Merge pull request #5081 from ggouaillardet/topic/v3.1.x/pmix_legacy_get

bwbarrett · web-flow · commit d9506519a170 · 2018-04-26T11:29:11.000-07:00
Fix support for external PMIx v2.0 with legacy PMIx_Get()
diff --git a/opal/mca/pmix/ext1x/pmix1x.c b/opal/mca/pmix/ext1x/pmix1x.c
@@ -1,6 +1,6 @@
 /* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
 /*
- * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2014-2017 Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2014-2015 Mellanox Technologies, Inc.
@@ -48,8 +48,13 @@
 
 static const char *pmix1_get_nspace(opal_jobid_t jobid);
 static void pmix1_register_jobid(opal_jobid_t jobid, const char *nspace);
+static bool legacy_get(void)
+{
+    return true;
+}
 
 const opal_pmix_base_module_t opal_pmix_ext1x_module = {
+    .legacy_get = legacy_get,
     /* client APIs */
     .init = pmix1_client_init,
     .finalize = pmix1_client_finalize,
diff --git a/opal/mca/pmix/ext1x/pmix1x_client.c b/opal/mca/pmix/ext1x/pmix1x_client.c
@@ -232,8 +232,10 @@ int pmix1_store_local(const opal_process_name_t *proc, opal_value_t *val)
             }
         }
         if (NULL == job) {
-            OPAL_ERROR_LOG(OPAL_ERR_NOT_FOUND);
-            return OPAL_ERR_NOT_FOUND;
+            job = OBJ_NEW(opal_pmix1_jobid_trkr_t);
+            (void)opal_snprintf_jobid(job->nspace, PMIX_MAX_NSLEN, proc->jobid);
+            job->jobid = proc->jobid;
+            opal_list_append(&mca_pmix_ext1x_component.jobids, &job->super);
         }
         (void)strncpy(p.nspace, job->nspace, PMIX_MAX_NSLEN);
         p.rank = proc->vpid;
diff --git a/opal/mca/pmix/pmix.h b/opal/mca/pmix/pmix.h
@@ -867,10 +867,13 @@ typedef int (*opal_pmix_base_process_monitor_fn_t)(opal_list_t *monitor,
                                                    opal_list_t *directives,
                                                    opal_pmix_info_cbfunc_t cbfunc, void *cbdata);
 
+typedef bool (*opal_pmix_base_legacy_get_fn_t)(void);
+
 /*
  * the standard public API data structure
  */
 typedef struct {
+    opal_pmix_base_legacy_get_fn_t                          legacy_get;
     /* client APIs */
     opal_pmix_base_module_init_fn_t                         init;
     opal_pmix_base_module_fini_fn_t                         finalize;
diff --git a/opal/mca/pmix/pmix2x/pmix2x.c b/opal/mca/pmix/pmix2x/pmix2x.c
@@ -1,6 +1,6 @@
 /* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
 /*
- * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2014-2017 Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2014-2015 Mellanox Technologies, Inc.
@@ -50,7 +50,7 @@
 
 /* These are functions used by both client and server to
  * access common functions in the embedded PMIx library */
-
+static bool legacy_get(void);
 static const char *pmix2x_get_nspace(opal_jobid_t jobid);
 static void pmix2x_register_jobid(opal_jobid_t jobid, const char *nspace);
 static void register_handler(opal_list_t *event_codes,
@@ -72,6 +72,7 @@ static void pmix2x_log(opal_list_t *info,
                        opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
 
 const opal_pmix_base_module_t opal_pmix_pmix2x_module = {
+    .legacy_get = legacy_get,
     /* client APIs */
     .init = pmix2x_client_init,
     .finalize = pmix2x_client_finalize,
@@ -126,6 +127,11 @@ const opal_pmix_base_module_t opal_pmix_pmix2x_module = {
     .register_jobid = pmix2x_register_jobid
 };
 
+static bool legacy_get(void)
+{
+    return mca_pmix_pmix2x_component.legacy_get;
+}
+
 static void opcbfunc(pmix_status_t status, void *cbdata)
 {
     pmix2x_opcaddy_t *op = (pmix2x_opcaddy_t*)cbdata;
diff --git a/opal/mca/pmix/pmix2x/pmix2x.h b/opal/mca/pmix/pmix2x/pmix2x.h
@@ -48,6 +48,7 @@ BEGIN_C_DECLS
 
 typedef struct {
   opal_pmix_base_component_t super;
+  bool legacy_get;
   opal_list_t jobids;
   bool native_launch;
   size_t evindex;
diff --git a/opal/mca/pmix/pmix2x/pmix2x_client.c b/opal/mca/pmix/pmix2x/pmix2x_client.c
@@ -1,6 +1,6 @@
 /* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
 /*
- * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2014-2017 Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2014-2017 Mellanox Technologies, Inc.
@@ -400,7 +400,6 @@ int pmix2x_store_local(const opal_process_name_t *proc, opal_value_t *val)
 
     PMIX_VALUE_CONSTRUCT(&kv);
     pmix2x_value_load(&kv, val);
-
     /* call the library - this is a blocking call */
     rc = PMIx_Store_internal(&p, val->key, &kv);
     PMIX_VALUE_DESTRUCT(&kv);
@@ -596,10 +595,11 @@ int pmix2x_get(const opal_process_name_t *proc, const char *key,
         return OPAL_ERR_NOT_INITIALIZED;
     }
 
-    if (NULL == proc) {
+    if (NULL == proc && NULL != key) {
         /* if they are asking for our jobid, then return it */
         if (0 == strcmp(key, OPAL_PMIX_JOBID)) {
             (*val) = OBJ_NEW(opal_value_t);
+            (*val)->key = strdup(key);
             (*val)->type = OPAL_UINT32;
             (*val)->data.uint32 = OPAL_PROC_MY_NAME.jobid;
             OPAL_PMIX_RELEASE_THREAD(&opal_pmix_base.lock);
@@ -608,6 +608,7 @@ int pmix2x_get(const opal_process_name_t *proc, const char *key,
         /* if they are asking for our rank, return it */
         if (0 == strcmp(key, OPAL_PMIX_RANK)) {
             (*val) = OBJ_NEW(opal_value_t);
+            (*val)->key = strdup(key);
             (*val)->type = OPAL_INT;
             (*val)->data.integer = pmix2x_convert_rank(my_proc.rank);
             OPAL_PMIX_RELEASE_THREAD(&opal_pmix_base.lock);
@@ -642,6 +643,9 @@ int pmix2x_get(const opal_process_name_t *proc, const char *key,
     rc = PMIx_Get(&p, key, pinfo, sz, &pval);
     if (PMIX_SUCCESS == rc) {
         ival = OBJ_NEW(opal_value_t);
+        if (NULL != key) {
+            ival->key = strdup(key);
+        }
         if (OPAL_SUCCESS != (ret = pmix2x_value_unload(ival, pval))) {
             rc = pmix2x_convert_opalrc(ret);
         } else {
@@ -663,6 +667,9 @@ static void val_cbfunc(pmix_status_t status,
 
     OPAL_ACQUIRE_OBJECT(op);
     OBJ_CONSTRUCT(&val, opal_value_t);
+    if (NULL != op->nspace) {
+        val.key = strdup(op->nspace);
+    }
     rc = pmix2x_convert_opalrc(status);
     if (PMIX_SUCCESS == status && NULL != kv) {
         rc = pmix2x_value_unload(&val, kv);
@@ -702,6 +709,7 @@ int pmix2x_getnb(const opal_process_name_t *proc, const char *key,
         if (0 == strcmp(key, OPAL_PMIX_JOBID)) {
             if (NULL != cbfunc) {
                 val = OBJ_NEW(opal_value_t);
+                val->key = strdup(key);
                 val->type = OPAL_UINT32;
                 val->data.uint32 = OPAL_PROC_MY_NAME.jobid;
                 cbfunc(OPAL_SUCCESS, val, cbdata);
@@ -713,6 +721,7 @@ int pmix2x_getnb(const opal_process_name_t *proc, const char *key,
         if (0 == strcmp(key, OPAL_PMIX_RANK)) {
             if (NULL != cbfunc) {
                 val = OBJ_NEW(opal_value_t);
+                val->key = strdup(key);
                 val->type = OPAL_INT;
                 val->data.integer = pmix2x_convert_rank(my_proc.rank);
                 cbfunc(OPAL_SUCCESS, val, cbdata);
@@ -726,7 +735,9 @@ int pmix2x_getnb(const opal_process_name_t *proc, const char *key,
     op = OBJ_NEW(pmix2x_opcaddy_t);
     op->valcbfunc = cbfunc;
     op->cbdata = cbdata;
-
+    if (NULL != key) {
+        op->nspace = strdup(key);
+    }
     if (NULL == proc) {
         (void)strncpy(op->p.nspace, my_proc.nspace, PMIX_MAX_NSLEN);
         op->p.rank = pmix2x_convert_rank(PMIX_RANK_WILDCARD);
diff --git a/opal/mca/pmix/pmix2x/pmix2x_component.c b/opal/mca/pmix/pmix2x/pmix2x_component.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2014-2015 Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2016 Cisco Systems, Inc.  All rights reserved.
@@ -21,6 +21,7 @@
 #include "opal/constants.h"
 #include "opal/class/opal_list.h"
 #include "opal/util/proc.h"
+#include "opal/util/show_help.h"
 #include "opal/mca/pmix/pmix.h"
 #include "pmix2x.h"
 
@@ -74,6 +75,7 @@ mca_pmix_pmix2x_component_t mca_pmix_pmix2x_component = {
             MCA_BASE_METADATA_PARAM_CHECKPOINT
         }
     },
+    .legacy_get = true,
     .native_launch = false
 };
 
diff --git a/orte/mca/grpcomm/direct/grpcomm_direct.c b/orte/mca/grpcomm/direct/grpcomm_direct.c
@@ -275,7 +275,7 @@ static void xcast_recv(int status, orte_process_name_t* sender,
     size_t inlen, cmplen;
     uint8_t *packed_data, *cmpdata;
     int32_t nvals, i;
-    opal_value_t *kv;
+    opal_value_t kv, *kval;
     orte_process_name_t dmn;
 
     OPAL_OUTPUT_VERBOSE((1, orte_grpcomm_base_framework.framework_output,
@@ -461,33 +461,57 @@ static void xcast_recv(int status, orte_process_name_t* sender,
                         OBJ_CONSTRUCT(&wireup, opal_buffer_t);
                         opal_dss.load(&wireup, bo->bytes, bo->size);
                         /* decode it, pushing the info into our database */
-                        cnt=1;
-                        while (OPAL_SUCCESS == (ret = opal_dss.unpack(&wireup, &dmn, &cnt, ORTE_NAME))) {
-                            cnt = 1;
-                            if (ORTE_SUCCESS != (ret = opal_dss.unpack(&wireup, &nvals, &cnt, OPAL_INT32))) {
+                        if (opal_pmix.legacy_get()) {
+                            OBJ_CONSTRUCT(&kv, opal_value_t);
+                            kv.key = OPAL_PMIX_PROC_URI;
+                            kv.type = OPAL_STRING;
+                            cnt=1;
+                            while (OPAL_SUCCESS == (ret = opal_dss.unpack(&wireup, &dmn, &cnt, ORTE_NAME))) {
+                                cnt = 1;
+                                if (ORTE_SUCCESS != (ret = opal_dss.unpack(&wireup, &kv.data.string, &cnt, OPAL_STRING))) {
+                                    ORTE_ERROR_LOG(ret);
+                                    break;
+                                }
+                                if (OPAL_SUCCESS != (ret = opal_pmix.store_local(&dmn, &kv))) {
+                                    ORTE_ERROR_LOG(ret);
+                                    free(kv.data.string);
+                                    break;
+                                }
+                                free(kv.data.string);
+                                kv.data.string = NULL;
+                            }
+                            if (ORTE_ERR_UNPACK_READ_PAST_END_OF_BUFFER != ret) {
                                 ORTE_ERROR_LOG(ret);
-                                break;
                             }
-                            for (i=0; i < nvals; i++) {
+                        } else {
+                           cnt=1;
+                           while (OPAL_SUCCESS == (ret = opal_dss.unpack(&wireup, &dmn, &cnt, ORTE_NAME))) {
+                               cnt = 1;
+                               if (ORTE_SUCCESS != (ret = opal_dss.unpack(&wireup, &nvals, &cnt, OPAL_INT32))) {
+                                   ORTE_ERROR_LOG(ret);
+                                   break;
+                               }
+                               for (i=0; i < nvals; i++) {
                                 cnt = 1;
-                                if (ORTE_SUCCESS != (ret = opal_dss.unpack(&wireup, &kv, &cnt, OPAL_VALUE))) {
+                                if (ORTE_SUCCESS != (ret = opal_dss.unpack(&wireup, &kval, &cnt, OPAL_VALUE))) {
                                     ORTE_ERROR_LOG(ret);
                                     break;
                                 }
                                 OPAL_OUTPUT_VERBOSE((5, orte_grpcomm_base_framework.framework_output,
-                                                    "%s STORING MODEX DATA FOR PROC %s KEY %s",
-                                                    ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
-                                                    ORTE_NAME_PRINT(&dmn), kv->key));
-                                if (OPAL_SUCCESS != (ret = opal_pmix.store_local(&dmn, kv))) {
+                                                     "%s STORING MODEX DATA FOR PROC %s KEY %s",
+                                                     ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
+                                                     ORTE_NAME_PRINT(&dmn), kval->key));
+                                if (OPAL_SUCCESS != (ret = opal_pmix.store_local(&dmn, kval))) {
                                     ORTE_ERROR_LOG(ret);
-                                    OBJ_RELEASE(kv);
+                                    OBJ_RELEASE(kval);
                                     break;
                                 }
-                                OBJ_RELEASE(kv);
+                                OBJ_RELEASE(kval);
+                            }
+                            }
+                            if (ORTE_ERR_UNPACK_READ_PAST_END_OF_BUFFER != ret) {
+                                ORTE_ERROR_LOG(ret);
                             }
-                        }
-                        if (ORTE_ERR_UNPACK_READ_PAST_END_OF_BUFFER != ret) {
-                            ORTE_ERROR_LOG(ret);
                         }
                         /* done with the wireup buffer - dump it */
                         OBJ_DESTRUCT(&wireup);
diff --git a/orte/mca/odls/base/odls_base_default_fns.c b/orte/mca/odls/base/odls_base_default_fns.c
diff --git a/orte/mca/plm/base/plm_base_launch_support.c b/orte/mca/plm/base/plm_base_launch_support.c
diff --git a/orte/mca/state/dvm/state_dvm.c b/orte/mca/state/dvm/state_dvm.c
diff --git a/orte/orted/orted_main.c b/orte/orted/orted_main.c

Original file line number	Diff line number	Diff line change
`@@ -232,8 +232,10 @@ int pmix1_store_local(const opal_process_name_t proc, opal_value_t val)`
`232`	`232`	`}`
`233`	`233`	`}`
`234`	`234`	`if (NULL == job) {`
`235`		`- OPAL_ERROR_LOG(OPAL_ERR_NOT_FOUND);`
`236`		`- return OPAL_ERR_NOT_FOUND;`
	`235`	`+ job = OBJ_NEW(opal_pmix1_jobid_trkr_t);`
	`236`	`+ (void)opal_snprintf_jobid(job->nspace, PMIX_MAX_NSLEN, proc->jobid);`
	`237`	`+ job->jobid = proc->jobid;`
	`238`	`+ opal_list_append(&mca_pmix_ext1x_component.jobids, &job->super);`
`237`	`239`	`}`
`238`	`240`	`(void)strncpy(p.nspace, job->nspace, PMIX_MAX_NSLEN);`
`239`	`241`	`p.rank = proc->vpid;`