From 7d2464f7331ad41923c46e8e9f2b3da17a1349e1 Mon Sep 17 00:00:00 2001
From: Rob Latham <robl@mcs.anl.gov>
Date: Thu, 20 Sep 2018 15:43:41 +0000
Subject: [PATCH] HDF5: option to enable collective metadata

In HDF5-1.10 the library has an option to read and write the metadata of a file collectively.  One has to opt-in to this optimization with a property list but particularly at large scale it can have tremendous performance implications.

Further information:
- https://support.hdfgroup.org/HDF5/docNewFeatures/CollMDataIO/RFC-CollectiveMetadataReads.pdf
- https://support.hdfgroup.org/HDF5/doc/RM/RM_H5P.html#Property-SetAllCollMetadataOps
---
 configure.ac                   |  4 ++++
 doc/sphinx/userDoc/options.rst |  3 +++
 src/aiori-HDF5.c               | 11 +++++++++++
 src/ior.h                      |  1 +
 src/parse_options.c            |  2 ++
 5 files changed, 21 insertions(+)

diff --git a/configure.ac b/configure.ac
index a59cba4..a3c41b0 100755
--- a/configure.ac
+++ b/configure.ac
@@ -98,8 +98,12 @@ AC_ARG_WITH([hdf5],
 AM_CONDITIONAL([USE_HDF5_AIORI], [test x$with_hdf5 = xyes])
 AM_COND_IF([USE_HDF5_AIORI],[
         AC_DEFINE([USE_HDF5_AIORI], [], [Build HDF5 backend AIORI])
+	AC_SEARCH_LIBS([H5Pset_all_coll_metadata_ops], [hdf5])
+	AC_CHECK_FUNCS([H5Pset_all_coll_metadata_ops])
 ])
 
+
+
 # HDFS support
 AC_ARG_WITH([hdfs],
         [AS_HELP_STRING([--with-hdfs],
diff --git a/doc/sphinx/userDoc/options.rst b/doc/sphinx/userDoc/options.rst
index bb7eb92..8b44126 100644
--- a/doc/sphinx/userDoc/options.rst
+++ b/doc/sphinx/userDoc/options.rst
@@ -289,6 +289,9 @@ HDF5-ONLY
 
   * setAlignment         - HDF5 alignment in bytes (e.g.: 8, 4k, 2m, 1g) [1]
 
+  * collectiveMetadata   - enable HDF5 collective metadata (available since
+                           HDF5-1.10.0)
+
 MPIIO-, HDF5-, AND NCMPI-ONLY
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   * collective           - uses collective operations for access [0=FALSE]
diff --git a/src/aiori-HDF5.c b/src/aiori-HDF5.c
index ffcda2a..173abb4 100755
--- a/src/aiori-HDF5.c
+++ b/src/aiori-HDF5.c
@@ -228,6 +228,17 @@ static void *HDF5_Open(char *testFileName, IOR_param_t * param)
                                     param->setAlignment),
                    "cannot set alignment");
 
+#ifdef HAVE_H5PSET_ALL_COLL_METADATA_OPS
+        if (param->collective_md) {
+                /* more scalable metadata */
+
+                HDF5_CHECK(H5Pset_all_coll_metadata_ops(accessPropList, 1),
+                        "cannot set collective md read");
+                HDF5_CHECK(H5Pset_coll_metadata_write(accessPropList, 1),
+                        "cannot set collective md write");
+        }
+#endif
+
         /* open file */
         if (param->open == WRITE) {     /* WRITE */
                 *fd = H5Fcreate(testFileName, fd_mode,
diff --git a/src/ior.h b/src/ior.h
index c283be7..b75299d 100755
--- a/src/ior.h
+++ b/src/ior.h
@@ -175,6 +175,7 @@ typedef struct
     char*       URI;                 /* "path" to target object */
     size_t      part_number;         /* multi-part upload increment (PER-RANK!) */
     char*       UploadId; /* key for multi-part-uploads */
+    int         collective_md;       /* use collective metatata optimization */
 
     /* RADOS variables */
     rados_t rados_cluster;           /* RADOS cluster handle */
diff --git a/src/parse_options.c b/src/parse_options.c
index a8f81b0..710447a 100755
--- a/src/parse_options.c
+++ b/src/parse_options.c
@@ -300,6 +300,8 @@ void DecodeDirective(char *line, IOR_param_t *params)
                 params->numTasks = atoi(value);
         } else if (strcasecmp(option, "summaryalways") == 0) {
                 params->summary_every_test = atoi(value);
+        } else if (strcasecmp(option, "collectiveMetadata") == 0) {
+                params->collective_md = atoi(value);
         } else {
                 if (rank == 0)
                         fprintf(out_logfile, "Unrecognized parameter \"%s\"\n",