Hello world,
the attached patch sets the I/O block size for unformatted files to
2**17 and makes this, and the block size for formatted files,
adjustable via environment variables.
The main reason is that -fconvert=big-endian was quite slow on
some HPC systems. A bigger buffer should eliminate that. Also,
People who use unformatted files are likely to write large amounts
of data, so this seems like a good fit. Finally, some benchmarking
showed that 131072 seemed like a good value to use. Thanks to Jerry
for support.
I didn't change the value for formatted files because, frankly, we are
using a lot of CPU for converting numbers there, so any gain
negligible (unless somebody comes up with a benchmark which says
otherwise).
As this is a change in behavior / new feature, I don't think that
backporting is indicated, but if somebody feels otherwise, please
speak up.
Regression-tested. OK for trunk?
Regards
Thomas
2019-07-07 Thomas König <tkoe...@gcc.gnu.org>
PR libfortran/91030
* gfortran.texi (GFORTRAN_BUFFER_SIZE_FORMATTED): Document
(GFORTRAN_BUFFER_SIZE_FORMATTED): Likewise.
2019-07-07 Thomas König <tkoe...@gcc.gnu.org>
PR libfortran/91030
* io/unix.c (BUFFER_SIZE): Delete.
(BUFFER_SIZE_FORMATTED_DEFAULT): New variable.
(BUFFER_SIZE_UNFORMATTED_DEFAULT): New variable.
(unix_stream): Add buffer_size.
(buf_read): Use s->buffer_size instead of BUFFER_SIZE.
(buf_write): Likewise.
(buf_init): Add argument unformatted. Handle block sizes
for unformatted vs. formatted, using defaults if provided.
(fd_to_stream): Add argument unformatted in call to buf_init.
* libgfortran.h (options_t): Add buffer_size_formatted and
buffer_size_unformatted.
* runtime/environ.c (variable_table): Add
GFORTRAN_BUFFER_SIZE_UNFORMATTED and GFORTRAN_BUFFER_SIZE_FORMATTED.
Index: gcc/fortran/gfortran.texi
===================================================================
--- gcc/fortran/gfortran.texi (Revision 273183)
+++ gcc/fortran/gfortran.texi (Arbeitskopie)
@@ -611,6 +611,8 @@ Malformed environment variables are silently ignor
* GFORTRAN_LIST_SEPARATOR:: Separator for list output
* GFORTRAN_CONVERT_UNIT:: Set endianness for unformatted I/O
* GFORTRAN_ERROR_BACKTRACE:: Show backtrace on run-time errors
+* GFORTRAN_BUFFER_SIZE_FORMATTED:: Buffer size for formatted files.
+* GFORTRAN_BUFFER_SIZE_UNFORMATTED:: Buffer size for unformatted files.
@end menu
@node TMPDIR
@@ -782,6 +784,20 @@ the backtracing, set the variable to @samp{n}, @sa
Default is to print a backtrace unless the @option{-fno-backtrace}
compile option was used.
+@node GFORTRAN_BUFFER_SIZE_FORMATTED
+@section @env{GFORTRAN_BUFFER_SIZE_FORMATTED}---Set buffer size for formatted I/O
+
+The @env{GFORTRAN_BUFFER_SIZE_FORMATTED} environment variable
+specifies buffer size in bytes to be used for formatted output.
+The default value is 8192.
+
+@node GFORTRAN_BUFFER_SIZE_UNFORMATTED
+@section @env{GFORTRAN_BUFFER_SIZE_UNFORMATTED}---Set buffer size for unformatted I/O
+
+The @env{GFORTRAN_BUFFER_SIZE_UNFORMATTED} environment variable
+specifies buffer size in bytes to be used for unformatted output.
+The default value is 131072.
+
@c =====================================================================
@c PART II: LANGUAGE REFERENCE
@c =====================================================================
Index: libgfortran/io/unix.c
===================================================================
--- libgfortran/io/unix.c (Revision 273183)
+++ libgfortran/io/unix.c (Arbeitskopie)
@@ -193,7 +193,8 @@ fallback_access (const char *path, int mode)
/* Unix and internal stream I/O module */
-static const int BUFFER_SIZE = 8192;
+static const int BUFFER_SIZE_FORMATTED_DEFAULT = 8192;
+static const int BUFFER_SIZE_UNFORMATTED_DEFAULT = 128*1024;
typedef struct
{
@@ -205,6 +206,7 @@ typedef struct
gfc_offset file_length; /* Length of the file. */
char *buffer; /* Pointer to the buffer. */
+ ssize_t buffer_size; /* Length of the buffer. */
int fd; /* The POSIX file descriptor. */
int active; /* Length of valid bytes in the buffer */
@@ -592,9 +594,9 @@ buf_read (unix_stream *s, void *buf, ssize_t nbyte
&& raw_seek (s, new_logical, SEEK_SET) < 0)
return -1;
s->buffer_offset = s->physical_offset = new_logical;
- if (to_read <= BUFFER_SIZE/2)
+ if (to_read <= s->buffer_size/2)
{
- did_read = raw_read (s, s->buffer, BUFFER_SIZE);
+ did_read = raw_read (s, s->buffer, s->buffer_size);
if (likely (did_read >= 0))
{
s->physical_offset += did_read;
@@ -632,11 +634,11 @@ buf_write (unix_stream *s, const void *buf, ssize_
s->buffer_offset = s->logical_offset;
/* Does the data fit into the buffer? As a special case, if the
- buffer is empty and the request is bigger than BUFFER_SIZE/2,
+ buffer is empty and the request is bigger than s->buffer_size/2,
write directly. This avoids the case where the buffer would have
to be flushed at every write. */
- if (!(s->ndirty == 0 && nbyte > BUFFER_SIZE/2)
- && s->logical_offset + nbyte <= s->buffer_offset + BUFFER_SIZE
+ if (!(s->ndirty == 0 && nbyte > s->buffer_size/2)
+ && s->logical_offset + nbyte <= s->buffer_offset + s->buffer_size
&& s->buffer_offset <= s->logical_offset
&& s->buffer_offset + s->ndirty >= s->logical_offset)
{
@@ -651,7 +653,7 @@ buf_write (unix_stream *s, const void *buf, ssize_
the request is bigger than the buffer size, write directly
bypassing the buffer. */
buf_flush (s);
- if (nbyte <= BUFFER_SIZE/2)
+ if (nbyte <= s->buffer_size/2)
{
memcpy (s->buffer, buf, nbyte);
s->buffer_offset = s->logical_offset;
@@ -688,7 +690,7 @@ buf_write (unix_stream *s, const void *buf, ssize_
static int
buf_markeor (unix_stream *s)
{
- if (s->unbuffered || s->ndirty >= BUFFER_SIZE / 2)
+ if (s->unbuffered || s->ndirty >= s->buffer_size / 2)
return buf_flush (s);
return 0;
}
@@ -765,11 +767,32 @@ static const struct stream_vtable buf_vtable = {
};
static int
-buf_init (unix_stream *s)
+buf_init (unix_stream *s, bool unformatted)
{
s->st.vptr = &buf_vtable;
- s->buffer = xmalloc (BUFFER_SIZE);
+ /* Try to guess a good value for the buffer size. For formatted
+ I/O, we use so many CPU cycles converting the data that there is
+ more sense in converving memory and especially cache. For
+ unformatted, a bigger block can have a large impact in some
+ environments. */
+
+ if (unformatted)
+ {
+ if (options.buffer_size_unformatted > 0)
+ s->buffer_size = options.buffer_size_unformatted;
+ else
+ s->buffer_size = BUFFER_SIZE_UNFORMATTED_DEFAULT;
+ }
+ else
+ {
+ if (options.buffer_size_formatted > 0)
+ s->buffer_size = options.buffer_size_formatted;
+ else
+ s->buffer_size = BUFFER_SIZE_FORMATTED_DEFAULT;
+ }
+
+ s->buffer = xmalloc (s->buffer_size);
return 0;
}
@@ -1120,13 +1143,13 @@ fd_to_stream (int fd, bool unformatted)
(s->fd == STDIN_FILENO
|| s->fd == STDOUT_FILENO
|| s->fd == STDERR_FILENO)))
- buf_init (s);
+ buf_init (s, unformatted);
else
{
if (unformatted)
{
s->unbuffered = true;
- buf_init (s);
+ buf_init (s, unformatted);
}
else
raw_init (s);
Index: libgfortran/libgfortran.h
===================================================================
--- libgfortran/libgfortran.h (Revision 273183)
+++ libgfortran/libgfortran.h (Arbeitskopie)
@@ -540,6 +540,7 @@ typedef struct
int all_unbuffered, unbuffered_preconnected;
int fpe, backtrace;
+ int buffer_size_unformatted, buffer_size_formatted;
}
options_t;
Index: libgfortran/runtime/environ.c
===================================================================
--- libgfortran/runtime/environ.c (Revision 273183)
+++ libgfortran/runtime/environ.c (Arbeitskopie)
@@ -198,6 +198,14 @@ static variable variable_table[] = {
/* Print out a backtrace if possible on runtime error */
{ "GFORTRAN_ERROR_BACKTRACE", -1, &options.backtrace, init_boolean },
+ /* Buffer size for unformatted files. */
+ { "GFORTRAN_BUFFER_SIZE_UNFORMATTED", 0, &options.buffer_size_unformatted,
+ init_integer },
+
+ /* Buffer size for formatted files. */
+ { "GFORTRAN_BUFFER_SIZE_FORMATTED", 0, &options.buffer_size_formatted,
+ init_integer },
+
{ NULL, 0, NULL, NULL }
};
