onflict that can cause messages to be lost. Add detection of this condition, and have both processes cancel their connect operations. The process with the higher rank will
reconnect, while the lower rank process will simply wait for the connection to be created.
Refs trac:3696
This commit was SVN r29139.
The following Trac tickets were found above:
Ticket 3696 --> https://svn.open-mpi.org/trac/ompi/ticket/3696
*** 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.
Roll in the ORTE state machine. Remove last traces of opal_sos. Remove UTK epoch code.
Please see the various emails about the state machine change for details. I'll send something out later with more info on the new arch.
This commit was SVN r26242.
specify btl_tcp_if_include because btl_tcp_if_exclude is defaulted to
the loopback devices.
This commit does a few things:
* Introduce a new OPAL MCA base function:
mca_base_param_check_exclusive_string(). It checks to see that the
''user'' does not set two MCA parameters that are mutually
exclusive by checking the source of those MCS param values.
* Use the above function in many BTLs (and the OOB TCP) to ensure
that <foo>_if_include and <foo>_if_exclude are not both specified
''by the user''.
* Re-arrange many of these BTLs to move their MCA registration code
into a separate component_register() function (vs. the
component_open() function).
This code has been nominally reviewed and checked by Ralph, George,
Terry, and Shiqing.
This commit was SVN r25043.
The following SVN revision numbers were found above:
r24976 --> open-mpi/ompi@8f4ac54336
- Delete unnecessary header files using
contrib/check_unnecessary_headers.sh after applying
patches, that include headers, being "lost" due to
inclusion in one of the now deleted headers...
In total 817 files are touched.
In ompi/mpi/c/ header files are moved up into the actual c-file,
where necessary (these are the only additional #include),
otherwise it is only deletions of #include (apart from the above
additions required due to notifier...)
- To get different MCAs (OpenIB, TM, ALPS), an earlier version was
successfully compiled (yesterday) on:
Linux locally using intel-11, gcc-4.3.2 and gcc-SVN + warnings enabled
Smoky cluster (x86-64 running Linux) using PGI-8.0.2 + warnings enabled
Lens cluster (x86-64 running Linux) using Pathscale-3.2 + warnings enabled
This commit was SVN r21096.
- This patch solely _adds_ required headers and is rather localized
The next patch (after RFC) heavily removes headers (based on script)
- ompi/communicator/communicator.h: For sources that use
ompi_mpi_comm_world, don't require them to include "mpi.h"
- ompi/debuggers/ompi_common_dll.c: mca_topo_base_comm_1_0_0_t needs
#include "ompi/mca/topo/topo.h"
- ompi/errhandler/errhandler_predefined.h:
ompi/communicator/communicator.h depends on this header file!
To prevent recursion just have fwd declarations.
#include "ompi/types.h" for fwd declarations of the main structs.
- ompi/mca/btl/btl.h: #include "opal/types.h" for ompi_ptr_t
- ompi/mca/mpool/base/mpool_base_tree.c: We use ompi_free_list_t and
ompi_rb_tree_t, so have the proper classes
- ompi/mca/op/op.h:
Op is pretty self-contained: Nobody up to now has done
#include "opal/class/opal_object.h"
- ompi/mca/osc/pt2pt/osc_pt2pt_replyreq.h:
#include "opal/types.h" for ompi_ptr_t
- ompi/mca/pml/base/base.h:
We use opal_lists
- ompi/mca/pml/dr/pml_dr_vfrag.h:
#include "opal/types.h" for ompi_ptr_t
- ompi/mca/pml/ob1/pml_ob1_hdr.h:
#include "ompi/mca/btl/btl.h" for mca_btl_base_segment_t
- opal/dss/dss_unpack.c:
#include "opal/types.h"
- opal/mca/base/base.h:
#include "opal/util/cmd_line.h" for opal_cmd_line_t
- orte/mca/oob/tcp/oob_tcp.c:
#include "opal/types.h" for opal_socklen_t
- orte/mca/oob/tcp/oob_tcp.h:
#include "opal/threads/threads.h" for opal_thread_t
- orte/mca/oob/tcp/oob_tcp_msg.c:
#include "opal/types.h"
- orte/mca/oob/tcp/oob_tcp_peer.c:
#include "opal/types.h" for opal_socklen_t
- orte/mca/oob/tcp/oob_tcp_send.c:
#include "opal/types.h"
- orte/mca/plm/base/plm_base_proxy.c:
#include "orte/util/name_fns.h" for ORTE_NAME_PRINT
- orte/mca/rml/base/rml_base_receive.c:
#include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE
- orte/mca/rml/oob/rml_oob_recv.c:
#include "opal/types.h" for ompi_iov_base_ptr_t
- orte/mca/rml/oob/rml_oob_send.c:
#include "opal/types.h" for ompi_iov_base_ptr_t
- orte/runtime/orte_data_server.c
#include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE
- orte/runtime/orte_globals.h:
#include "orte/util/name_fns.h" for ORTE_NAME_PRINT
Tested on Linux/x86-64
This commit was SVN r20817.
y combination of comma-separated values and ranges. Daemons will use the first port in the range, MPI procs will use the other ports in the range assuming that they know their node rank in time and enough ports were specified.
NOTE: this capability only works under specific conditions. I will outline more about this in a note to devel as the remainder of the implementation progresses. For now, the only environment where this works is slurm. The linear routed module has also been adjusted to work with static ports so that all messaging flows strictly through the topology, including the initial daemon callback - thus limiting the number of sockets opened by mpirun.
This commit was SVN r20390.
* add "register" function to mca_base_component_t
* converted coll:basic and paffinity:linux and paffinity:solaris to
use this function
* we'll convert the rest over time (I'll file a ticket once all
this is committed)
* add 32 bytes of "reserved" space to the end of mca_base_component_t
and mca_base_component_data_2_0_0_t to make future upgrades
[slightly] easier
* new mca_base_component_t size: 196 bytes
* new mca_base_component_data_2_0_0_t size: 36 bytes
* MCA base version bumped to v2.0
* '''We now refuse to load components that are not MCA v2.0.x'''
* all MCA frameworks versions bumped to v2.0
* be a little more explicit about version numbers in the MCA base
* add big comment in mca.h about versioning philosophy
This commit was SVN r19073.
The following Trac tickets were found above:
Ticket 1392 --> https://svn.open-mpi.org/trac/ompi/ticket/1392
Like btl_tcp_disable_family, this parameter more or less disables
a whole address family. Though the sockets are still created, the
corresponding information isn't added to the connection strings.
Likewise, we don't try to connect to addresses matching the disabled
address family.
This is particularly important for multidomain clusters, where IPv4 is
oftenly filtered (firewalled), sometimes by simply dropping the packets
instead of rejecting them (thus causing a connection timeout instead of
a quick "no route to host").
This commit was SVN r18163.
has his own range which is defined by a min value and a range. By default
there is no limitation on the port range, which is exactly the same
behavior as before.
This commit was SVN r16584.
The commit has been tested for C/R and Cray operations, and on Odin (SLURM, rsh) and RoadRunner (TM). I tried to update all environments, but obviously could not test them. I know that Windows needs some work, and have highlighted what is know to be needed in the odls process component.
This represents a lot of work by Brian, Tim P, Josh, and myself, with much advice from Jeff and others. For posterity, I have appended a copy of the email describing the work that was done:
As we have repeatedly noted, the modex operation in MPI_Init is the single greatest consumer of time during startup. To-date, we have executed that operation as an ORTE stage gate that held the process until a startup message containing all required modex (and OOB contact info - see #3 below) info could be sent to it. Each process would send its data to the HNP's registry, which assembled and sent the message when all processes had reported in.
In addition, ORTE had taken responsibility for monitoring process status as it progressed through a series of "stage gates". The process reported its status at each gate, and ORTE would then send a "release" message once all procs had reported in.
The incoming changes revamp these procedures in three ways:
1. eliminating the ORTE stage gate system and cleanly delineating responsibility between the OMPI and ORTE layers for MPI init/finalize. The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info. The allgather is implemented using the orte_grpcomm framework since the BTL's are not active at that point. At the moment, the grpcomm framework only has a "basic" component analogous to OMPI's "basic" coll framework - I would recommend that the MPI team create additional, more advanced components to improve performance of this step.
The other stage gates have been replaced by orte_grpcomm barrier functions. We tried to use MPI barriers instead (since the BTL's are active at that point), but - as we discussed on the telecon - these are not currently true barriers so the job would hang when we fell through while messages were still in process. Note that the grpcomm barrier doesn't actually resolve that problem, but Brian has pointed out that we are unlikely to ever see it violated. Again, you might want to spend a little time on an advanced barrier algorithm as the one in "basic" is very simplistic.
Summarizing this change: ORTE no longer tracks process state nor has direct responsibility for synchronizing jobs. This is now done via collective operations within the MPI layer, albeit using ORTE collective communication services. I -strongly- urge the MPI team to implement advanced collective algorithms to improve the performance of this critical procedure.
2. reducing the volume of data exchanged during modex. Data in the modex consisted of the process name, the name of the node where that process is located (expressed as a string), plus a string representation of all contact info. The nodename was required in order for the modex to determine if the process was local or not - in addition, some people like to have it to print pretty error messages when a connection failed.
The size of this data has been reduced in three ways:
(a) reducing the size of the process name itself. The process name consisted of two 32-bit fields for the jobid and vpid. This is far larger than any current system, or system likely to exist in the near future, can support. Accordingly, the default size of these fields has been reduced to 16-bits, which means you can have 32k procs in each of 32k jobs. Since the daemons must have a vpid, and we require one daemon/node, this also restricts the default configuration to 32k nodes.
To support any future "mega-clusters", a configuration option --enable-jumbo-apps has been added. This option increases the jobid and vpid field sizes to 32-bits. Someday, if necessary, someone can add yet another option to increase them to 64-bits, I suppose.
(b) replacing the string nodename with an integer nodeid. Since we have one daemon/node, the nodeid corresponds to the local daemon's vpid. This replaces an often lengthy string with only 2 (or at most 4) bytes, a substantial reduction.
(c) when the mca param requesting that nodenames be sent to support pretty error messages, a second mca param is now used to request FQDN - otherwise, the domain name is stripped (by default) from the message to save space. If someone wants to combine those into a single param somehow (perhaps with an argument?), they are welcome to do so - I didn't want to alter what people are already using.
While these may seem like small savings, they actually amount to a significant impact when aggregated across the entire modex operation. Since every proc must receive the modex data regardless of the collective used to send it, just reducing the size of the process name removes nearly 400MBytes of communication from a 32k proc job (admittedly, much of this comm may occur in parallel). So it does add up pretty quickly.
3. routing RML messages to reduce connections. The default messaging system remains point-to-point - i.e., each proc opens a socket to every proc it communicates with and sends its messages directly. A new option uses the orteds as routers - i.e., each proc only opens a single socket to its local orted. All messages are sent from the proc to the orted, which forwards the message to the orted on the node where the intended recipient proc is located - that orted then forwards the message to its local proc (the recipient). This greatly reduces the connection storm we have encountered during startup.
It also has the benefit of removing the sharing of every proc's OOB contact with every other proc. The orted routing tables are populated during launch since every orted gets a map of where every proc is being placed. Each proc, therefore, only needs to know the contact info for its local daemon, which is passed in via the environment when the proc is fork/exec'd by the daemon. This alone removes ~50 bytes/process of communication that was in the current STG1 startup message - so for our 32k proc job, this saves us roughly 32k*50 = 1.6MBytes sent to 32k procs = 51GBytes of messaging.
Note that you can use the new routing method by specifying -mca routed tree - if you so desire. This mode will become the default at some point in the future.
There are a few minor additional changes in the commit that I'll just note in passing:
* propagation of command line mca params to the orteds - fixes ticket #1073. See note there for details.
* requiring of "finalize" prior to "exit" for MPI procs - fixes ticket #1144. See note there for details.
* cleanup of some stale header files
This commit was SVN r16364.
* General TCP cleanup for OPAL / ORTE
* Simplifying the OOB by moving much of the logic into the RML
* Allowing the OOB RML component to do routing of messages
* Adding a component framework for handling routing tables
* Moving the xcast functionality from the OOB base to its own framework
Includes merge from tmp/bwb-oob-rml-merge revisions:
r15506, r15507, r15508, r15510, r15511, r15512, r15513
This commit was SVN r15528.
The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
r15506
r15507
r15508
r15510
r15511
r15512
r15513
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.
Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.
Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.
With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.
Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".
This commit was SVN r14711.
* Remove the connect() timeout code, as it had some nasty race conditions
when connections were established as the trigger was firing. A better
solution has been found for the cluster where this was needed, so just
removing it was easiest.
* When a fatal error (too many connection failures) occurs, set an error
on messages in the queue even if there isn't an active message. The
first message to any peer will be queued without being active (and
so will all subsequent messages until the connection is established),
and the orteds will hang until that first message completes. So if
an orted can never contact it's peer, it will never exit and just sit
waiting for that message to complete.
* Cover an interesting RST condition in the connect code. A connection
can complete the three-way handshake, the connector can even send
some data, but the server side will drop the connection because it
can't move it from the half-connected to fully-connected state because
of space shortage in the listen backlog queue. This causes a RST to
be received first time that recv() is called, which will be when waiting
for the remote side of the OOB ack. In this case, transition the
connection back into a CLOSED state and try to connect again.
* Add levels of debugging, rather than all or nothing, each building on
the previous level. 0 (default) is hard errors. 1 is connection
error debugging info. 2 is all connection info. 3 is more state
info. 4 includes all message info.
* Add some hopefully useful comments
This commit was SVN r14261.
This merge adds Checkpoint/Restart support to Open MPI. The initial
frameworks and components support a LAM/MPI-like implementation.
This commit follows the risk assessment presented to the Open MPI core
development group on Feb. 22, 2007.
This commit closes trac:158
More details to follow.
This commit was SVN r14051.
The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
r13912
The following Trac tickets were found above:
Ticket 158 --> https://svn.open-mpi.org/trac/ompi/ticket/158
Accordingly, there are new APIs to the name service to support the ability to get a job's parent, root, immediate children, and all its descendants. In addition, the terminate_job, terminate_orted, and signal_job APIs for the PLS have been modified to accept attributes that define the extent of their actions. For example, doing a "terminate_job" with an attribute of ORTE_NS_INCLUDE_DESCENDANTS will terminate the given jobid AND all jobs that descended from it.
I have tested this capability on a MacBook under rsh, Odin under SLURM, and LANL's Flash (bproc). It worked successfully on non-MPI jobs (both simple and including a spawn), and MPI jobs (again, both simple and with a spawn).
This commit was SVN r12597.
Each 's' partition has its own TCP network. It's fine to use this network for jobs that fit inside the partition, but the TCP OOB errors when trying to connect across two partitions, because there are two disjoint networks. Each node also has another TCP network connecting ALL nodes together.
So the solution is to actually try all the available TCP interfaces on a node, instead of erroring when the first one fails.
Also, the default TCP connect() timeout is way too long (5 minutes) - use our own timeout mechanism, with the timeout value expressed as an MCA parameter.
This commit was SVN r11718.
- use the OPAL functions for PATH and environment variables
- make all headers C++ friendly
- no unamed structures
- no implicit cast.
Plus a full implementation for the orte_wait functions.
This commit was SVN r11347.
different macros, one for each project. Therefore, now we have OPAL_DECLSPEC,
ORTE_DECLSPEC and OMPI_DECLSPEC. Please use them based on the sub-project.
This commit was SVN r11270.
r10841, so revert it (and it's fixes) out. Will bring back once cleaned up from
the code used in the tbird experiment
This commit was SVN r10991.
The following SVN revision numbers were found above:
r10841 --> open-mpi/ompi@dfa1221c3b
than $(LN_S). This causes problems with with Windows and probably
elsewhere (re: #200). So use a slightly different trick to get the
right header selected for the MEMCPY and TIMER components.
* Using the same trick used to solve the AC_CONFIG_LINKS problem,
stop using a separate header file for direct calling in the
PML and MTL. This lets me remove some icky code in ompi_mca.m4
that was more fragile than I really liked.
This commit was SVN r10841.
- moved hton64 and ntoh64 from the bunch of places it had been copied
into one header file
- properly set and use the btl_tcp's nbo option to put things in
network byte order on the wire if both sides don't have the same
endianness
- Put the OB1 PML's headers (with a couple exceptions I need to discuss
with Tim) in network byte order on the wire if both sides don't have
the same endianness
- since it was needed for the TCP BTL, move the orte_process_name_t
HTON and NTOH macros from the TCP OOB to ns_types.h
This commit was SVN r9145.
- move files out of toplevel include/ and etc/, moving it into the
sub-projects
- rather than including config headers with <project>/include,
have them as <project>
- require all headers to be included with a project prefix, with
the exception of the config headers ({opal,orte,ompi}_config.h
mpi.h, and mpif.h)
This commit was SVN r8985.
However we do want to do a bit of cleanup on the node before we exit,
specificly clean out the session directory. I also had a couple of the
subsystems that don't depend upon peers (which is key) clean up as well.
Pedantic formatting issue in oob_tcp.h
This commit was SVN r7387.
