2004-07-01 18:49:54 +04:00
|
|
|
/*
|
2007-03-17 02:11:45 +03:00
|
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
2005-11-05 22:57:48 +03:00
|
|
|
* University Research and Technology
|
|
|
|
* Corporation. All rights reserved.
|
2006-08-23 07:32:36 +04:00
|
|
|
* Copyright (c) 2004-2006 The University of Tennessee and The University
|
2005-11-05 22:57:48 +03:00
|
|
|
* of Tennessee Research Foundation. All rights
|
|
|
|
* reserved.
|
2004-11-28 23:09:25 +03:00
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
|
|
* University of Stuttgart. All rights reserved.
|
2005-03-24 15:43:37 +03:00
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
2004-11-22 04:38:40 +03:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
2004-01-10 08:13:00 +03:00
|
|
|
* $HEADER$
|
|
|
|
*/
|
2004-07-01 18:49:54 +04:00
|
|
|
/** @file:
|
2004-01-10 11:09:54 +03:00
|
|
|
*
|
2004-08-05 03:42:51 +04:00
|
|
|
* Contains the internal functions and typedefs for the use of the oob
|
2004-07-01 18:49:54 +04:00
|
|
|
*/
|
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
#ifndef MCA_OOB_H_
|
|
|
|
#define MCA_OOB_H_
|
2004-01-10 08:13:00 +03:00
|
|
|
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "orte_config.h"
|
2004-01-10 11:09:54 +03:00
|
|
|
|
2005-12-01 21:28:20 +03:00
|
|
|
#ifdef HAVE_UNISTD_H
|
|
|
|
#include <unistd.h>
|
|
|
|
#endif
|
|
|
|
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "opal/types.h"
|
|
|
|
#include "opal/mca/mca.h"
|
2005-03-14 23:57:21 +03:00
|
|
|
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "orte/mca/ns/ns_types.h"
|
2005-03-14 23:57:21 +03:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
#include "orte/mca/rml/rml.h"
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "orte/mca/oob/oob_types.h"
|
2004-08-11 01:02:36 +04:00
|
|
|
|
2007-03-17 02:11:45 +03:00
|
|
|
#include "opal/mca/crs/crs.h"
|
|
|
|
#include "opal/mca/crs/base/base.h"
|
|
|
|
|
2004-08-11 01:02:36 +04:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
BEGIN_C_DECLS
|
|
|
|
|
|
|
|
|
|
|
|
struct mca_oob_1_0_0_t;
|
2004-08-11 01:02:36 +04:00
|
|
|
typedef struct mca_oob_1_0_0_t mca_oob_1_0_0_t;
|
|
|
|
typedef struct mca_oob_1_0_0_t mca_oob_t;
|
|
|
|
|
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
typedef mca_oob_t* (*mca_oob_base_component_init_fn_t)(int *priority);
|
|
|
|
|
|
|
|
struct mca_oob_base_component_1_0_0_t {
|
|
|
|
mca_base_component_t oob_base;
|
|
|
|
mca_base_component_data_1_0_0_t oob_data;
|
|
|
|
mca_oob_base_component_init_fn_t oob_init;
|
|
|
|
};
|
|
|
|
typedef struct mca_oob_base_component_1_0_0_t mca_oob_base_component_1_0_0_t;
|
|
|
|
typedef mca_oob_base_component_1_0_0_t mca_oob_base_component_t;
|
2004-07-01 18:49:54 +04:00
|
|
|
|
2004-01-10 08:13:00 +03:00
|
|
|
|
2004-08-16 23:39:54 +04:00
|
|
|
|
|
|
|
typedef char* (*mca_oob_base_module_get_addr_fn_t)(void);
|
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
typedef int (*mca_oob_base_module_set_addr_fn_t)(const orte_process_name_t* peer,
|
|
|
|
const char* uri);
|
2004-08-16 23:39:54 +04:00
|
|
|
|
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
typedef int (*mca_oob_base_module_get_new_name_fn_t)(orte_process_name_t*);
|
2004-09-08 21:02:24 +04:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Implementation of mca_oob_ping().
|
|
|
|
*
|
|
|
|
* @param peer (IN) Opaque name of peer process.
|
|
|
|
* @param tv (IN) Timeout to wait in connection response.
|
2006-02-12 04:33:29 +03:00
|
|
|
* @return OMPI error code (<0) or ORTE_SUCCESS
|
2004-09-08 21:02:24 +04:00
|
|
|
*/
|
2007-07-20 05:34:02 +04:00
|
|
|
typedef int (*mca_oob_base_module_ping_fn_t)(const orte_process_name_t*,
|
|
|
|
const char* uri,
|
|
|
|
const struct timeval* tv);
|
2004-09-08 21:02:24 +04:00
|
|
|
|
2004-07-01 18:49:54 +04:00
|
|
|
|
|
|
|
/**
|
These changes were mostly captured in a prior RFC (except for #2 below) and are aimed specifically at improving startup performance and setting up the remaining modifications described in that RFC.
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.
2007-10-05 23:48:23 +04:00
|
|
|
* Send an oob message
|
|
|
|
*
|
|
|
|
* Send an oob message. All oob sends are non-blocking, and cbfunc
|
|
|
|
* will be called when the message has been sent. When cbfunc is
|
|
|
|
* called, message has been injected into the network but no guarantee
|
|
|
|
* is made about whether the target has received the message.
|
|
|
|
*
|
|
|
|
* @param[in] target Destination process name
|
|
|
|
* @param[in] origin Origin process for the message, for the purposes
|
|
|
|
* of message matching. This can be different from
|
|
|
|
* the process calling send().
|
|
|
|
* @param[in] msg Array of iovecs describing user buffers and lengths.
|
|
|
|
* @param[in] count Number of elements in iovec array.
|
|
|
|
* @param[in] tag User defined tag for matching send/recv.
|
|
|
|
* @param[in] flags Currently unused.
|
|
|
|
* @param[in] cbfunc Callback function on send completion.
|
|
|
|
* @param[in] cbdata User data that is passed to callback function.
|
|
|
|
*
|
|
|
|
* @return OMPI error code (<0) on error number of bytes actually sent.
|
|
|
|
*/
|
2004-08-02 04:24:22 +04:00
|
|
|
typedef int (*mca_oob_base_module_send_nb_fn_t)(
|
These changes were mostly captured in a prior RFC (except for #2 below) and are aimed specifically at improving startup performance and setting up the remaining modifications described in that RFC.
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.
2007-10-05 23:48:23 +04:00
|
|
|
orte_process_name_t* target,
|
|
|
|
orte_process_name_t* origin,
|
2004-08-13 02:41:42 +04:00
|
|
|
struct iovec* msg,
|
2004-08-05 03:42:51 +04:00
|
|
|
int count,
|
2004-08-03 01:24:00 +04:00
|
|
|
int tag,
|
2004-08-05 03:42:51 +04:00
|
|
|
int flags,
|
2007-07-20 05:34:02 +04:00
|
|
|
orte_rml_callback_fn_t cbfunc,
|
2004-07-01 18:49:54 +04:00
|
|
|
void* cbdata);
|
2004-01-10 11:09:54 +03:00
|
|
|
|
2004-07-01 18:49:54 +04:00
|
|
|
/**
|
|
|
|
* Implementation of mca_oob_recv_nb().
|
|
|
|
*
|
Bring over the update to terminate orteds that are generated by a dynamic spawn such as comm_spawn. This introduces the concept of a job "family" - i.e., jobs that have a parent/child relationship. Comm_spawn'ed jobs have a parent (the one that spawned them). We track that relationship throughout the lineage - i.e., if a comm_spawned job in turn calls comm_spawn, then it has a parent (the one that spawned it) and a "root" job (the original job that started things).
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.
2006-11-14 22:34:59 +03:00
|
|
|
* @param peer (IN) Opaque name of peer process or ORTE_NAME_WILDCARD for wildcard receive.
|
2004-07-01 18:49:54 +04:00
|
|
|
* @param msg (IN) Array of iovecs describing user buffers and lengths.
|
|
|
|
* @param count (IN) Number of elements in iovec array.
|
2004-08-03 01:24:00 +04:00
|
|
|
* @param tag (IN) User defined tag for matching send/recv.
|
2004-07-15 23:08:54 +04:00
|
|
|
* @param flags (IN) May be MCA_OOB_PEEK to return up to size bytes of msg w/out removing it from the queue,
|
2004-07-01 18:49:54 +04:00
|
|
|
* @param cbfunc (IN) Callback function on recv completion.
|
|
|
|
* @param cbdata (IN) User data that is passed to callback function.
|
|
|
|
* @return OMPI error code (<0) on error or number of bytes actually received.
|
|
|
|
*/
|
|
|
|
|
2004-08-02 04:24:22 +04:00
|
|
|
typedef int (*mca_oob_base_module_recv_nb_fn_t)(
|
2005-03-14 23:57:21 +03:00
|
|
|
orte_process_name_t* peer,
|
2004-08-13 02:41:42 +04:00
|
|
|
struct iovec* msg,
|
2004-08-05 03:42:51 +04:00
|
|
|
int count,
|
2004-08-03 01:24:00 +04:00
|
|
|
int tag,
|
2004-08-05 03:42:51 +04:00
|
|
|
int flags,
|
2007-07-20 05:34:02 +04:00
|
|
|
orte_rml_callback_fn_t cbfunc,
|
2004-07-01 18:49:54 +04:00
|
|
|
void* cbdata);
|
|
|
|
|
2004-09-30 19:09:29 +04:00
|
|
|
/**
|
|
|
|
* Implementation of mca_oob_recv_cancel().
|
|
|
|
*
|
Bring over the update to terminate orteds that are generated by a dynamic spawn such as comm_spawn. This introduces the concept of a job "family" - i.e., jobs that have a parent/child relationship. Comm_spawn'ed jobs have a parent (the one that spawned them). We track that relationship throughout the lineage - i.e., if a comm_spawned job in turn calls comm_spawn, then it has a parent (the one that spawned it) and a "root" job (the original job that started things).
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.
2006-11-14 22:34:59 +03:00
|
|
|
* @param peer (IN) Opaque name of peer process or ORTE_NAME_WILDCARD for wildcard receive.
|
2004-09-30 19:09:29 +04:00
|
|
|
* @param tag (IN) User defined tag for matching send/recv.
|
|
|
|
* @return OMPI error code (<0) on error or number of bytes actually received.
|
|
|
|
*/
|
|
|
|
|
2005-03-14 23:57:21 +03:00
|
|
|
typedef int (*mca_oob_base_module_recv_cancel_fn_t)(orte_process_name_t* peer, int tag);
|
2004-09-30 19:09:29 +04:00
|
|
|
|
2004-08-11 01:02:36 +04:00
|
|
|
/**
|
2004-08-19 23:34:37 +04:00
|
|
|
* Hook function called by mca_oob_base_register to allow
|
|
|
|
* the oob component a chance to register contact information
|
2004-08-11 01:02:36 +04:00
|
|
|
*/
|
2004-08-19 23:34:37 +04:00
|
|
|
typedef int (*mca_oob_base_module_init_fn_t)(void);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Cleanup during finalize.
|
|
|
|
*/
|
|
|
|
typedef int (*mca_oob_base_module_fini_fn_t)(void);
|
2004-08-11 01:02:36 +04:00
|
|
|
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
/* ft event */
|
2007-03-17 02:11:45 +03:00
|
|
|
typedef int (*mca_oob_base_module_ft_event_fn_t)( int state );
|
|
|
|
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
|
2004-08-10 03:07:53 +04:00
|
|
|
/**
|
2004-07-01 18:49:54 +04:00
|
|
|
* OOB Module
|
|
|
|
*/
|
2004-08-03 01:24:00 +04:00
|
|
|
struct mca_oob_1_0_0_t {
|
2007-07-20 05:34:02 +04:00
|
|
|
mca_oob_base_module_init_fn_t oob_init;
|
|
|
|
mca_oob_base_module_fini_fn_t oob_fini;
|
|
|
|
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
mca_oob_base_module_get_addr_fn_t oob_get_addr;
|
|
|
|
mca_oob_base_module_set_addr_fn_t oob_set_addr;
|
2007-07-20 05:34:02 +04:00
|
|
|
|
|
|
|
mca_oob_base_module_get_new_name_fn_t oob_get_new_name;
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
mca_oob_base_module_ping_fn_t oob_ping;
|
2007-07-20 05:34:02 +04:00
|
|
|
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
mca_oob_base_module_send_nb_fn_t oob_send_nb;
|
2007-07-20 05:34:02 +04:00
|
|
|
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
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.
2007-05-21 22:31:28 +04:00
|
|
|
mca_oob_base_module_recv_nb_fn_t oob_recv_nb;
|
|
|
|
mca_oob_base_module_recv_cancel_fn_t oob_recv_cancel;
|
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
mca_oob_base_module_ft_event_fn_t oob_ft_event;
|
2004-08-02 04:24:22 +04:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
orte_rml_exception_callback_t oob_exception_callback;
|
2004-07-01 18:49:54 +04:00
|
|
|
};
|
2004-08-11 01:02:36 +04:00
|
|
|
|
2004-08-10 03:07:53 +04:00
|
|
|
/**
|
2004-07-01 18:49:54 +04:00
|
|
|
* Macro for use in components that are of type oob v1.0.0
|
2004-01-12 01:52:59 +03:00
|
|
|
*/
|
|
|
|
#define MCA_OOB_BASE_VERSION_1_0_0 \
|
2004-08-05 03:42:51 +04:00
|
|
|
/* oob v1.0 is chained to MCA v1.0 */ \
|
2004-01-12 01:52:59 +03:00
|
|
|
MCA_BASE_VERSION_1_0_0, \
|
2004-08-05 03:42:51 +04:00
|
|
|
/* oob v1.0 */ \
|
2004-01-12 01:52:59 +03:00
|
|
|
"oob", 1, 0, 0
|
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
/*
|
2007-07-20 05:34:02 +04:00
|
|
|
* BWB - FIX ME - This is the first module on the list. This is here
|
|
|
|
* temporarily to make things work
|
2004-08-05 03:42:51 +04:00
|
|
|
*/
|
2004-10-22 20:06:05 +04:00
|
|
|
|
2006-08-20 19:54:04 +04:00
|
|
|
ORTE_DECLSPEC extern mca_oob_t mca_oob;
|
2004-08-05 03:42:51 +04:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
END_C_DECLS
|
2005-10-06 23:39:20 +04:00
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
#endif
|