*** 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.
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.
This commit reintroduces key compression into the pmi db. This feature
compresses the keys stored into the component into a small number of
PMI keys by serializing the data and base64 encoding the result. This
will avoid issues with Cray PMI which restricts us to ~ 3 PMI keys per
rank.
This commit was SVN r28993.
Add support for MPI_Count type and MPI_COUNT datatype and add the required
MPI-3 functions MPI_Get_elements_x, MPI_Status_set_elements_x,
MPI_Type_get_extent_x, MPI_Type_get_true_extent_x, and MPI_Type_size_x.
This commit adds only the C bindings. Fortran bindins will be added in
another commit. For now the MPI_Count type is define to have the same size
as MPI_Offset. The type is required to be at least as large as MPI_Offset
and MPI_Aint. The type was initially intended to be a ssize_t (if it was
the same size as a long long) but there were issues compiling romio with
that definition (despite the inclusion of stddef.h).
I updated the datatype engine to use size_t instead of uint32_t to support
large datatypes. This will require some review to make sure that 1) the
changes are beneficial, 2) nothing was broken by the change (I doubt
anything was), and 3) there are no performance regressions due to this
change.
Increase the maximum number of predifined datatypes to support MPI_Count
Put common get_elements code to ompi/datatype/ompi_datatype_get_elements.c
Update MPI_Get_count to reflect changes in MPI-3 (return MPI_UNDEFINED when the count is too large for an int)
This commit was SVN r28932.
This commit adds an API for registering and querying performance
variables (mca_base_pvar) in the MCA base. The existing MCA variable
system API has been updated to reflect the new API: MCA variable
groups have performance variables, and new types have been added (double,
unsigned long long) to reflect what is required by the MPI_T
interface. Additionally, the MCA variable group code has been split
into its own set of files: mca_base_var_group.[ch].
Details of the new API can be found in doxygen comments in the header:
mca_base_pvar.h.
Other changes to the variable system:
- Use an opal_hash_table to speed up variable/group lookup.
- Clean up code associated with MCA variable types.
- Registered performance variables are printed by ompi_info -a. In the
future an option should be added to control this behavior.
Changes to OMPI:
- Added full support for the MPI_T performance variable interface.
This commit was SVN r28800.
(since this is used in the fast path) for when you ''know'' that there
will be a room available:
* Don't do the last_unoccupied_room check
* Return void
This commit was SVN r28757.
Add an option to ompi_info (-l, --level) that takes a number in the
interval (1,9). Only MCA variables up to this level will be printed.
The default level is 1.
Print the level as part of both the parsable and readable output.
This commit was SVN r28750.
sandbox team has informed me that they are getting rid of SANDBOX_PID
in the future and that using SANDBOX_ON would be preferred.
This commit was SVN r28708.
To resolve this situation, add the ability to specify a backend topology file that mpirun shall use for its mapping operations. Create a new "set_topology" function in opal hwloc to support it.
This commit was SVN r28682.
