cat: use larger buffer sizes to reduce read/write-syscall overhead

* src/cat.c (max): Remove definition.  Use MAX from system.h instead.
(compute_buffer_size): New function to compute the input and output
buffer sizes, which are now set at 8 times st_blksize with a maximum
of 32KiB. Previously the typical block sizes used were 1KiB for pipes
and 4KiB for files, and now will be 8KiB and 32KiB respectively.
(main): Use it.
This change can double throughput on modern systems.  For timings,
see http://article.gmane.org/gmane.comp.gnu.core-utils.bugs/16040
Suggestion from Tzvi Rotshtein.

diff --git a/THANKS b/THANKS
index e8c7b5cd11019d6b8980202acfcf2bd549c3c389..c4e900b12bc75cfa1d4b9c63d51c08630a77a294 100644 (file)
--- a/THANKS
+++ b/THANKS
@@ -553,6 +553,7 @@ Torbjorn Granlund                   tege@nada.kth.se
 Torbjorn Lindgren                   tl@funcom.no
 Torsten Landschoff                  torsten@pclab.ifg.uni-kiel.de
 Tristan Miller                      psychonaut@nothingisreal.com
+Tzvi Rotshtein                      tzvi.ro@gmail.com
 Ulrich Drepper                      drepper@gnu.org
 Ulrich Hermisson                    ulrich_hermisson@hotmail.com
 Urs Thuermann                       urs@isnogud.escape.de

diff --git a/src/cat.c b/src/cat.c
index 543e5cf138423f3212bb8dbe50094717b69dd6f2..04eb204d4beb090ffb752590758d93f91d622ea7 100644 (file)
--- a/src/cat.c
+++ b/src/cat.c
@@ -1,5 +1,5 @@
 /* cat -- concatenate files and print on the standard output.
-   Copyright (C) 88, 90, 91, 1995-2008 Free Software Foundation, Inc.
+   Copyright (C) 88, 90, 91, 1995-2009 Free Software Foundation, Inc.
 
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -48,10 +48,6 @@
   proper_name_utf8 ("Torbjorn Granlund", "Torbj\303\266rn Granlund"), \
   proper_name ("Richard M. Stallman")
 
-/* Undefine, to avoid warning about redefinition on some systems.  */
-#undef max
-#define max(h,i) ((h) > (i) ? (h) : (i))
-
 /* Name of input file.  May be "-".  */
 static char const *infile;
 
@@ -82,6 +78,12 @@ static char *line_num_end = line_buf + LINE_COUNTER_BUF_LEN - 3;
 /* Preserves the `cat' function's local `newlines' between invocations.  */
 static int newlines2 = 0;
 
+static inline size_t
+compute_buffer_size (struct stat st)
+{
+  return MIN (8 * ST_BLKSIZE (st), 32 * 1024);
+}
+
 void
 usage (int status)
 {
@@ -640,7 +642,7 @@ main (int argc, char **argv)
   if (fstat (STDOUT_FILENO, &stat_buf) < 0)
     error (EXIT_FAILURE, errno, _("standard output"));
 
-  outsize = ST_BLKSIZE (stat_buf);
+  outsize = compute_buffer_size (stat_buf);
   /* Input file can be output file for non-regular files.
      fstat on pipes returns S_IFSOCK on some systems, S_IFIFO
      on others, so the checking should not be done for those types,
@@ -704,7 +706,7 @@ main (int argc, char **argv)
          ok = false;
          goto contin;
        }
-      insize = ST_BLKSIZE (stat_buf);
+      insize = compute_buffer_size (stat_buf);
 
       /* Compare the device and i-node numbers of this input file with
         the corresponding values of the (output file associated with)
@@ -726,7 +728,7 @@ main (int argc, char **argv)
       if (! (number | show_ends | show_nonprinting
             | show_tabs | squeeze_blank))
        {
-         insize = max (insize, outsize);
+         insize = MAX (insize, outsize);
          inbuf = xmalloc (insize + page_size - 1);
 
          ok &= simple_cat (ptr_align (inbuf, page_size), insize);