cmr:v1.7.4:reviewer=hjelmn
This commit was SVN r29435.
The following common shared libraries did not have versioning:
* ompi/common/ofacm
* ompi/common/verbs
* ompi/common/ugni
Additionally, we still had shared library versions in VERSION for the
following libraries, which no longer exist:
* ompi/common/portals
* opal/common/hwloc
This commit was SVN r29421.
Fix two problems that surfaced when using direct launch under SLURM:
1. locally store our own data because some BTLs want to retrieve
it during add_procs rather than use what they have internally
2. cleanup MPI_Abort so it correctly passes the error status all
the way down to the actual exit. When someone implemented the
"abort_peers" API, they left out the error status. So we lost
it at that point and *always* exited with a status of 1. This
forces a change to the API to include the status.
cmr:v1.7.3:reviewer=jsquyres:subject=Fix MPI_Abort and modex_recv for direct launch
This commit was SVN r29405.
So we now allow singletons to start on their own, only spawning an HNP when initiating an operation that actually requires it.
cmr:v1.7.4:reviewer=jsquyres
This commit was SVN r29354.
The algorithms are intended for MPI-3.0 compliance and are not
optimized. We should aim to add better algorithms in the future through
cheetah.
MPI_Iallreduce and MPI_Igatherv on intercommunicators are required for
MPI_Comm_idup support.
cmr=v1.7.4:reviewer=brbarret:ticket=trac:2715
This commit was SVN r29333.
The following Trac tickets were found above:
Ticket 2715 --> https://svn.open-mpi.org/trac/ompi/ticket/2715
1. Change in rte api implementation: now comm_world used to do p2p.
This allows to not worry about other comms being destroyed.
2. added a notification mechanism with a help of which runtime can say libhcoll that RTE api can not be used any longer.
pass a pointer to a flag, and its size to libhcoll.
The flag changes when the RTE is no longer available.
Currently this flag is just ompi_mpi_finalized global bool value.
cmr=v1.7.3:reviewer=jladd
This commit was SVN r29331.
Create a new required key in the OMPI layer for retrieving a "node id" from the database. ALL RTE'S MUST DEFINE THIS KEY. This allows us to compute locality in the MPI layer, which is necessary when we do things like intercomm_create.
cmr:v1.7.4:reviewer=rhc:subject=Cleanup handling of modex data
This commit was SVN r29274.
arrays.
The MPI 3.0 standard added const to all in buffers in the C bindings. This
commit adds the const keyword and in most cases casts const away. We will
eventually should go through and update the various interfaces (coll, pml,
io, etc) to take the const keyword. The group, comm, win, and datatype
interfaces have been updated with const.
cmr=v1.7.4:ticket=trac:3785:reviewer=jsquyres
This commit was SVN r29266.
The following Trac tickets were found above:
Ticket 3785 --> https://svn.open-mpi.org/trac/ompi/ticket/3785
Blocking versions are simple linear algorithms implemented in coll/basic. Non-
blocking versions are from libnbc 1.1.1. All algorithms have been tested with
simple test cases.
cmr=v1.7.4:reviewer=jsquyres
This commit was SVN r29265.
Prevent frag from being freed out from under us in the case
the PML callback routine calls usnic_free(). We accomplish this
by delaying decrement of sf_bytes_to_ack until after the callback is
performed, since sf_bytes_to_ack == 0 is condition of freeing the frag.
Fixes Cisco bug CSCuj45094.
Authored-by: Reese Faucette <rfaucett@cisco.com>
cmr=v1.7.3
This commit was SVN r29264.
This commit changes the underlying opal complex datatypes to match the
C99 types: float _Complex, double _Complex, and long double _Complex. The
fortran and C++ types now are aliases to these basic types instead of
structure types. The operators in ompi/mca/op/base now work on only the
C99 types and the fortran types use these operators if the fortran type
matches a C complex type (this should almost always be the case.)
C99 is not is use in both the datatype and operator code and should make
the code both cleaner and much less fragile.
This commit was SVN r29193.
of MPI_Alltoall.
- add support for MPI_IN_PLACE in the self collective component.
- fix the extent usage in the tuned collective component.
- correctly use the peer counts instead of local - add support for MPI_IN_PLACE in the self collective component.
- fix the extent usage in the tuned collective component.
- correctly use the peer counts instead of local.
Thanks to Fujitsu for the patch.
This commit was SVN r29187.
MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and
also when BTL calls PML with a recv completion (not send completions)"
MSGDEBUG1 means print more internal gory detail
MSGDEBUG is gone, replaced by MSGDEBUG1
In the process also found that PUT_DEST style fragments could
potentially be leaked in usnic_free() since send_fragment tests were
being applied to see if it was eligible to be freed.
This commit was SVN r29185.
changes required to support MPI_Bsend(). Introduces concept of
attaching a buffer to a large segment that the PML can scribble into and
we will send from. The reason we don't use a pinned buffer and send
directly from that is that usnic_verbs does not (yes) support num_sge>1
for regular sends. This means the data gets copied twice, but that is
unavoidable.
changed the logic in handle_large_send to be more sensible
Incorporated David's review comments
This commit was SVN r29184.
Do not assume that the "size" passed to alloc_send() will be the same as
the size of the message the resulting fragment will hold when
usnic_send() is called. This means usnic_send()/usnic_put() can never
trust any pre-computed size values, and are only allowed to look at the
lengths and pointers of the elements in the desc SG list.
This commit was SVN r29183.
- tag needs to be sent in *our* header, not the PML header
- usnic_alloc() should return smaller value if too much data requested
- be careful about callbacks vs removing items from lists
(we need to remove from outr lists *before* the callback)
- improve send callback handling
- add some more MSGDEBUG2 logging and cleanup
This commit was SVN r29181.
The intercomm "merge" function can create a linkage between procs that was not reflected anywhere in a modex, and so at least some of the procs in the resulting communicator don't know how to talk to some of the new communicator's peers.
For example, consider the case where:
1. parent job A comm_spawns a process (job B) - these processes exchange modex and can communicate
2. parent job A now comm_spawns another process (job C) - again, these can communicate, but the proc in C knows nothing of B
3. do an intercomm merge across the communicators created by the two comm_spawns. This puts B and C into the same communicator, but they know nothing about how to talk to each other as they were not involved in any exchange of contact info. Hence, collectives on that communicator now fail.
This fix adds an API to the ompi/dpm framework that (a) exchanges the modex info across the procs in the merge to ensure all procs know how to communicate, and (b) calls add_procs to give the btl's a chance to select transports to any new procs.
cmr:v1.7.3:reviewer=jsquyres
This commit was SVN r29166.
The following Trac tickets were found above:
Ticket 2904 --> https://svn.open-mpi.org/trac/ompi/ticket/2904
The FREE_LIST_*_MT stuff was introduced on the SVN trunk in r28722
(2013-07-04), but so far, has not been merged into the v1.7 branch yet
(2013-09-06). So put it in its own #ifdef, rather than defining it
based on OMPI_MAJOR_VERSION/OMPI_MINOR_VERSION.
This commit was SVN r29148.
The following SVN revision numbers were found above:
r28722 --> open-mpi/ompi@c9e5ab9ed1
The Cisco-maintained v1.6 port of the usnic BTL has diverged from the
upstream trunk and v1.7 branches. This commit adjusts the trunk to more
closely match the v1.6 branch to simplify future merging and
cherry-picking.
The usnic MCA parameters also need work on this side.
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29138.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
The fix for the HPL SEGV was incorrect because it assumed the
prepare_src() routine was always allowed to return "bytes processed"
less than the requested "bytes to send". It turns out this is only true
if the convertor is what limits the size, we are not allowed to limit
the data sent for our own reasons, else we break login in the upper
layers.
This means we need to learn the number of bytes out of the size
requested the convertor will give us, no matter how big the size is.
Unfortunately, this is a destructive test, and (currently) the only way to
learn that number is to actually have the convertor copy the data out into
buffers.
This change implements this, copying the entire data out into a chain of
send segments which are attached to the large send fragment. Now we can
always return the proper size value to the PML.
Fixes Cisco bug CSCuj08024
Authored-by: Reese Faucette <rfaucett@cisco.com>
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29137.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
Authored-by: Reese Faucette <rfaucett@cisco.com>
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29136.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29135.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29134.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
- round segment buffer allocation to cache-line
- split some routines into an inline fast section and a called
slower section
- introduce receive fastpath in component_progress that:
o returns immediately if there is a packet available on priority
queue and fastpath is enabled
o disables fastpath for 1 time after use to provide fairness to
other processing
o defers receive buffer posting
o defers bookeeping for receive until next call
to usnic_component_progress
Authored-by: Reese Faucette <rfaucett@cisco.com>
Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760)
This commit was SVN r29133.
The following Trac tickets were found above:
Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
Without this, an `--enable-debug` build would hit an assertion in the
list code when run under valgrind with `--malloc-fill=0xff` or any other
case where malloc returned non-zeroed buffers.
Also allow the normal OBJ_ machinery to handle the constructor
invocation ordering for us instead of doing it by hand (which could have
led to future bugs).
Reviewed-by: jsquyres@cisco.com
cmr=v1.7.4
Depends on trunk functionality in r29095 and r29096. Refs trac:3740,#3741.
This commit was SVN r29127.
The following SVN revision numbers were found above:
r29095 --> open-mpi/ompi@d1b5940e97
r29096 --> open-mpi/ompi@a552921171
The following Trac tickets were found above:
Ticket 3740 --> https://svn.open-mpi.org/trac/ompi/ticket/3740
configure-time dynamic allocation of flags. The net result for platforms
which only support BTL-based communication is a reduction of 8*nprocs bytes
per process. Platforms which support both MTLs and BTLs will not see
a space reduction, but will now be able to safely run both the MTL and BTL
side-by-side, which will prove useful.
This commit was SVN r29100.
The usnic BTL now builds cleanly under `--enable-picky` when `MSGDEBUG1`
is set.
Reviewed-by: jsquyres
cmr=v1.7.4:reviewer=jsquyres
This commit was SVN r29097.
osc_pt2pt_data_move.c: In function 'ompi_osc_pt2pt_sendreq_recv_accum_long_cb':
osc_pt2pt_data_move.c:643:9: warning: variable 'ret' set but not used [-Wunused-but-set-variable]
osc_rdma_data_move.c: In function 'ompi_osc_rdma_control_send_cb':
osc_rdma_data_move.c:1312:37: warning: variable 'header' set but not used [-Wunused-but-set-variable]
This commit was SVN r29092.
endpoint_rfstart was being initialized from a value which was not yet
set. Also ensure that rfstart is a valid index in the range
0..WINDOW_SIZE-1, since it is used as the index into endpoint_rcvd_segs,
which has WINDOW_SIZE elements.
Without this change there is significant risk of memory corruption or
segfaults, resulting in hangs or crashes, if malloc ever returns us a
value >=WINDOW_SIZE (4096). Right now we seem to be getting lucky that
the malloc is returning zero-pages to us when we are allocating endpoint
structures (possibly because the freelist performs a single large
allocation for all endpoints).
Fixes Cisco bug CSCui88781.
Reviewed-by: rfaucett@cisco.com
Reviewed-by: jsquyres@cisco.com
cmr=v1.7.3:reviewer=jsquyres
This commit was SVN r29075.
option to autodetect whether fragmentation should be enabled
cmr=v1.7.3:ticket=trac:3717
This commit was SVN r29065.
The following Trac tickets were found above:
Ticket 3717 --> https://svn.open-mpi.org/trac/ompi/ticket/3717
* paccept - establish a persistent listening port for async connect requests
* pconnect - async connect to remote process that has posted a paccept port. Provides a timeout mechanism, and allows the underlying implementation to retry until timeout
* pclose - shuts down a prior paccept posting
Includes example programs paccept.c and pconnect.c in orte/test/mpi. New MPI extension interfaces coming...
This commit was SVN r29063.
Turns out that AC_CHECK_DECLS is one of the "new style" Autoconf
macros that #defines the output to be 0 or 1 (vs. #define'ing or
#undef'ing it). So don't check for "#if defined(..."; just check for
"#if ...".
This commit was SVN r29059.
The following Trac tickets were found above:
Ticket 3730 --> https://svn.open-mpi.org/trac/ompi/ticket/3730
*** 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.
So shift the cutoff param to the MPI layer, and have it solely determine whether or not we call modex_recv on the hostname. If comm_world is of size greater than the cutoff, then we don't automatically retrieve the hostname when we build the ompi_proc_t for a process - instead, we fill the hostname entry on first call to modex_recv for that process.
The param is now "ompi_hostname_cutoff=N", where N=number of procs for cutoff.
Refs trac:3729
This commit was SVN r29056.
The following Trac tickets were found above:
Ticket 3729 --> https://svn.open-mpi.org/trac/ompi/ticket/3729
Commit r27211 added ifdef checks for #define
HAVE_IBV_LINK_LAYER_ETHERNET, which is incorrect. The correct #define
is HAVE_DECL_IBV_LINK_LAYER_ETHERNET. This broke OMPI over iWARP.
This fixes trac:3726 and should be added to cmr:v1.7.3:reviewer=jsquyres
This commit was SVN r29053.
The following SVN revision numbers were found above:
r27211 --> open-mpi/ompi@b27862e5c7
The following Trac tickets were found above:
Ticket 3726 --> https://svn.open-mpi.org/trac/ompi/ticket/3726
* add a new MCA param orte_hostname_cutoff to specify the number of nodes at which we stop including hostnames. This defaults to INT_MAX => always include hostnames. If a value is given, then we will include hostnames for any allocation smaller than the given limit.
* remove ompi_proc_get_hostname. Replace all occurrences with a direct link to ompi_proc_t's proc_hostname, protected by appropriate "if NULL"
* modify the OMPI-ORTE integration component so that any call to modex_recv automatically loads the ompi_proc_t->proc_hostname field as well as returning the requested info. Thus, any process whose modex info you retrieve will automatically receive the hostname. Note that on-demand retrieval is still enabled - i.e., if we are running under direct launch with PMI, the hostname will be fetched upon first call to modex_recv, and then the ompi_proc_t->proc_hostname field will be loaded
* removed a stale MCA param "mpi_keep_peer_hostnames" that was no longer used anywhere in the code base
* added an envar lookup in ess/pmi for the number of nodes in the allocation. Sadly, PMI itself doesn't provide that info, so we have to get it a different way. Currently, we support PBS-based systems and SLURM - for any other, rank0 will emit a warning and we assume max number of daemons so we will always retain hostnames
This commit was SVN r29052.
This creates a really bad scaling behavior. Users have found a nearly 20% launch time differential between mpirun and PMI, with PMI being the slower method. Some of the problem is attributable to poor exchange algorithms in RM's like Slurm and Alps, but we make things worse by calling "get" so many times.
Nathan (with a tad advice from me) has attempted to alleviate this problem by reducing the number of "get" calls. This required the following changes:
* upon first request for data, have the OPAL db pmi component fetch and decode *all* the info from a given remote proc. It turned out we weren't caching the info, so we would continually request it and only decode the piece we needed for the immediate request. We now decode all the info and push it into the db hash component for local storage - and then all subsequent retrievals are fulfilled locally
* reduced the amount of data by eliminating the exchange of the OMPI_ARCH value if heterogeneity is not enabled. This was used solely as a check so we would error out if the system wasn't actually homogeneous, which was fine when we thought there was no cost in doing the check. Unfortunately, at large scale and with direct launch, there is a non-zero cost of making this test. We are open to finding a compromise (perhaps turning the test off if requested?), if people feel strongly about performing the test
* reduced the amount of RTE data being automatically fetched, and fetched the rest only upon request. In particular, we no longer immediately fetch the hostname (which is only used for error reporting), but instead get it when needed. Likewise for the RML uri as that info is only required for some (not all) environments. In addition, we no longer fetch the locality unless required, relying instead on the PMI clique info to tell us who is on our local node (if additional info is required, the fetch is performed when a modex_recv is issued).
Again, all this only impacts direct launch - all the info is provided when launched via mpirun as there is no added cost to getting it
Barring objections, we may move this (plus any required other pieces) to the 1.7 branch once it soaks for an appropriate time.
This commit was SVN r29040.
non-contiguous converter. We can't "convert on the fly" because the #
of bytes requested may not divide evenly into the convertor data type.
This commit was SVN r29014.
spawning a process using MPI_Comm_spawn. For this, the first operation has to
be collective which we can not guarantuee outside of the MPI_File_open
operation.
This commit was SVN r29008.
improvements:
* Fix minor memory leaks during component_init
* Ensure that an initialization loop does not underflow an unsigned int
* Improve mlock limit checking
* Fix set of BTL modules created during component_init when failing to
get QP resources or otherwise excluding some (but not all) usnic
verbs devices
* Fix/improve error messages to be consistent with other Cisco
documentation
* Randomize the initial sliding window sequence number so that we
silently drop incoming frames from previous jobs that still have
existant processes in the middle of dying (and are still
transmitting)
* Ensure we don't break out of add_procs too soon and create an
asymetrical view of what interfaces are available
This commit was SVN r28975.
mpi_leave_pinned_pipeline
This change should improve performance is the non-pinned case where
the same memory region is involved in multiple simultaneous transfers.
cmr=v1.7.3:reviewer=brbarret
This commit was SVN r28973.
Working on faster algorithms for tuned that will come at a later time.
cmr=v1.7.3:ticket=trac:2965
This commit was SVN r28952.
The following Trac tickets were found above:
Ticket 2965 --> https://svn.open-mpi.org/trac/ompi/ticket/2965
Use the new sysfs files to check that there are enough VFs, QPs, and
CQs for all the MPI processes on this server.
Move the checking code into its own subroutine to make it smaller and
easier to read/grok.
This commit was SVN r28937.
Brian (rightfully) hit me on the head with the
don't-use-ORTE-use-the-rte-framework clue bat; the usnic BTL now
nicely plays with the RTE framework.
This commit was SVN r28907.
Note that the PMI RTE still doesn't listen for asynchronous errors, so
the error handler still won't ever actually do anything :).
This commit was SVN r28886.
The following SVN revision numbers were found above:
r28852 --> open-mpi/ompi@e4e678e234
This BTL accesses the Cisco usNIC Linux device via the Linux verbs
API via Unreliable Datagram queue pairs. A few noteworthy points:
* This BTL does most of its own fragmentation; it tells the PML that
it has a very high max_send_size (much higher than the network
MTU).
* Since UD fragments are, by definition, unreliable, the usnic BTL
handles all of its own reliability via a sliding window approach
using the opal_hotel construct and many tricks stolen from the
corpus of knowledge surrounding efficient TCP.
* There is a fun PML latency-metric based optimization for NUMA
awareness of short messages.
* Note that this is ''not'' a generic UD verbs BTL; it is specific to
the Cisco usNIC device.
This commit was SVN r28879.
George and I were talking about ORTE's error handling the other day in regards to the right way to deal with errors in the updated OOB. Specifically, it seemed a bad idea for a library such as ORTE to be aborting the job on its own prerogative. If we lose a connection or cannot send a message, then we really should just report it upwards and let the application and/or upper layers decide what to do about it.
The current code base only allows a single error callback to exist, which seemed unduly limiting. So, based on the conversation, I've modified the errmgr interface to provide a mechanism for registering any number of error handlers (this replaces the current "set_fault_callback" API). When an error occurs, these handlers will be called in order until one responds that the error has been "resolved" - i.e., no further action is required - by returning OMPI_SUCCESS. The default MPI layer error handler is specified to go "last" and calls mpi_abort, so the current "abort" behavior is preserved unless other error handlers are registered.
In the register_callback function, I provide an "order" param so you can specify "this callback must come first" or "this callback must come last". Seemed to me that we will probably have different code areas registering callbacks, and one might require it go first (the default "abort" will always require it go last). So you can append and prepend, or go first. Note that only one registration can declare itself "first" or "last", and since the default "abort" callback automatically takes "last", that one isn't available. :-)
The errhandler callback function passes an opal_pointer_array of structs, each of which contains the name of the proc involved (which can be yourself for internal errors) and the error code. This is a change from the current fault callback which returned an opal_pointer_array of just process names. Rationale is that you might need to see the cause of the error to decide what action to take. I realize that isn't a requirement for remote procs, but remember that we will use the SAME interface to report RTE errors internal to the proc itself. In those cases, you really do need to see the error code. It is legal to pass a NULL for the pointer array (e.g., when reporting an internal failure without error code), so handlers must be prepared for that possibility. If people find that too burdensome, we can remove it.
Should we ever decide to create a separate callback path for internal errors vs remote process failures, or if we decide to do something different based on experience, then we can adjust this API.
This commit was SVN r28852.
- extend the framework API
- remove the dummy component, not require anymore
- add four components to perform the actual job.
This commit was SVN r28828.
soon:
- add a new abstraction layer to be used internally for some operations
- add a new mca parameter to control lazy intialization of shared file
pointer structures
This commit was SVN r28826.
This commit improved the small message latency and bandwidth when using
the vader btl. These improvements should make performance competative
with other MPI implementations.
This commit was SVN r28760.
many builds. I am temporarily .ompi_ignore'ing this component until
it can be fixed by its owner.
* It calls AC_MSG_ERROR, which configure.m4 scripts are ''never''
supposed to do. If you don't want to build, then call $2.
* All static and --disable-dlopen builds are broken; they fall afoul
of whatever test configure.m4 is doing and therefore error out of
configure entirely (vs. simply disabling the hcoll component).
* There appear to be multiple shell scripting errors in the
configure.m4. Here's the output of "./configure --disable-dlopen":
{{{
--- MCA component coll:hcoll (m4 configuration macro)
checking for MCA component coll:hcoll compile mode... static
checking --with-hcoll value... simple ok (unspecified)
./configure: line 421: test: basic: integer expression expected
configure: error: Can not use coll/hcoll and coll/ml (static build)
simultaneously. You have two options:
1. Use static build & disable ml with:
--enable-mpi-no-build=coll-ml
2. Use dso build for ML & disable ml at runtime: -mca
coll self
./configure: line 310: return: basic: numeric argument required
./configure: line 320: exit: basic: numeric argument required
}}}
Finally, all of these configure.m4 errors aside, I don't understand
why there is a ''compile-time'' exclusion between the hcoll and ml
components. Why isn't this a ''run-time'' decision? Having what
seems to be an unnecessary compile-time exclusion goes against the
general Open MPI philosophy.
Note: Open MPI 1.7 is also broken in all the same ways. I suggest
that the RM's .ompi_ignore hcoll over there, too.
Mellanox: please fix.
This commit was SVN r28748.
