Accepting request 558744 from home:NMoreyChaisemartin:branches:science:HPC

- Update to v1.5.3
  - Core
    - Handle malloc failures
    - Ensure global lock is initialized on Windows
    - Fix spelling and formatting errors in man pages
  - PSM
    - Fix print format mismatches
    - Remove 15 second startup delay when no hardware is installed
    - Preserve FI_MR_SCALABLE mode bit for backwards compatability
  - PSM2
    - Fix print format mismatches
    - Allow all to all communication between scalable endpoints
    - Preserve FI_MR_SCALABLE mode bit for backwards compatability
    - Fix reference counting issue with opened domains
    - Fix segfault for RMA/atomic operations to local scalable endpoints
    - Fix resource counting related issues for Tx/Rx contexts
    - Allow completion suppression when fi_context is non-NULL
    - Use correct queue for triggered operations with scalable endpoints
  - Sockets
    - Fix check for invalid connection handle
    - Fix crash in fi_av_remove
  - Util
    - Fix number of bits used for connection index
  - Verbs
    - Fix incorrect CQ entry data for MSG endpoints
    - Properly check for errors from getifaddrs
    - Retry getifaddr on failure because of busy netlink sockets
    - Ack CM events on error paths
- Remove 0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch
   as it was merged upstream

OBS-URL: https://build.opensuse.org/request/show/558744
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=28

0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch

@@ -1,86 +0,0 @@
-From 6c8c40ad84fa790831407e5cd25375af898d929b Mon Sep 17 00:00:00 2001
-From: Jianxin Xiong <jianxin.xiong@intel.com>
-Date: Mon, 9 Oct 2017 15:10:45 -0700
-Subject: [PATCH] prov/psm: Eliminate psm2-compat library delay with hfi
- devices missing
-
-The PSM2 library may introduce a 15 second delay at device initialization
-time if the hfi devices are missing. This has been handled in the psm2
-provider by checking the existence of the device files before initializing
-the device.
-
-The psm provider didn't handle this situation because the issue doesn't
-exist with native PSM library over TrueScale. However, when PSM is
-supported via the psm2-compat library over PSM2, the same delay can be
-observed.
-
-Now add the same mechanism to the psm provider.
-
-Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com>
----
- prov/psm/src/psmx_init.c | 34 ++++++++++++++++++++++++++++++++++
- 1 file changed, 34 insertions(+)
-
-diff --git a/prov/psm/src/psmx_init.c b/prov/psm/src/psmx_init.c
-index 118ef1a81..c4b06160c 100644
---- a/prov/psm/src/psmx_init.c
-+++ b/prov/psm/src/psmx_init.c
-@@ -32,10 +32,12 @@
- 
- #include "psmx.h"
- #include "prov.h"
-+#include <glob.h>
- 
- static int psmx_init_count = 0;
- static int psmx_lib_initialized = 0;
- static pthread_mutex_t psmx_lib_mutex; 
-+static int psmx_compat_lib = 0;
- 
- struct psmx_env psmx_env = {
- 	.name_server	= 1,
-@@ -103,6 +105,12 @@ static int psmx_init_lib(void)
- 			PSM_VERNO_MAJOR, PSM_VERNO_MINOR, major, minor);
- 	}
- 
-+	if (major > 1) {
-+		psmx_compat_lib = 1;
-+		FI_INFO(&psmx_prov, FI_LOG_CORE,
-+			"PSM is supported via the psm2-compat library over PSM2.\n");
-+	}
-+
- 	psmx_lib_initialized = 1;
- 
- out:
-@@ -197,6 +205,32 @@ static int psmx_getinfo(uint32_t version, const char *node, const char *service,
- 	if (psmx_init_lib())
- 		return -FI_ENODATA;
- 
-+	if (psmx_compat_lib) {
-+		/*
-+		 * native PSM running over TrueScale doesn't have the issue handled
-+		 * here. it's only present when PSM is supported via the psm2-compat
-+		 * library, where the PSM functions are just wrappers around the PSM2
-+		 * counterparts.
-+		 *
-+		 * psm2_ep_num_devunits() may wait for 15 seconds before return
-+		 * when /dev/hfi1_0 is not present. Check the existence of any hfi1
-+		 * device interface first to avoid this delay. Note that the devices
-+		 * don't necessarily appear consecutively so we need to check all
-+		 * possible device names before returning "no device found" error.
-+		 * This also means if "/dev/hfi1_0" doesn't exist but other devices
-+		 * exist, we are still going to see the delay; but that's a rare case.
-+		 */
-+		glob_t glob_buf;
-+
-+		if ((glob("/dev/hfi1_[0-9]", 0, NULL, &glob_buf) != 0) &&
-+		    (glob("/dev/hfi1_[0-9][0-9]", GLOB_APPEND, NULL, &glob_buf) != 0)) {
-+			FI_INFO(&psmx_prov, FI_LOG_CORE,
-+				"no hfi1 device is found.\n");
-+			return -FI_ENODATA;
-+		}
-+		globfree(&glob_buf);
-+	}
-+
- 	if (psm_ep_num_devunits(&cnt) || !cnt) {
- 		FI_INFO(&psmx_prov, FI_LOG_CORE,
- 			"no PSM device is found.\n");

_service

@@ -8,7 +8,7 @@
     <param name="versionformat">@PARENT_TAG@.@TAG_OFFSET@.%h</param>
     <param name="versionrewrite-pattern">v(.*)</param>
     <param name="versionrewrite-replacement">\1</param>
-    <param name="revision">480a6db351fbe8ee38077902c8df875e3cd13205</param>
+    <param name="revision">09aaaf78c239df7fb57f19de44cc96b25701bcb0</param>
   </service>
   <service name="recompress" mode="disabled">
     <param name="file">libfabric*.tar</param>

libfabric-1.5.2.0.480a6db3.tar.bz2

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c2ebdb6376c35b4c88935648843e633bb0a2549eed96d8e610d4ce7ea39d2754
-size 1068927

libfabric-1.5.3.0.09aaaf78c239.tar.bz2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeca796583059a9d3454648b585a98e790ea9c16f8ebe75872e824e410eb8010
+size 1072867

libfabric.changes

@@ -1,3 +1,37 @@
+-------------------------------------------------------------------
+Wed Dec 20 08:49:03 UTC 2017 - nmoreychaisemartin@suse.com
+
+- Update to v1.5.3
+  - Core
+    - Handle malloc failures
+    - Ensure global lock is initialized on Windows
+    - Fix spelling and formatting errors in man pages
+  - PSM
+    - Fix print format mismatches
+    - Remove 15 second startup delay when no hardware is installed
+    - Preserve FI_MR_SCALABLE mode bit for backwards compatability
+  - PSM2
+    - Fix print format mismatches
+    - Allow all to all communication between scalable endpoints
+    - Preserve FI_MR_SCALABLE mode bit for backwards compatability
+    - Fix reference counting issue with opened domains
+    - Fix segfault for RMA/atomic operations to local scalable endpoints
+    - Fix resource counting related issues for Tx/Rx contexts
+    - Allow completion suppression when fi_context is non-NULL
+    - Use correct queue for triggered operations with scalable endpoints
+  - Sockets
+    - Fix check for invalid connection handle
+    - Fix crash in fi_av_remove
+  - Util
+    - Fix number of bits used for connection index
+  - Verbs
+    - Fix incorrect CQ entry data for MSG endpoints
+    - Properly check for errors from getifaddrs
+    - Retry getifaddr on failure because of busy netlink sockets
+    - Ack CM events on error paths
+- Remove 0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch
+   as it was merged upstream
+
 -------------------------------------------------------------------
 Mon Nov 20 16:27:13 UTC 2017 - nmoreychaisemartin@suse.com
 

libfabric.spec

@@ -17,18 +17,17 @@
 
 
 #
-%define git_ver .0.480a6db3
+%define git_ver .0.09aaaf78c239
 
 Name:           libfabric
 Summary:        User-space RDMA Fabric Interfaces
 License:        GPL-2.0 or BSD-2-Clause
 Group:          Development/Libraries/C and C++
-Version:        1.5.2
+Version:        1.5.3
 Release:        0
 Source:         %{name}-%{version}%{git_ver}.tar.bz2
 Source1:        baselibs.conf
 Patch0:         libfabric-libtool.patch
-Patch1:         0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch
 Url:            http://www.github.com/ofiwg/libfabric
 Prefix:         ${_prefix}
 BuildRequires:  autoconf
@@ -72,7 +71,6 @@ services, such as RDMA. This package contains the development files.
 %prep
 %setup -q -n  %{name}-%{version}%{git_ver}
 %patch0 -p1
-%patch1 -p1
 
 %build
 rm -f config/libtool.m4