From dae35bac98520c1402d29c60df11a2993889ec85 Mon Sep 17 00:00:00 2001
From: Joey Degges <jdegges@gmail.com>
Date: Mon, 1 Mar 2010 10:26:22 +0000
Subject: sort: inform the system about our input access pattern

Tell the system that we'll access input sequentially,
so that we more efficiently process uncached files in a few cases:

Reading from faster flash devices. E.g. 21 MB/s key:
  NORMAL     31.6s (26.8 user)
  SEQUENTIAL 27.7s
  WILLNEED   27.7s

Processing in parallel with readahead when using a small 1M buffer:
  NORMAL     24.7s (21.1 user)
  SEQUENTIAL 22.7s
  WILLNEED   25.6s

A small benefit when merging:
  NORMAL     25.0s (16.9 user)
  SEQUENTIAL 24.6s (16.6 user)
  WILLNEED   38.4s (13.1 user)

Note WILLNEED is presented above for comparison to show it
has some unwanted characteristics due to its synchronous
prepopulation of the cache. It has a good benefit on a
mechanical disk @ 80MB/s and a multicore system with
competing processes:
  NORMAL     14.73s
  SEQUENTIAL 10.95s
  WILLNEED   05.22s
However the scheduling differences causing this result
are probably best explicitly managed using `nice` etc.

* m4/jm-macros.m4 (coreutils_MACROS): check for posix_fadvise().
* src/sort.c (fadvise_input): A new function to apply
the POSIX_FADV_SEQUENTIAL hint to an input stream.
(stream_open): Call the above function for all input streams.
---
 m4/jm-macros.m4 |  1 +
 src/sort.c      | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/m4/jm-macros.m4 b/m4/jm-macros.m4
index 0ddbf2fdc..d4e20f9c1 100644
--- a/m4/jm-macros.m4
+++ b/m4/jm-macros.m4
@@ -64,6 +64,7 @@ AC_DEFUN([coreutils_MACROS],
   LIBS=$coreutils_saved_libs
 
   # Used by sort.c.
+  AC_CHECK_FUNCS_ONCE([posix_fadvise])
   AC_CHECK_FUNCS_ONCE([nl_langinfo])
 
   # Used by tail.c.
diff --git a/src/sort.c b/src/sort.c
index 39cb6d6f2..02b23510d 100644
--- a/src/sort.c
+++ b/src/sort.c
@@ -32,6 +32,7 @@
 #include "filevercmp.h"
 #include "hard-locale.h"
 #include "hash.h"
+#include "ignore-value.h"
 #include "md5.h"
 #include "physmem.h"
 #include "posixver.h"
@@ -794,6 +795,61 @@ create_temp_file (int *pfd, bool survive_fd_exhaustion)
   return node;
 }
 
+/* Predeclare an access pattern for input files.
+   Ignore any errors -- this is only advisory.
+
+   There are a few hints we could possibly provide,
+   and after careful testing it was decided that
+   specifying POSIX_FADV_SEQUENTIAL was not detrimental
+   to any cases.  On Linux 2.6.31, this option doubles
+   the size of read ahead performed and thus was seen to
+   benefit these cases:
+     Merging
+     Sorting with a smaller internal buffer
+     Reading from faster flash devices
+
+   In _addition_ one could also specify other hints...
+
+   POSIX_FADV_WILLNEED was tested, but Linux 2.6.31
+   at least uses that to _synchronously_ prepopulate the cache
+   with the specified range.  While sort does need to
+   read all of its input before outputting, a synchronous
+   read of the whole file up front precludes any processing
+   that sort could do in parallel with the system doing
+   read ahead of the data. This was seen to have negative effects
+   in a couple of cases:
+     Merging
+     Sorting with a smaller internal buffer
+   Note this option was seen to shorten the runtime for sort
+   on a multicore system with lots of RAM and other processes
+   competing for CPU.  It could be argued that more explicit
+   scheduling hints with `nice` et. al. are more appropriate
+   for this situation.
+
+   POSIX_FADV_NOREUSE is a possibility as it could lower
+   the priority of input data in the cache as sort will
+   only need to process it once.  However its functionality
+   has changed over Linux kernel versions and as of 2.6.31
+   it does nothing and thus we can't depend on what it might
+   do in future.
+
+   POSIX_FADV_DONTNEED is not appropriate for user specified
+   input files, but for temp files we do want to drop the
+   cache immediately after processing.  This is done implicitly
+   however when the files are unlinked.  */
+
+static void
+fadvise_input (FILE *fp)
+{
+#if HAVE_POSIX_FADVISE
+  if (fp)
+    {
+      int fd = fileno (fp);
+      ignore_value (posix_fadvise (fd, 0, 0, POSIX_FADV_SEQUENTIAL));
+    }
+#endif
+}
+
 /* Return a stream for FILE, opened with mode HOW.  A null FILE means
    standard output; HOW should be "w".  When opening for input, "-"
    means standard input.  To avoid confusion, do not return file
@@ -805,10 +861,18 @@ stream_open (const char *file, const char *how)
 {
   if (!file)
     return stdout;
-  if (STREQ (file, "-") && *how == 'r')
+  if (*how == 'r')
     {
-      have_read_stdin = true;
-      return stdin;
+      FILE *fp;
+      if (STREQ (file, "-"))
+        {
+          have_read_stdin = true;
+          fp = stdin;
+        }
+      else
+        fp = fopen (file, how);
+      fadvise_input (fp);
+      return fp;
     }
   return fopen (file, how);
 }
-- 
cgit v1.2.3-70-g09d2