Move away from verbs-specific terms "device" and "port" in the usnic
BTL help messages. Replace them with "usNIC interface" (since usNIC
has no concept of a port).
cmr=v1.8.2:ticket=trac:4734
This commit was SVN r32029.
The following Trac tickets were found above:
Ticket 4734 --> https://svn.open-mpi.org/trac/ompi/ticket/4734
Now that the infrastructure is calling BTL del_procs() before the BTL
finalize(), the usnic BTL had to re-order some of its teardown
sequence to avoid assert() failing.
This is part of a larger conversation involving #4669. Since
MPI_FINALIZE and MPI_COMM_DISCONNECT currently use an
oob/grpcomm-based barrier, the usnic BTL can ''absolutely know'' that
these endpoints and procs will no longer be used. If the ORTE DPM
goes back to a PML-based barrier, the usnic BTL will need to grow more
complex teardown semantics (a la TCP socket FIN/ACK/FIN_WAIT states).
Refs trac:4669
This commit was SVN r31871.
The following Trac tickets were found above:
Ticket 4669 --> https://svn.open-mpi.org/trac/ompi/ticket/4669
Two things to note:
- This change will allow us to expand the BTL interface without
having to worry about modifying BTLs that will not support the new
interfaces. More on this will come later this year as part of the
1.9 series.
- C99 guarantees that uninitialed members of structs declared outside
of functions (DATA binary section) will be initialized with
0's. This allows us to drop stuff like .btl_flags = 0, or .btl_get
= NULL.
This commit was SVN r31388.
If ompi_modex_recv() fails with OPAL_ERR_DATA_VALUE_NOT_FOUND, it
simply means that the peer process did not put any usnic BTL modex
info -- it is not an error. So have the usnic BTL simply ignore that
peer (vs. disqualifying itself / treating this like a real error).
Refs trac:4442.
This commit was SVN r31258.
The following Trac tickets were found above:
Ticket 4442 --> https://svn.open-mpi.org/trac/ompi/ticket/4442
* Ensure that all endpoints[x] values are initialized to NULL
* If ibv_create_ah fails, remove each endpoint from the
module->all_endpoints list so that the endpoint can be destructed
properly.
Submitted by Jeff Squyres, reviewed by Dave Goodell.
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r31111.
Follow on to SVN trunk r30850: consolidate the ibv_create_ah() calls
into a single loop, MPI_WAITALL-style. That is, call the (effectively
non-blocking) ibv_create_ah() for each endpoint. If we get
NULL+EAGAIN, it means that the UDP ARP is still ongoing down in the
kernel, so just try again later. We put these all into a single loop
because it allows us to parallelize the ARP progress in the kernel.
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30879.
The following SVN revision numbers were found above:
r30850 --> open-mpi/ompi@3641500442
r30852 --> open-mpi/ompi@4e282a3295
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
Basically: since usnic is a connectionless transport, we do not get
OS-provided services "for free" that connection-oriented transports
get, namely: "hey, I wasn't able to make a connection to peer X", and
"hey, your connection to peer X has died."
This connectivity-checker runs in a separate progress thread in the
usnic BTL in local rank 0 on each server. Upon first send in any
process, the connectivty-checker agent will send some UDP pings to the
peer to ensure that we can reach it. If we can't, we'll abort the job
with a nice show_help message.
There's a lengthy comment in btl_usnic_connectivity.h explains the
scheme and how it works.
Reviewed by Dave Goodell.
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30860.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
Follow on to SVN trunk r30850: consolidate the ibv_create_ah() calls
into a single loop, MPI_WAITALL-style. That is, call the (effectively
non-blocking) ibv_create_ah() for each endpoint. If we get
NULL+EAGAIN, it means that the UDP ARP is still ongoing down in the
kernel, so just try again later. We put these all into a single loop
because it allows us to parallelize the ARP progress in the kernel.
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30852.
The following SVN revision numbers were found above:
r30850 --> open-mpi/ompi@3641500442
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
Prior to this commit we matched local interfaces to remote interfaces in
order to create endpoints in a simplistic way. If any remote interfaces
were on the same subnet as any of our local interfaces then only local
interfaces would be paired (IP-routed remote interfaces would be
ignored).
This commit introduces a more general scheme which attempts to make the
"best" pairing of local interfaces to remote interfaces. We now cast
the problem as a graph theory problem known as the "Assignment Problem",
or finding a maximum-cardinality, minimum-weight bipartite matching. We
solve this problem by reducing the bipartite graph of interface
connectivity to a flow network and then solving for a minimum cost flow.
This is then easily converted into back into a matching on the original
bipartite graph.
In the new scheme, interfaces on the same subnet are preferred over
interfaces requiring intermediate routing hops and higher bandwidth
links are preferred over lower bandwidth links.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30849.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
These includes only exist in the Cisco-internal usnic-v1.6 code base,
but they should not exist anywhere except btl_usnic_compat.h in order to
minimize source differences between usnic-v1.6 and v1.7/trunk.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30844.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
This commit decouples OMPI deployment from the version(s) of the lower
layers of the stack by probing for UDP support.
Verbs applications assume a 40-byte header (there is no current
mechanism for querying payload offset). So to support a 42-byte UDP
header without causing existing applications like ibv_ud_pingpong or
older versions of OMPI to crash, we must inform libusnic_verbs that we
are aware of the nonstandard payload offset. We do this by overriding
the `transport_type` field of the device to be 42 before calling
`ibv_open_device`. If the library resets it to something else, then we
know the lower layers are UDP capable. Otherwise we use the older
custom-L2 format.
This necessitated some minor ugliness in common_verbs, but it's as tidy
as Jeff and I know how to make it right now.
This commit only adds support for UDP headers and connectivity over the
same L2 network, it does not touch routing or interface pairing.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30838.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
Authored-by: Reese Faucette <rfaucett@cisco.com>
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30834.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
Valgrind showed this one, just a bit of sloppiness with the reference
counting.
Reviewed-by: Jeff Squyres <jsquyres@cisco.com>
cmr=v1.7.5:ticket=trac:4253
This commit was SVN r30832.
The following Trac tickets were found above:
Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
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
We're going to be bringing a bunch of usnic code to the SVN trunk
soon, and I basically brought this commit over out of order. So I'm
reverting it for now; the same functionality will come back shortly.
This commit was SVN r30805.
The following SVN revision numbers were found above:
r30804 --> open-mpi/ompi@5bedcc15bf
These constants are now upstream (see
https://git.kernel.org/cgit/libs/infiniband/libibverbs.git/commit/?id=f57a9c67eabb9e7f19c624ac3c8c27b7be55796c),
so let's support them properly in Open MPI.
Added bonus: consolidating these checks up in
ompi_check_openfabrics.m4 allowed removing some custom checks and
AC_DEFINE's from the usnic configure.m4 script.
Also change the usnic/configure.m4 check for IBV_EVENT_GID_CHANGE to
use AC_CHECK_DECLS (vs. AC_CHECK_DECL).
cmr=v1.7.5:reviewer=dgoodell
This commit was SVN r30804.
* Use the prefix rule for global variables
* Elimiante seed_prng() since it isn't necessary any more
These files will need to get edited again then the RNG type obeys the
prefix rule.
Refs trac:4298
This commit was SVN r30803.
The following SVN revision numbers were found above:
r30801 --> open-mpi/ompi@e39d9f4080
The following Trac tickets were found above:
Ticket 4298 --> https://svn.open-mpi.org/trac/ompi/ticket/4298
* Remove some set-but-not-used variables
* Make a convenience function return void (we weren't using the
return code, anyway)
* Mark a function as inline (it was supposed to be inline anyway)
Reviewed by Dave Goodell.
cmr=v1.7.5:reviewer=ompi-rm1.7:subject=Fix usnic BTL compiler warnings
This commit was SVN r30160.
branch (it's not necessary on trunk/v1.7 because they require C99,
which allows variadic macros).
Also fix another compiler warning (using %p to print a (void*)).
Submitted by Jeff, reviewed by Dave.
cmr=v1.7.4:reviewer=ompi-rm1.7:subject=two usnic BTL fixes
This commit was SVN r29966.
usnic_channel_finalize() was deregistering recv buffers before
destroying the QP to which they were posted. The QP needs to be
destroyed first so that the NIC does not attemp tto write to
deregistered memory, causing the DMAR messages.
Submitted by Reese, reviewed by Jeff.
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r29963.
Note that this event should never happen within a single OMPI job,
because OMPI will ignore usnic ports that are down. The PORT_ACTIVE
event should only occur if a port ''was'' down and is now ''up''. But
what the heck -- if we ever do get this event, it is harmless -- just
ignore it.
This commit was SVN r29852.
On the off chance that the PML is twiddling fields that it really
shouldn't be...
Reviewed-by: Reese Faucette <rfaucett@cisco.com>
This commit was SVN r29804.
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
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 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.
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.
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.
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.
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 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
- 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
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.
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.
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.
