[Emacs-diffs] trunk r114578: Do not allocate huge temporary memory areas and objects while encoding

[Dmitry Antipov]

------------------------------------------------------------
revno: 114578
revision-id: address@hidden
parent: address@hidden
committer: Dmitry Antipov <address@hidden>
branch nick: trunk
timestamp: Tue 2013-10-08 10:40:09 +0400
message:
  Do not allocate huge temporary memory areas and objects while encoding
  for file I/O, thus reducing an enormous memory usage for large buffers.
  See http://lists.gnu.org/archive/html/emacs-devel/2013-10/msg00180.html.
  * coding.h (struct coding_system): New member raw_destination.
  * coding.c (setup_coding_system): Initialize it to zero.
  (encode_coding_object): If raw_destination is set, do not create
  dst_object.  Add comment.
  * fileio.c (toplevel): New constant E_WRITE_MAX.
  (e_write): Do not encode more than E_WRITE_MAX characters per one loop
  iteration.  Use raw_destination if E_WRITE_MAX characters is encoded.
modified:
  src/ChangeLog                  changelog-20091113204419-o5vbwnq5f7feedwu-1438
  src/coding.c                   coding.c-20091113204419-o5vbwnq5f7feedwu-1077
  src/coding.h                   coding.h-20091113204419-o5vbwnq5f7feedwu-1078
  src/fileio.c                   fileio.c-20091113204419-o5vbwnq5f7feedwu-210

=== modified file 'src/ChangeLog'
--- a/src/ChangeLog     2013-10-08 06:12:40 +0000
+++ b/src/ChangeLog     2013-10-08 06:40:09 +0000
@@ -1,3 +1,16 @@
+2013-10-08  Dmitry Antipov  <address@hidden>
+
+       Do not allocate huge temporary memory areas and objects while encoding
+       for file I/O, thus reducing an enormous memory usage for large buffers.
+       See http://lists.gnu.org/archive/html/emacs-devel/2013-10/msg00180.html.
+       * coding.h (struct coding_system): New member raw_destination.
+       * coding.c (setup_coding_system): Initialize it to zero.
+       (encode_coding_object): If raw_destination is set, do not create
+       dst_object.  Add comment.
+       * fileio.c (toplevel): New constant E_WRITE_MAX.
+       (e_write): Do not encode more than E_WRITE_MAX characters per one loop
+       iteration.  Use raw_destination if E_WRITE_MAX characters is encoded.
+
 2013-10-08  Jan Djärv  <address@hidden>
 
        * nsterm.m (windowDidExitFullScreen:):

=== modified file 'src/coding.c'
--- a/src/coding.c      2013-08-26 05:20:59 +0000
+++ b/src/coding.c      2013-10-08 06:40:09 +0000
@@ -5761,6 +5761,7 @@
   coding->safe_charsets = SDATA (val);
   coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs));
   coding->carryover_bytes = 0;
+  coding->raw_destination = 0;
 
   coding_type = CODING_ATTR_TYPE (attrs);
   if (EQ (coding_type, Qundecided))
@@ -8352,6 +8353,11 @@
     {
       if (BUFFERP (coding->dst_object))
        coding->dst_object = Fbuffer_string ();
+      else if (coding->raw_destination)
+       /* This is used to avoid creating huge Lisp string.
+          NOTE: caller who sets `raw_destination' is also
+          responsible for freeing `destination' buffer.  */
+       coding->dst_object = Qnil;
       else
        {
          coding->dst_object

=== modified file 'src/coding.h'
--- a/src/coding.h      2013-08-30 12:17:44 +0000
+++ b/src/coding.h      2013-10-08 06:40:09 +0000
@@ -512,6 +512,10 @@
      `charbuf', but at `src_object'.  */
   unsigned chars_at_source : 1;
 
+  /* Nonzero if the result of conversion is in `destination'
+     buffer rather than in `dst_object'.  */
+  unsigned raw_destination : 1;
+
   /* Set to 1 if charbuf contains an annotation.  */
   unsigned annotated : 1;
 

=== modified file 'src/fileio.c'
--- a/src/fileio.c      2013-09-11 05:03:23 +0000
+++ b/src/fileio.c      2013-10-08 06:40:09 +0000
@@ -5263,6 +5263,10 @@
   return 1;
 }
 
+/* Maximum number of characters that the next
+   function encodes per one loop iteration.  */
+
+enum { E_WRITE_MAX = 8 * 1024 * 1024 };
 
 /* Write text in the range START and END into descriptor DESC,
    encoding them with coding system CODING.  If STRING is nil, START
@@ -5289,9 +5293,16 @@
          coding->src_multibyte = SCHARS (string) < SBYTES (string);
          if (CODING_REQUIRE_ENCODING (coding))
            {
-             encode_coding_object (coding, string,
-                                   start, string_char_to_byte (string, start),
-                                   end, string_char_to_byte (string, end), Qt);
+             ptrdiff_t nchars = min (end - start, E_WRITE_MAX);
+
+             /* Avoid creating huge Lisp string in encode_coding_object.  */
+             if (nchars == E_WRITE_MAX)
+               coding->raw_destination = 1;
+
+             encode_coding_object
+               (coding, string, start, string_char_to_byte (string, start),
+                start + nchars, string_char_to_byte (string, start + nchars),
+                Qt);
            }
          else
            {
@@ -5308,8 +5319,15 @@
          coding->src_multibyte = (end - start) < (end_byte - start_byte);
          if (CODING_REQUIRE_ENCODING (coding))
            {
-             encode_coding_object (coding, Fcurrent_buffer (),
-                                   start, start_byte, end, end_byte, Qt);
+             ptrdiff_t nchars = min (end - start, E_WRITE_MAX);
+
+             /* Likewise.  */
+             if (nchars == E_WRITE_MAX)
+               coding->raw_destination = 1;
+
+             encode_coding_object
+               (coding, Fcurrent_buffer (), start, start_byte,
+                start + nchars, CHAR_TO_BYTE (start + nchars), Qt);
            }
          else
            {
@@ -5330,11 +5348,19 @@
 
       if (coding->produced > 0)
        {
-         char *buf = (STRINGP (coding->dst_object)
-                      ? SSDATA (coding->dst_object)
-                      : (char *) BYTE_POS_ADDR (coding->dst_pos_byte));
+         char *buf = (coding->raw_destination ? (char *) coding->destination
+                      : (STRINGP (coding->dst_object)
+                         ? SSDATA (coding->dst_object)
+                         : (char *) BYTE_POS_ADDR (coding->dst_pos_byte)));
          coding->produced -= emacs_write_sig (desc, buf, coding->produced);
 
+         if (coding->raw_destination)
+           {
+             /* We're responsible for freeing this, see
+                encode_coding_object to check why.  */
+             xfree (coding->destination);
+             coding->raw_destination = 0;
+           }
          if (coding->produced)
            return 0;
        }