a200e4f865
*** 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.
470 строки
16 KiB
C
470 строки
16 KiB
C
/*
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2011 The University of Tennessee and The University
|
|
* of Tennessee Research Foundation. All rights
|
|
* reserved.
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
* University of Stuttgart. All rights reserved.
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
* All rights reserved.
|
|
* Copyright (c) 2008-2012 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2012-2013 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2013 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif /* HAVE_UNISTD_H */
|
|
#ifdef HAVE_STRING_H
|
|
#include <string.h>
|
|
#endif /* HAVE_STRING_H */
|
|
#include <ctype.h>
|
|
#ifdef HAVE_NETDB_H
|
|
#include <netdb.h>
|
|
#endif
|
|
#ifdef HAVE_IFADDRS_H
|
|
#include <ifaddrs.h>
|
|
#endif
|
|
|
|
#include <pmi.h>
|
|
#if WANT_PMI2_SUPPORT
|
|
#include <pmi2.h>
|
|
#endif
|
|
|
|
#include "opal/util/opal_environ.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/util/argv.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
#include "opal/mca/hwloc/base/base.h"
|
|
#include "opal/util/printf.h"
|
|
#include "opal/mca/common/pmi/common_pmi.h"
|
|
|
|
#include "opal/mca/db/db.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
#include "orte/mca/rml/rml.h"
|
|
#include "orte/util/proc_info.h"
|
|
#include "orte/util/show_help.h"
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/util/nidmap.h"
|
|
#include "orte/util/pre_condition_transports.h"
|
|
#include "orte/util/regex.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
#include "orte/runtime/orte_wait.h"
|
|
|
|
#include "orte/mca/ess/ess.h"
|
|
#include "orte/mca/ess/base/base.h"
|
|
#include "orte/mca/ess/pmi/ess_pmi.h"
|
|
|
|
static int rte_init(void);
|
|
static int rte_finalize(void);
|
|
static void rte_abort(int error_code, bool report);
|
|
|
|
orte_ess_base_module_t orte_ess_pmi_module = {
|
|
rte_init,
|
|
rte_finalize,
|
|
rte_abort,
|
|
NULL /* ft_event */
|
|
};
|
|
|
|
static bool app_init_complete=false;
|
|
|
|
/**** MODULE FUNCTIONS ****/
|
|
|
|
static int rte_init(void)
|
|
{
|
|
int ret, i, j;
|
|
char *error = NULL, *localj;
|
|
int32_t jobfam, stepid;
|
|
char *envar, *ev1, *ev2;
|
|
uint64_t unique_key[2];
|
|
char *cs_env, *string_key;
|
|
char *pmi_id=NULL;
|
|
int *ranks=NULL;
|
|
orte_jobid_t jobid;
|
|
orte_local_rank_t local_rank;
|
|
orte_node_rank_t node_rank;
|
|
char *rmluri;
|
|
opal_hwloc_locality_t locality;
|
|
char *tmp;
|
|
|
|
/* run the prolog */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_std_prolog())) {
|
|
error = "orte_ess_base_std_prolog";
|
|
goto error;
|
|
}
|
|
|
|
#if OPAL_HAVE_HWLOC
|
|
/* get the topology */
|
|
if (NULL == opal_hwloc_topology) {
|
|
if (OPAL_SUCCESS != opal_hwloc_base_get_topology()) {
|
|
error = "topology discovery";
|
|
goto error;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
if (ORTE_PROC_IS_DAEMON) { /* I am a daemon, launched by mpirun */
|
|
/* we had to be given a jobid */
|
|
if (NULL == orte_ess_base_jobid) {
|
|
error = "missing jobid";
|
|
ret = ORTE_ERR_FATAL;
|
|
goto error;
|
|
}
|
|
if (ORTE_SUCCESS != (ret = orte_util_convert_string_to_jobid(&jobid, orte_ess_base_jobid))) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "convert jobid";
|
|
goto error;
|
|
}
|
|
ORTE_PROC_MY_NAME->jobid = jobid;
|
|
/* get our rank from PMI */
|
|
if (!mca_common_pmi_rank(&i)) {
|
|
error = "could not get PMI rank";
|
|
goto error;
|
|
}
|
|
ORTE_PROC_MY_NAME->vpid = i + 1; /* compensate for orterun */
|
|
|
|
/* get the number of procs from PMI */
|
|
if (!mca_common_pmi_size(&i)) {
|
|
error = "could not get PMI universe size";
|
|
goto error;
|
|
}
|
|
orte_process_info.num_procs = i + 1; /* compensate for orterun */
|
|
|
|
/* complete setup */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_setup(NULL))) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_orted_setup";
|
|
goto error;
|
|
}
|
|
} else { /* we are a direct-launched MPI process */
|
|
#if WANT_PMI2_SUPPORT
|
|
/* Get domain id */
|
|
pmi_id = (char*)malloc(PMI2_MAX_VALLEN);
|
|
if (PMI_SUCCESS != (ret = PMI2_Job_GetId(pmi_id, PMI2_MAX_VALLEN))) {
|
|
error = "PMI2_Job_GetId failed";
|
|
goto error;
|
|
}
|
|
#else
|
|
{
|
|
int pmi_maxlen;
|
|
|
|
/* get our PMI id length */
|
|
if (PMI_SUCCESS != (ret = PMI_Get_id_length_max(&pmi_maxlen))) {
|
|
error = "PMI_Get_id_length_max";
|
|
goto error;
|
|
}
|
|
pmi_id = (char*)malloc(pmi_maxlen);
|
|
if (PMI_SUCCESS != (ret = PMI_Get_kvs_domain_id(pmi_id, pmi_maxlen))) {
|
|
free(pmi_id);
|
|
error = "PMI_Get_kvs_domain_id";
|
|
goto error;
|
|
}
|
|
}
|
|
#endif
|
|
/* PMI is very nice to us - the domain id is an integer followed
|
|
* by a '.', followed by essentially a stepid. The first integer
|
|
* defines an overall job number. The second integer is the number of
|
|
* individual jobs we have run within that allocation. So we translate
|
|
* this as the overall job number equating to our job family, and
|
|
* the individual number equating to our local jobid
|
|
*/
|
|
jobfam = strtol(pmi_id, &localj, 10);
|
|
if (NULL == localj) {
|
|
/* hmmm - no '.', so let's just use zero */
|
|
stepid = 0;
|
|
} else {
|
|
localj++; /* step over the '.' */
|
|
stepid = strtol(localj, NULL, 10) + 1; /* add one to avoid looking like a daemon */
|
|
}
|
|
free(pmi_id);
|
|
|
|
/* now build the jobid */
|
|
ORTE_PROC_MY_NAME->jobid = ORTE_CONSTRUCT_LOCAL_JOBID(jobfam << 16, stepid);
|
|
|
|
/* get our rank */
|
|
if (!mca_common_pmi_rank(&i)) {
|
|
error = "could not get PMI rank";
|
|
goto error;
|
|
}
|
|
ORTE_PROC_MY_NAME->vpid = i;
|
|
|
|
/* get the number of procs from PMI */
|
|
if (!mca_common_pmi_size(&i)) {
|
|
error = "could not get PMI universe size";
|
|
goto error;
|
|
}
|
|
orte_process_info.num_procs = i;
|
|
/* push into the environ for pickup in MPI layer for
|
|
* MPI-3 required info key
|
|
*/
|
|
asprintf(&ev1, "OMPI_MCA_orte_ess_num_procs=%d", i);
|
|
putenv(ev1);
|
|
asprintf(&ev2, "OMPI_APP_CTX_NUM_PROCS=%d", i);
|
|
putenv(ev2);
|
|
|
|
/* setup transport keys in case the MPI layer needs them -
|
|
* we can use the jobfam and stepid as unique keys
|
|
* because they are unique values assigned by the RM
|
|
*/
|
|
unique_key[0] = (uint64_t)jobfam;
|
|
unique_key[1] = (uint64_t)stepid;
|
|
if (NULL == (string_key = orte_pre_condition_transports_print(unique_key))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_OUT_OF_RESOURCE);
|
|
return ORTE_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
if (OPAL_SUCCESS != mca_base_var_env_name ("orte_precondition_transports", &cs_env)) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_OUT_OF_RESOURCE);
|
|
return ORTE_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
asprintf(&envar, "%s=%s", cs_env, string_key);
|
|
putenv(envar);
|
|
/* cannot free the envar as that messes up our environ */
|
|
free(cs_env);
|
|
free(string_key);
|
|
|
|
/* our app_context number can only be 0 as we don't support
|
|
* dynamic spawns
|
|
*/
|
|
orte_process_info.app_num = 0;
|
|
|
|
/* setup my daemon's name - arbitrary, since we don't route
|
|
* messages
|
|
*/
|
|
ORTE_PROC_MY_DAEMON->jobid = 0;
|
|
ORTE_PROC_MY_DAEMON->vpid = 0;
|
|
|
|
/* ensure we pick the correct critical components */
|
|
putenv("OMPI_MCA_grpcomm=pmi");
|
|
putenv("OMPI_MCA_db_pmi_store_priority=100");
|
|
putenv("OMPI_MCA_routed=direct");
|
|
|
|
/* now use the default procedure to finish my setup */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_app_setup())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_app_setup";
|
|
goto error;
|
|
}
|
|
|
|
#if WANT_PMI2_SUPPORT
|
|
{
|
|
/* get our local proc info to find our local rank */
|
|
char *pmapping = (char*)malloc(PMI2_MAX_VALLEN);
|
|
int found, sid, nodes, procs, k;
|
|
orte_vpid_t n;
|
|
char *p;
|
|
ret = PMI2_Info_GetJobAttr("PMI_process_mapping", pmapping, PMI2_MAX_VALLEN, &found);
|
|
if (!found || PMI_SUCCESS != ret) { /* can't check PMI2_SUCCESS as some folks (i.e., Cray) don't define it */
|
|
error = "could not get PMI_process_mapping (PMI2_Info_GetJobAttr() failed)";
|
|
goto error;
|
|
}
|
|
|
|
i = 0; n = 0; procs = 0;
|
|
if (NULL != (p = strstr(pmapping, "(vector"))) {
|
|
while (NULL != (p = strstr(p+1, ",("))) {
|
|
if (3 == sscanf(p, ",(%d,%d,%d)", &sid, &nodes, &procs)) {
|
|
for (k = 0; k < nodes; k++) {
|
|
if ((ORTE_PROC_MY_NAME->vpid >= n) &&
|
|
(ORTE_PROC_MY_NAME->vpid < (n + procs))) {
|
|
break;
|
|
}
|
|
n += procs;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
free(pmapping);
|
|
|
|
if ((procs > 0) && (n < orte_process_info.num_procs)) {
|
|
ranks = (int*)malloc(procs * sizeof(int));
|
|
for (i=0; i < procs; i++) {
|
|
ranks[i] = n + i;
|
|
}
|
|
}
|
|
|
|
if (NULL == ranks) {
|
|
error = "could not get PMI_process_mapping";
|
|
goto error;
|
|
}
|
|
}
|
|
#else
|
|
/* get our local proc info to find our local rank */
|
|
if (PMI_SUCCESS != (ret = PMI_Get_clique_size(&i))) {
|
|
OPAL_PMI_ERROR(ret, "PMI_Get_clique_size");
|
|
error = "could not get PMI clique size";
|
|
goto error;
|
|
}
|
|
/* now get the specific ranks */
|
|
ranks = (int*)malloc(i * sizeof(int));
|
|
if (PMI_SUCCESS != (ret = PMI_Get_clique_ranks(ranks, i))) {
|
|
OPAL_PMI_ERROR(ret, "PMI_Get_clique_ranks");
|
|
error = "could not get clique ranks";
|
|
goto error;
|
|
}
|
|
#endif
|
|
/* store the number of local peers - remember, we want the number
|
|
* of peers that share the node WITH ME, so we have to subtract
|
|
* ourselves from that number
|
|
*/
|
|
orte_process_info.num_local_peers = i - 1;
|
|
/* The clique ranks are returned in rank order, so
|
|
* cycle thru the array and update the local/node
|
|
* rank info
|
|
*/
|
|
for (j=0; j < i; j++) {
|
|
local_rank = j;
|
|
node_rank = j;
|
|
if (ranks[j] == (int)ORTE_PROC_MY_NAME->vpid) {
|
|
orte_process_info.my_local_rank = local_rank;
|
|
orte_process_info.my_node_rank = node_rank;
|
|
}
|
|
}
|
|
free(ranks);
|
|
|
|
/* setup process binding */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_proc_binding())) {
|
|
error = "proc_binding";
|
|
goto error;
|
|
}
|
|
|
|
/* this needs to be set to enable debugger use when direct launched */
|
|
orte_standalone_operation = true;
|
|
}
|
|
|
|
/* set max procs */
|
|
if (orte_process_info.max_procs < orte_process_info.num_procs) {
|
|
orte_process_info.max_procs = orte_process_info.num_procs;
|
|
}
|
|
|
|
/* set the number of nodes - have to test as it could be
|
|
* one of multiple environments
|
|
*/
|
|
if (NULL != (tmp = getenv("SLURM_NNODES"))) {
|
|
orte_process_info.num_daemons = strtol(tmp, NULL, 10);
|
|
} else if (NULL != (tmp = getenv("PBS_NUM_NODES"))) {
|
|
orte_process_info.num_daemons = strtol(tmp, NULL, 10);
|
|
} else {
|
|
if (0 == ORTE_PROC_MY_NAME->vpid) {
|
|
orte_show_help("help-orte-runtime.txt",
|
|
"orte_init:startup:num_daemons", true);
|
|
}
|
|
orte_process_info.num_daemons = UINT_MAX;
|
|
}
|
|
|
|
/* construct the PMI RTE string */
|
|
rmluri = orte_rml.get_contact_info();
|
|
|
|
/* store our info in the internal database */
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_GLOBAL, ORTE_DB_RMLURI,
|
|
rmluri, OPAL_STRING))) {
|
|
error = "db store uri";
|
|
goto error;
|
|
}
|
|
free(rmluri);
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_GLOBAL, ORTE_DB_HOSTNAME,
|
|
orte_process_info.nodename, OPAL_STRING))) {
|
|
error = "db store hostname";
|
|
goto error;
|
|
}
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_GLOBAL, ORTE_DB_CPUSET,
|
|
orte_process_info.cpuset, OPAL_STRING))) {
|
|
error = "db store cpuset";
|
|
goto error;
|
|
}
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_GLOBAL, ORTE_DB_LOCALRANK,
|
|
&orte_process_info.my_local_rank, ORTE_LOCAL_RANK))) {
|
|
error = "db store local rank";
|
|
goto error;
|
|
}
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_GLOBAL, ORTE_DB_NODERANK,
|
|
&orte_process_info.my_node_rank, ORTE_NODE_RANK))) {
|
|
error = "db store node rank";
|
|
goto error;
|
|
}
|
|
|
|
/* save local locality */
|
|
locality = OPAL_PROC_ALL_LOCAL;
|
|
if (ORTE_SUCCESS != (ret = opal_db.store((opal_identifier_t*)ORTE_PROC_MY_NAME,
|
|
OPAL_DB_INTERNAL, ORTE_DB_LOCALITY,
|
|
&locality, OPAL_HWLOC_LOCALITY_T))) {
|
|
error = "db store locality";
|
|
goto error;
|
|
}
|
|
|
|
/* flag that we completed init */
|
|
app_init_complete = true;
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
error:
|
|
if (ORTE_ERR_SILENT != ret && !orte_report_silent_errors) {
|
|
orte_show_help("help-orte-runtime.txt",
|
|
"orte_init:startup:internal-failure",
|
|
true, error, ORTE_ERROR_NAME(ret), ret);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int rte_finalize(void)
|
|
{
|
|
int ret;
|
|
|
|
if (app_init_complete) {
|
|
/* if I am a daemon, finalize using the default procedure */
|
|
if (ORTE_PROC_IS_DAEMON) {
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_finalize())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
return ret;
|
|
}
|
|
} else {
|
|
/* remove the envars that we pushed into environ
|
|
* so we leave that structure intact
|
|
*/
|
|
unsetenv("OMPI_MCA_grpcomm");
|
|
unsetenv("OMPI_MCA_routed");
|
|
unsetenv("OMPI_MCA_orte_precondition_transports");
|
|
/* use the default app procedure to finish */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_app_finalize())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
return ret;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* deconstruct my nidmap and jobmap arrays - this
|
|
* function protects itself from being called
|
|
* before things were initialized
|
|
*/
|
|
orte_util_nidmap_finalize();
|
|
|
|
#if OPAL_HAVE_HWLOC
|
|
if (NULL != opal_hwloc_topology) {
|
|
opal_hwloc_base_free_topology(opal_hwloc_topology);
|
|
opal_hwloc_topology = NULL;
|
|
}
|
|
#endif
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static void rte_abort(int error_code, bool report)
|
|
{
|
|
orte_ess_base_app_abort(error_code, report);
|
|
}
|