Fix possible performance regression introduced with in-place type conversion in 1.14.2 (#3424)

* Fix possible performance regression introduced with in-place type conversion in 1.14.2 (#3376)

* Add RELEASE.txt entry for compound performance regression fix (#3376) (#3416)

* Fix errors in release notes from forgetting to hit save.

2 files changed, 31 insertions, 1 deletions

diff --git a/release_docs/RELEASE.txt b/release_docs/RELEASE.txt
index a083c13..40faff6 100644
--- a/release_docs/RELEASE.txt
+++ b/release_docs/RELEASE.txt
@@ -109,7 +109,17 @@ Bug Fixes since HDF5-1.14.2 release
 ===================================
     Library
     -------
-    - 
+    - Fixed performance regression with some compound type conversions
+
+      In-place type conversion was introduced for most use cases in 1.14.2.
+      While being able to use the read buffer for type conversion potentially
+      improves performance by performing the entire I/O at once, it also
+      disables the optimized compound type conversion used when the destination
+      is a subset of the source. Disabled in-place type conversion when using
+      this optimized conversion and there is no benefit in terms of the I/O
+      size.
+
+    - Fixed an assertion in a previous fix for CVE-2016-4332
 
 
     Java Library
diff --git a/src/H5Dscatgath.c b/src/H5Dscatgath.c
index cf6b4fd..4516f1f 100644
--- a/src/H5Dscatgath.c
+++ b/src/H5Dscatgath.c
@@ -478,6 +478,16 @@ H5D__scatgath_read(const H5D_io_info_t *io_info, const H5D_dset_io_info_t *dset_
     in_place_tconv = dset_info->layout_io_info.contig_piece_info &&
                      dset_info->layout_io_info.contig_piece_info->in_place_tconv;
 
+    /* Check if we should disable in-place type conversion for performance.  Do so if we can use the optimized
+     * compound read function, if this is not a selection I/O operation (so we have normal size conversion
+     * buffers), and the either entire I/O operation can fit in the type conversion buffer or we need to use a
+     * background buffer (and therefore could not do the I/O in one operation with in-place conversion
+     * anyways). */
+    if (in_place_tconv && H5D__SCATGATH_USE_CMPD_OPT_READ(dset_info, FALSE) &&
+        (io_info->use_select_io != H5D_SELECTION_IO_MODE_ON) &&
+        (dset_info->type_info.need_bkg || (dset_info->nelmts <= dset_info->type_info.request_nelmts)))
+        in_place_tconv = FALSE;
+
     /* Allocate the iterators */
     if (NULL == (mem_iter = H5FL_MALLOC(H5S_sel_iter_t)))
         HGOTO_ERROR(H5E_DATASET, H5E_CANTALLOC, FAIL, "can't allocate memory iterator");
@@ -653,6 +663,16 @@ H5D__scatgath_write(const H5D_io_info_t *io_info, const H5D_dset_io_info_t *dset
     in_place_tconv = dset_info->layout_io_info.contig_piece_info &&
                      dset_info->layout_io_info.contig_piece_info->in_place_tconv;
 
+    /* Check if we should disable in-place type conversion for performance.  Do so if we can use the optimized
+     * compound write function, if this is not a selection I/O operation (so we have normal size conversion
+     * buffers), and the either entire I/O operation can fit in the type conversion buffer or we need to use a
+     * background buffer (and therefore could not do the I/O in one operation with in-place conversion
+     * anyways). */
+    if (in_place_tconv && H5D__SCATGATH_USE_CMPD_OPT_WRITE(dset_info, FALSE) &&
+        (io_info->use_select_io != H5D_SELECTION_IO_MODE_ON) &&
+        (dset_info->type_info.need_bkg || (dset_info->nelmts <= dset_info->type_info.request_nelmts)))
+        in_place_tconv = FALSE;
+
     /* Allocate the iterators */
     if (NULL == (mem_iter = H5FL_MALLOC(H5S_sel_iter_t)))
         HGOTO_ERROR(H5E_DATASET, H5E_CANTALLOC, FAIL, "can't allocate memory iterator");