Update to track PMIx v2.0.1

Ralph Castain · Ralph Castain · commit ed85512a7c34 · 2017-06-25T07:29:32.000-07:00
Signed-off-by: Ralph Castain &lt;rhc@open-mpi.org&gt;
diff --git a/opal/mca/pmix/pmix2x/pmix/AUTHORS b/opal/mca/pmix/pmix2x/pmix/AUTHORS
@@ -9,31 +9,22 @@ Email                           Name                        Affiliation(s)
 alinask                         Elena Shipunova             Mellanox
 annu13                          Annapurna Dasari            Intel
 artpol84                        Artem Polyakov              Mellanox
-ashleypittman                   Ashley Pittman              Intel
 dsolt                           Dave Solt                   IBM
-garlick                         Jim Garlick                 LLNL
 ggouaillardet                   Gilles Gouaillardet         RIST
 hjelmn                          Nathan Hjelm                LANL
 igor-ivanov                     Igor Ivanov                 Mellanox
 jladd-mlnx                      Joshua Ladd                 Mellanox
-jjhursey                        Joshua Hursey               IBM
-jsquyres                        Jeff Squyres                Cisco
-karasevb                        Boris Karasev               Mellanox
-kawashima-fj                    Takahiro Kawashima          Fujitsu
+jsquyres                        Jeff Squyres                Cisco, IU
 nkogteva                        Nadezhda Kogteva            Mellanox
-nysal                           Nysal Jan KA                IBM
-PHHargrove                      Paul Hargrove               LBNL
-rhc54                           Ralph Castain               Intel
+rhc54                           Ralph Castain               LANL, Cisco, Intel
 ------------------------------- --------------------------- -------------------
 
 Affiliation abbreviations:
 --------------------------
 Cisco = Cisco Systems, Inc.
-Fujitsu = Fujitsu
 IBM = International Business Machines, Inc.
 Intel = Intel, Inc.
+IU = Indiana University
 LANL = Los Alamos National Laboratory
-LBNL = Lawrence Berkeley National Laboratory
-LLNL = Lawrence Livermore National Laboratory
 Mellanox = Mellanox
 RIST = Research Organization for Information Science and Technology
diff --git a/opal/mca/pmix/pmix2x/pmix/INSTALL b/opal/mca/pmix/pmix2x/pmix/INSTALL
@@ -24,7 +24,7 @@ This file is a *very* short overview of building and installing
 the PMIx library.  Much more information is available on the
 PMIx web site (e.g., see the FAQ section):
 
-    http://pmix.github.io/pmix/pmix
+    http://pmix.github.io/pmix/master
 
 
 Developer Builds
@@ -34,7 +34,7 @@ If you have checked out a DEVELOPER'S COPY of PMIx (i.e., you checked
 out from Git), you should read the HACKING file before attempting to
 build PMIx.  You must then run:
 
-shell$ ./autogen.pl
+shell$ ./autogen.sh
 
 You will need very recent versions of GNU Autoconf, Automake, and
 Libtool.  If autogen.sh fails, read the HACKING file.  If anything
diff --git a/opal/mca/pmix/pmix2x/pmix/NEWS b/opal/mca/pmix/pmix2x/pmix/NEWS
@@ -24,65 +24,6 @@ current release as well as the "stable" bug fix release branch.
 Master (not on release branches yet)
 ------------------------------------
 
-
-2.0.0
-------
-**** NOTE: This release implements the complete PMIX v2.0 Standard
-**** and therefore includes a number of new APIs and features. These
-**** can be tracked by their RFC's in the RFC repository at:
-**** https://github.com/pmix/RFCs. A formal standards document will
-**** be included in a later v2.x release. Some of the changes are
-**** identified below.
-- Added the Modular Component Architecture (MCA) plugin manager and
-  converted a number of operations to plugins, thereby allowing easy
-  customization and extension (including proprietary offerings)
-- Added support for TCP sockets instead of Unix domain sockets for
-  client-server communications
-- Added support for on-the-fly Allocation requests, including requests
-  for additional resources, extension of time for currently allocated
-  resources, and return of identified allocated resources to the scheduler
-  (RFC 0005 - https://github.com/pmix/RFCs/blob/master/RFC0005.md)
-- Tightened rules on the processing of PMIx_Get requests, including
-  reservation of the "pmix" prefix for attribute keys and specifying
-  behaviors associated with the PMIX_RANK_WILDCARD value
-  (RFC 0009 - https://github.com/pmix/RFCs/blob/master/RFC0009.md)
-- Extended support for tool interactions with a PMIx server aimed at
-  meeting the needs of debuggers and other tools. Includes support
-  for rendezvousing with a system-level PMIx server for interacting
-  with the system management stack (SMS) outside of an allocated
-  session, and adds two new APIs:
-  - PMIx_Query: request general information such as the process
-    table for a specified job, and available SMS capabilities
-  - PMIx_Log: log messages (e.g., application progress) to a
-    system-hosted persistent store
-  (RFC 0010 - https://github.com/pmix/RFCs/blob/master/RFC0010.md)
-- Added support for fabric/network interactions associated with
-  "instant on" application startup
-  (RFC 0012 - https://github.com/pmix/RFCs/blob/master/RFC0012.md)
-- Added an attribute to support getting the time remaining in an
-  allocation via the PMIx_Query interface
-  (RFC 0013 - https://github.com/pmix/RFCs/blob/master/RFC0013.md)
-- Added interfaces to support job control and monitoring requests,
-  including heartbeat and file monitors to detect stalled applications.
-  Job control interface supports standard signal-related operations
-  (pause, kill, resume, etc.) as well as checkpoint/restart requests.
-  The interface can also be used by an application to indicate it is
-  willing to be pre-empted, with the host RM providing an event
-  notification when the preemption is desired.
-  (RFC 0015 - https://github.com/pmix/RFCs/blob/master/RFC0015.md)
-- Extended the event notification system to support notifications
-  across threads in the same process, and the ability to direct
-  ordering of notifications when registering event handlers.
-  (RFC 0018 - https://github.com/pmix/RFCs/blob/master/RFC0018.md)
-- Expose the buffer manipulation functions via a new set of APIs
-  to support heterogeneous data transfers within the host RM
-  environment
-  (RFC 0020 - https://github.com/pmix/RFCs/blob/master/RFC0020.md)
-- Fix a number of race condition issues that arose at scale
-- Enable PMIx servers to generate notifications to the host RM
-  and to themselves
-
-
 1.2.2 -- 21 March 2017
 ----------------------
 - Compiler fix for Sun/Oracle CC (PR #322)
diff --git a/opal/mca/pmix/pmix2x/pmix/VERSION b/opal/mca/pmix/pmix2x/pmix/VERSION
@@ -13,7 +13,7 @@
 # major, minor, and release are generally combined in the form
 # <major>.<minor>.<release>.
 
-major=2
+major=3
 minor=0
 release=0
 
@@ -23,14 +23,14 @@ release=0
 # The only requirement is that it must be entirely printable ASCII
 # characters and have no white space.
 
-greek=
+greek=a1
 
 # If repo_rev is empty, then the repository version number will be
 # obtained during "make dist" via the "git describe --tags --always"
 # command, or with the date (if "git describe" fails) in the form of
 # "date<date>".
 
-repo_rev=git6fb501d
+repo_rev=git4c2c8d0
 
 # If tarball_version is not empty, it is used as the version string in
 # the tarball filename, regardless of all other versions listed in
@@ -44,7 +44,7 @@ tarball_version=
 
 # The date when this release was created
 
-date="Jun 19, 2017"
+date="Jun 25, 2017"
 
 # The shared library version of each of PMIx's public libraries.
 # These versions are maintained in accordance with the "Library
@@ -75,4 +75,4 @@ date="Jun 19, 2017"
 # Version numbers are described in the Libtool current:revision:age
 # format.
 
-libpmix_so_version=3:0:1
+libpmix_so_version=0:0:0
diff --git a/opal/mca/pmix/pmix2x/pmix/include/pmix_common.h b/opal/mca/pmix/pmix2x/pmix/include/pmix_common.h
@@ -124,6 +124,8 @@ typedef uint32_t pmix_rank_t;
 #define PMIX_CONNECT_SYSTEM_FIRST           "pmix.cnct.sys.first"   // (bool) Preferentially look for a system-level PMIx server first
 #define PMIX_REGISTER_NODATA                "pmix.reg.nodata"       // (bool) Registration is for nspace only, do not copy job data
 #define PMIX_SERVER_ENABLE_MONITORING       "pmix.srv.monitor"      // (bool) Enable PMIx internal monitoring by server
+#define PMIX_SERVER_NSPACE                  "pmix.srv.nspace"       // (char*) Name of the nspace to use for this server
+#define PMIX_SERVER_RANK                    "pmix.srv.rank"         // (pmix_rank_t) Rank of this server
 
 
 /* identification attributes */
diff --git a/opal/mca/pmix/pmix2x/pmix/src/buffer_ops/copy.c b/opal/mca/pmix/pmix2x/pmix/src/buffer_ops/copy.c
@@ -425,7 +425,7 @@ PMIX_EXPORT pmix_status_t pmix_value_xfer(pmix_value_t *p, pmix_value_t *src)
             break;
         }
         /* allocate space and do the copy */
-        switch (src->type) {
+        switch (src->data.darray->type) {
             case PMIX_UINT8:
             case PMIX_INT8:
             case PMIX_BYTE:
diff --git a/opal/mca/pmix/pmix2x/pmix/src/buffer_ops/unpack.c b/opal/mca/pmix/pmix2x/pmix/src/buffer_ops/unpack.c
@@ -769,6 +769,7 @@ pmix_status_t pmix_bfrop_unpack_info(pmix_buffer_t *buffer, void *dest,
             return ret;
         }
         if (NULL == tmp) {
+            PMIX_ERROR_LOG(PMIX_ERROR);
             return PMIX_ERROR;
         }
         (void)strncpy(ptr[i].key, tmp, PMIX_MAX_KEYLEN);
diff --git a/opal/mca/pmix/pmix2x/pmix/src/client/pmix_client_get.c b/opal/mca/pmix/pmix2x/pmix/src/client/pmix_client_get.c
@@ -111,7 +111,7 @@ PMIX_EXPORT pmix_status_t PMIx_Get(const pmix_proc_t *proc, const char key[],
     PMIX_RELEASE(cb);
 
     pmix_output_verbose(2, pmix_globals.debug_output,
-                        "pmix:client get completed");
+                        "pmix:client get completed %d", rc);
 
     return rc;
 }
@@ -464,7 +464,7 @@ static pmix_status_t process_val(pmix_value_t *val,
     }
     nvals = 0;
     for (n=0; n < nsize; n++) {
-        if (PMIX_SUCCESS != (rc = pmix_pointer_array_add(results, &info[n]))) {
+        if (0 > (rc = pmix_pointer_array_add(results, &info[n]))) {
             return rc;
         }
         ++nvals;
@@ -536,25 +536,45 @@ static void _getnbfn(int fd, short flags, void *cbdata)
         /* if the rank is WILDCARD, then they want all the job-level info,
          * so no need to check the modex */
         if (PMIX_RANK_WILDCARD != cb->rank) {
+            rc = PMIX_ERR_NOT_FOUND;
 #if defined(PMIX_ENABLE_DSTORE) && (PMIX_ENABLE_DSTORE == 1)
-            if (PMIX_SUCCESS == (rc = pmix_dstore_fetch(nptr->nspace, cb->rank, NULL, &val))) {
-#else
-            if (PMIX_SUCCESS == (rc = pmix_hash_fetch(&nptr->modex, cb->rank, NULL, &val))) {
+            /* my own data is in the hash table, so don't bother looking
+             * in the dstore if that is what they want */
+            if (pmix_globals.myid.rank != cb->rank) {
+                if (PMIX_SUCCESS == (rc = pmix_dstore_fetch(nptr->nspace, cb->rank, NULL, &val))) {
+                    pmix_output_verbose(2, pmix_globals.debug_output,
+                                        "pmix_get[%d]: value retrieved from dstore", __LINE__);
+                    if (PMIX_SUCCESS != (rc = process_val(val, &nvals, &results))) {
+                        cb->value_cbfunc(rc, NULL, cb->cbdata);
+                        /* cleanup */
+                        if (NULL != val) {
+                            PMIX_VALUE_RELEASE(val);
+                        }
+                        PMIX_RELEASE(cb);
+                        return;
+                    }
+                }
+            }
 #endif /* PMIX_ENABLE_DSTORE */
-                pmix_output_verbose(2, pmix_globals.debug_output,
-                                    "pmix_get[%d]: value retrieved from dstore", __LINE__);
-                if (PMIX_SUCCESS != (rc = process_val(val, &nvals, &results))) {
-                    cb->value_cbfunc(rc, NULL, cb->cbdata);
-                    /* cleanup */
-                    if (NULL != val) {
-                        PMIX_VALUE_RELEASE(val);
+            if (PMIX_SUCCESS != rc) {
+                /* if the user was asking about themselves, or we aren't using the dstore,
+                 * then we need to check the hash table */
+                if (PMIX_SUCCESS == (rc = pmix_hash_fetch(&nptr->modex, cb->rank, NULL, &val))) {
+                    pmix_output_verbose(2, pmix_globals.debug_output,
+                                        "pmix_get[%d]: value retrieved from hash", __LINE__);
+                    if (PMIX_SUCCESS != (rc = process_val(val, &nvals, &results))) {
+                        cb->value_cbfunc(rc, NULL, cb->cbdata);
+                        /* cleanup */
+                        if (NULL != val) {
+                            PMIX_VALUE_RELEASE(val);
+                        }
+                        PMIX_RELEASE(cb);
+                        return;
                     }
-                    PMIX_RELEASE(cb);
-                    return;
+                    PMIX_VALUE_RELEASE(val);
                 }
-                /* cleanup */
-                PMIX_VALUE_RELEASE(val);
-            } else {
+            }
+            if (PMIX_SUCCESS != rc) {
                 /* if we didn't find a modex for this rank, then we need
                  * to go get it. Thus, the caller wants -all- information for
                  * the specified rank, not just the job-level info. */
@@ -572,12 +592,17 @@ static void _getnbfn(int fd, short flags, void *cbdata)
                 PMIX_RELEASE(cb);
                 return;
             }
-            /* cleanup */
             PMIX_VALUE_RELEASE(val);
         }
         /* now let's package up the results */
         PMIX_VALUE_CREATE(val, 1);
         val->type = PMIX_DATA_ARRAY;
+        val->data.darray = (pmix_data_array_t*)malloc(sizeof(pmix_data_array_t));
+        if (NULL == val->data.darray) {
+            PMIX_VALUE_RELEASE(val);
+            cb->value_cbfunc(PMIX_ERR_NOMEM, NULL, cb->cbdata);
+            return;
+        }
         val->data.darray->type = PMIX_INFO;
         val->data.darray->size = nvals;
         PMIX_INFO_CREATE(iptr, nvals);
@@ -597,14 +622,13 @@ static void _getnbfn(int fd, short flags, void *cbdata)
                 } else {
                     pmix_value_xfer(&iptr[n].value, &info->value);
                 }
-                PMIX_INFO_FREE(info, 1);
+                PMIX_INFO_DESTRUCT(info);
             }
         }
         /* done with results array */
         PMIX_DESTRUCT(&results);
-        /* return the result to the caller */
+        /* return the result to the caller - they are responsible for releasing it */
         cb->value_cbfunc(PMIX_SUCCESS, val, cb->cbdata);
-        PMIX_VALUE_FREE(val, 1);
         PMIX_RELEASE(cb);
         return;
     }
diff --git a/opal/mca/pmix/pmix2x/pmix/src/server/pmix_server.c b/opal/mca/pmix/pmix2x/pmix/src/server/pmix_server.c
diff --git a/opal/mca/pmix/pmix2x/pmix/src/util/hash.c b/opal/mca/pmix/pmix2x/pmix/src/util/hash.c
diff --git a/opal/mca/pmix/pmix2x/pmix/test/simple/simpclient.c b/opal/mca/pmix/pmix2x/pmix/test/simple/simpclient.c
diff --git a/opal/mca/pmix/pmix2x/pmix/test/test_common.c b/opal/mca/pmix/pmix2x/pmix/test/test_common.c

Original file line number	Diff line number	Diff line change
`@@ -425,7 +425,7 @@ PMIX_EXPORT pmix_status_t pmix_value_xfer(pmix_value_t p, pmix_value_t src)`
`425`	`425`	`break;`
`426`	`426`	`}`
`427`	`427`	`/* allocate space and do the copy */`
`428`		`- switch (src->type) {`
	`428`	`+ switch (src->data.darray->type) {`
`429`	`429`	`case PMIX_UINT8:`
`430`	`430`	`case PMIX_INT8:`
`431`	`431`	`case PMIX_BYTE:`
Original file line number	Diff line number	Diff line change
`@@ -769,6 +769,7 @@ pmix_status_t pmix_bfrop_unpack_info(pmix_buffer_t buffer, void dest,`
`769`	`769`	`return ret;`
`770`	`770`	`}`
`771`	`771`	`if (NULL == tmp) {`
	`772`	`+ PMIX_ERROR_LOG(PMIX_ERROR);`
`772`	`773`	`return PMIX_ERROR;`
`773`	`774`	`}`
`774`	`775`	`(void)strncpy(ptr[i].key, tmp, PMIX_MAX_KEYLEN);`