ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
openmpi/orte/mca/ras/ccp/ras_ccp_module.c

343 строки
11 KiB
C
Исходник Обычный вид История

Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
/*
* Copyright (c) 2004-2007 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2008 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "orte_config.h"
#include "orte/constants.h"
#include "orte/types.h"
#include <windows.h>
#include <stdio.h>
#include <stdlib.h>
#include <comutil.h>
#include <errno.h>
#include <string.h>
#include "opal/util/argv.h"
Correct the output global variables. This commit was SVN r20745.
2009-03-06 15:31:12 +00:00
#include "opal/util/output.h"
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
#include "orte/util/show_help.h"
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
#include "opal/util/os_path.h"
#include "orte/runtime/orte_globals.h"
#include "orte/util/name_fns.h"
#include "orte/mca/ras/base/ras_private.h"
#include "ras_ccp.h"
/* Import the Windows CCP API. */
#import "ccpapi.tlb" named_guids no_namespace raw_interfaces_only \
rename("SetEnvironmentVariable","SetEnvVar") \
rename("GetJob", "GetSingleJob") \
rename("AddJob", "AddSingleJob")
- 2/4 commit for Windows Visual Studio and CCP support: changes to the already existing ccp components event/win32.c: merge old FD handling into new opal_installdirs_windows.c:fix the registry handling This commit was SVN r20109.
2008-12-10 21:01:54 +00:00
/* Include the library for ::ConvertBSTRToString */
#pragma comment(lib, "comsuppw.lib")
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
/*
* Local functions
*/
static int orte_ras_ccp_allocate(opal_list_t *nodes);
static int orte_ras_ccp_finalize(void);
static int discover(opal_list_t* nodelist, ICluster* pCluster);
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
void ras_get_cluster_message(ICluster* pCluster);
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
/*
* Local variables
*/
orte_ras_base_module_t orte_ras_ccp_module = {
orte_ras_ccp_allocate,
orte_ras_ccp_finalize
};
/**
* Discover available (pre-allocated) nodes. Allocate the
* requested number of nodes/process slots to the job.
*/
static int orte_ras_ccp_allocate(opal_list_t *nodes)
{
int ret, i;
size_t len;
char *cluster_head = NULL;
HRESULT hr = S_OK;
ICluster* pCluster = NULL;
/* CCP is not thread safe. Use the apartment model. */
CoInitializeEx(NULL, COINIT_APARTMENTTHREADED);
/* Create the Cluster object. */
hr = CoCreateInstance( __uuidof(Cluster),
NULL,
CLSCTX_INPROC_SERVER,
__uuidof(ICluster),
reinterpret_cast<void **> (&pCluster) );
if (FAILED(hr)) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate: failed to create cluster object!"));
return ORTE_ERROR;
}
/* Get the cluster head nodes name */
_dupenv_s(&cluster_head, &len, "LOGONSERVER");
if(cluster_head == NULL) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate: connot find cluster head node!"));
return ORTE_ERROR;
}
/* Get rid of the beginning '//'. */
for( i = 0; i < sizeof(cluster_head) * 2 - 2; i++){
cluster_head[i] = cluster_head[i+2];
cluster_head[i+2] = '\0';
}
/* Connect to the cluster's head node */
hr = pCluster->Connect(_bstr_t(cluster_head));
if (FAILED(hr)) {
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
ras_get_cluster_message(pCluster);
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate: connection failed!"));
return ORTE_ERROR;
}
if (ORTE_SUCCESS != (ret = discover(nodes, pCluster))) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate: discover failed!"));
return ret;
}
/* in the CCP world, if we didn't find anything, then this
* is an unrecoverable error - report it
*/
if (opal_list_is_empty(nodes)) {
This commit represents a bunch of work on a Mercurial side branch. As such, the commit message back to the master SVN repository is fairly long. = ORTE Job-Level Output Messages = Add two new interfaces that should be used for all new code throughout the ORTE and OMPI layers (we already make the search-and-replace on the existing ORTE / OMPI layers): * orte_output(): (and corresponding friends ORTE_OUTPUT, orte_output_verbose, etc.) This function sends the output directly to the HNP for processing as part of a job-specific output channel. It supports all the same outputs as opal_output() (syslog, file, stdout, stderr), but for stdout/stderr, the output is sent to the HNP for processing and output. More on this below. * orte_show_help(): This function is a drop-in-replacement for opal_show_help(), with two differences in functionality: 1. the rendered text help message output is sent to the HNP for display (rather than outputting directly into the process' stderr stream) 1. the HNP detects duplicate help messages and does not display them (so that you don't see the same error message N times, once from each of your N MPI processes); instead, it counts "new" instances of the help message and displays a message every ~5 seconds when there are new ones ("I got X new copies of the help message...") opal_show_help and opal_output still exist, but they only output in the current process. The intent for the new orte_* functions is that they can apply job-level intelligence to the output. As such, we recommend that all new ORTE and OMPI code use the new orte_* functions, not thei opal_* functions. === New code === For ORTE and OMPI programmers, here's what you need to do differently in new code: * Do not include opal/util/show_help.h or opal/util/output.h. Instead, include orte/util/output.h (this one header file has declarations for both the orte_output() series of functions and orte_show_help()). * Effectively s/opal_output/orte_output/gi throughout your code. Note that orte_output_open() takes a slightly different argument list (as a way to pass data to the filtering stream -- see below), so you if explicitly call opal_output_open(), you'll need to slightly adapt to the new signature of orte_output_open(). * Literally s/opal_show_help/orte_show_help/. The function signature is identical. === Notes === * orte_output'ing to stream 0 will do similar to what opal_output'ing did, so leaving a hard-coded "0" as the first argument is safe. * For systems that do not use ORTE's RML or the HNP, the effect of orte_output_* and orte_show_help will be identical to their opal counterparts (the additional information passed to orte_output_open() will be lost!). Indeed, the orte_* functions simply become trivial wrappers to their opal_* counterparts. Note that we have not tested this; the code is simple but it is quite possible that we mucked something up. = Filter Framework = Messages sent view the new orte_* functions described above and messages output via the IOF on the HNP will now optionally be passed through a new "filter" framework before being output to stdout/stderr. The "filter" OPAL MCA framework is intended to allow preprocessing to messages before they are sent to their final destinations. The first component that was written in the filter framework was to create an XML stream, segregating all the messages into different XML tags, etc. This will allow 3rd party tools to read the stdout/stderr from the HNP and be able to know exactly what each text message is (e.g., a help message, another OMPI infrastructure message, stdout from the user process, stderr from the user process, etc.). Filtering is not active by default. Filter components must be specifically requested, such as: {{{ $ mpirun --mca filter xml ... }}} There can only be one filter component active. = New MCA Parameters = The new functionality described above introduces two new MCA parameters: * '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that help messages will be aggregated, as described above. If set to 0, all help messages will be displayed, even if they are duplicates (i.e., the original behavior). * '''orte_base_show_output_recursions''': An MCA parameter to help debug one of the known issues, described below. It is likely that this MCA parameter will disappear before v1.3 final. = Known Issues = * The XML filter component is not complete. The current output from this component is preliminary and not real XML. A bit more work needs to be done to configure.m4 search for an appropriate XML library/link it in/use it at run time. * There are possible recursion loops in the orte_output() and orte_show_help() functions -- e.g., if RML send calls orte_output() or orte_show_help(). We have some ideas how to fix these, but figured that it was ok to commit before feature freeze with known issues. The code currently contains sub-optimal workarounds so that this will not be a problem, but it would be good to actually solve the problem rather than have hackish workarounds before v1.3 final. This commit was SVN r18434.
2008-05-13 20:00:55 +00:00
orte_show_help("help-ras-ccp.txt", "no-nodes-found", true);
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
return ORTE_ERR_NOT_FOUND;
}
/* All finished, release cluster object*/
pCluster->Release();
CoUninitialize();
return ret;
}
/*
* There's really nothing to do here
*/
static int orte_ras_ccp_finalize(void)
{
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:finalize: success (nothing to do)"));
return ORTE_SUCCESS;
}
/**
* Discover the available resources. Obtain directly from head node
*
* - validate any Windows Cluster nodes
* - check for additional nodes that have already been allocated
*/
static int discover(opal_list_t* nodelist, ICluster* pCluster)
{
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
int ret = ORTE_ERROR;
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
int32_t nodeid;
orte_node_t *node;
opal_list_item_t* item;
opal_list_t new_nodes;
struct timeval start, stop;
HRESULT hr = S_OK;
long idle_processors = 0;
IClusterEnumerable* pNodesCollection = NULL;
IEnumVARIANT* pNodes = NULL;
INode* pNode = NULL;
BSTR node_name = NULL, node_arch = NULL;
VARIANT var;
NodeStatus Status;
size_t len;
/* check for timing request - get start time if so */
if (orte_timing) {
gettimeofday(&start, NULL);
}
/* Get the collection of nodes. */
hr = pCluster->get_ComputeNodes(&pNodesCollection);
if (FAILED(hr)) {
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
ras_get_cluster_message(pCluster);
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pCluster->get_ComputeNodes failed."));
return ORTE_ERROR;
}
/* Get the enumerator used to iterate through the collection. */
hr = pNodesCollection->GetEnumerator(&pNodes);
if (FAILED(hr)) {
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
ras_get_cluster_message(pCluster);
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pNodesCollection->GetEnumerator failed."));
return ORTE_ERROR;
}
VariantInit(&var);
/* Construct new node list. */
OBJ_CONSTRUCT(&new_nodes, opal_list_t);
nodeid=0;
/* Loop through the collection. */
while (hr = pNodes->Next(1, &var, NULL) == S_OK) {
var.pdispVal->QueryInterface(IID_INode, reinterpret_cast<void **> (&pNode));
/* Check wether the node is ready.
* There are four states:
* NodeStatus_Ready = 0,
* NodeStatus_Paused = 1,
* NodeStatus_Unreachable = 2, probably not a windows cluster node.
* NodeStatus_PendingApproval = 3
*/
hr = pNode->get_Status(&Status);
if (FAILED(hr)) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pNode->get_Status failed."));
ret = ORTE_ERROR;
goto cleanup;
}
/* Get available number of processors on each node. */
hr = pNode->get_NumberOfIdleProcessors(&idle_processors);
if (FAILED(hr)) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pNode->get_NumberOfIdleProcessors failed."));
ret = ORTE_ERROR;
goto cleanup;
}
/* Do we have enough processors on the available nodes?
* Question: How do we get the required number of processors?
*/
if ( (Status != NodeStatus_Unreachable) && (idle_processors > 0) ) {
/* Get node name. */
hr = pNode->get_Name(&node_name);
if (FAILED(hr)) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pNode->get_Name failed."));
ret = ORTE_ERROR;
goto cleanup;
}
/* Get node processor architecture. */
hr = pNode->get_ProcessorArchitecture(&node_arch);
if (FAILED(hr)) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:pNode->get_ProcessorArchitecture failed."));
ret = ORTE_ERROR;
goto cleanup;
}
/* Prevent duplicated nodes in the list*/
for (item = opal_list_get_first(&new_nodes);
opal_list_get_end(&new_nodes) != item;
item = opal_list_get_next(item)) {
node = (orte_node_t*) item;
if (0 == strcmp(node->name, (char *)node_name)) {
++node->slots;
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate:discover: found -- bumped slots to %d",
node->slots));
break;
}
}
/* Did we find it? */
if (opal_list_get_end(&new_nodes) == item) {
/* Nope -- didn't find it, so add a new item to the list */
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate:discover: not found -- added to list"));
node = OBJ_NEW(orte_node_t);
/* The function _dupenv_s is much safer than getenv on Windows. */
_dupenv_s(&node->username, &len, "username");
node->name = _com_util::ConvertBSTRToString(node_name);
node->launch_id = nodeid;
node->slots_inuse = 0;
node->slots_max = 0;
node->slots = 1;
opal_list_append(nodelist, &node->super);
}
/* up the nodeid */
nodeid++;
}
pNode->Release();
VariantClear(&var);
}
pNodes->Release();
if (nodeid > 0) ret = ORTE_SUCCESS;
/* All done */
cleanup:
if (ORTE_SUCCESS == ret) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate:discover: success"));
} else {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
"ras:ccp:allocate:discover: failed (rc=%d)", ret));
}
OBJ_DESTRUCT(&new_nodes);
SysFreeString(node_name);
SysFreeString(node_arch);
/* check for timing request - get stop time and report elapsed time if so */
if (orte_timing) {
gettimeofday(&stop, NULL);
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 14:53:58 +00:00
opal_output(0, "ras_ccp: time to allocate is %ld usec",
Update the RAS and PLM components for Windows. These won't suffer another platforms but only windows. This commit was SVN r17686.
2008-03-04 17:13:01 +00:00
(long int)((stop.tv_sec - start.tv_sec)*1000000 +
(stop.tv_usec - start.tv_usec)));
gettimeofday(&start, NULL);
}
return ret;
}
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
void ras_get_cluster_message(ICluster* pCluster)
{
HRESULT hr = S_OK;
BSTR message = NULL;
hr = pCluster->get_ErrorMessage(&message);
if (SUCCEEDED(hr)) {
Correct the output global variables. This commit was SVN r20745.
2009-03-06 15:31:12 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
_com_util::ConvertBSTRToString(message)));
SysFreeString(message);
}
else {
Correct the output global variables. This commit was SVN r20745.
2009-03-06 15:31:12 +00:00
OPAL_OUTPUT_VERBOSE((1, orte_ras_base.ras_output,
Update the ccp module: rename the get_cluster_message function for both ras/plm. use _umask instead of umask. add WIN32_DCOM definition to support Windows Vista. This commit was SVN r19470.
2008-09-01 16:35:38 +00:00
"pCluster->get_ErrorMessage failed.\n"));
}
}
Копировать постоянную ссылку