bug#73784: [PATCH] cp: new option --nocache-source

[Masatake YAMATO]

When copying files, the system data cache are consumed, the system
data cache is utilized for both the source and destination files. In
scenarios such as creating backup files for old, unused files, it is
clear to users that these files will not be needed in the near
future. In such cases, retaining the data for these files in the cache
constitutes a waste of computer resources, especially when running
applications that require significant memory in the foreground.

With the new option, users will have the ability to request the
discarding of the system data cache, thereby avoiding the unwanted
swapping out of data from foreground processes.

I evaluated cache consumption using a script called
run.bash. Initially, run.bash creates many small files, each 8 KB in
size. It then copies these files using the cp command, both with and
without the specified option. Finally, it reports the difference in
the total size of the caches before and after the copying process.

run.bash:

    #!/bin/bash
    CP=$1
    shift

    [[ -e "$CP" ]] || {
        echo "no file found: $CP" 1>&2
        exit 1
    }

    N=8
    S=drop-src
    D=${HOME}/drop-dst

    mkdir -p $S
    mkdir -p $D

    start=
    end=
    print_cached()
    {
        grep ^Cached: /proc/meminfo
    }

    start()
    {
        start=$(print_cached | awk '{print $2}')
    }

    end()
    {
        end=$(print_cached | awk '{print $2}')
    }

    report()
    {
        echo -n "delta[$N:$1/$2]: "
        expr "$end" - "$start"
    }

    cleanup()
    {
        local i
        local j
        for ((i = 0; i < 10; i++)); do
            for ((j = 0; j < 10; j++)); do
                rm -f $S/F-${i}${j}*
                rm -f $D/F-${i}${j}*
            done
        done
        rm -f $S/F-*
        rm -f $D/F-*
    }

    prep()
    {
        local i
        for ((i = 0; i < 1024 * $N; i++ )); do
            if ! dd if=/dev/zero of=$S/F-$i bs=4096 count=2 \
                    status=none; then
                echo "failed in dd of=$S/F-$F" 1>&2
                exit 1
            fi
        done
        sync
    }

    run_cp()
    {
        start

        local i
        time for ((i = 0; i < 1024 * $N; i++ )); do
            if ! "${CP}" "$@" "$S/F-$i" "$D/F-$i"; then
                echo "failed in cp " "$@" "$S/F-$i" " $D/F-$i" 1>&2
                exit 1
            fi
        done

        end
        report "$1" $2
    }

    cleanup
    sync

    prep
    run_cp "$@"

running:

    ~/coreutils/nocache$  ./run.bash ../src/cp

    real        0m16.051s
    user        0m4.249s
    sys 0m12.437s
    delta[8:/]: 65548
    ~/coreutils/nocache$  ./run.bash ../src/cp --nocache-source

    real        0m17.109s
    user        0m4.492s
    sys 0m13.317s
    delta[8:--nocache-source/]: 620

--nocache-source option suppresses the consumption of the cache
massively.

* src/copy.h (struct cp_options): New member 'src_nocache'.
* src/copy.c (copy_reg): Call 'fdadvise (..., FADVISE_DONTNEED)'
if the new member is true.
* src/cp.c (NOCACHE_SOURCE_OPTION):
New enumerator.
(long_opts): Add the option.
(usage): Document the option.
(main): Support the option.
* doc/coreutils.texi (mv invocation): Document the option.
* NEWS: Mention the option.
---
 NEWS               |  3 +++
 doc/coreutils.texi |  4 ++++
 src/copy.c         |  2 ++
 src/copy.h         |  3 +++
 src/cp.c           | 13 +++++++++++++
 5 files changed, 25 insertions(+)

diff --git a/NEWS b/NEWS
index 8fea2657b..483c79e91 100644
--- a/NEWS
+++ b/NEWS
@@ -46,6 +46,9 @@ GNU coreutils NEWS                                    -*- 
outline -*-
   %<i>$ format, where '<i>' is an integer referencing a particular argument,
   thus allowing repetition or reordering of printf arguments.
 
+  cp now accepts --nocache-source option, which causes cp to request to discard
+  the system data cache for the source files.
+
 ** Improvements
 
   'head -c NUM', 'head -n NUM', 'nl -l NUM', 'nproc --ignore NUM',
diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index d5dd55092..e5bdc70ff 100644
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -10305,6 +10305,10 @@ skip existing files but not fail.
 If a file cannot be renamed because the destination file system differs,
 fail with a diagnostic instead of copying and then removing the file.
 
+@item --nocache-source
+@opindex --nocache-source
+Request to discard the system data cache for the source files.
+
 @item --exchange
 @opindex --exchange
 Exchange source and destination instead of renaming source to destination.
diff --git a/src/copy.c b/src/copy.c
index b1ac52c79..1c2ed367d 100644
--- a/src/copy.c
+++ b/src/copy.c
@@ -1705,6 +1705,8 @@ close_src_and_dst_desc:
       return_val = false;
     }
 close_src_desc:
+  if (x->src_nocache)
+    fdadvise (source_desc, 0, 0, FADVISE_DONTNEED);
   if (close (source_desc) < 0)
     {
       error (0, errno, _("failed to close %s"), quoteaf (src_name));
diff --git a/src/copy.h b/src/copy.h
index ab89c75fd..1042ecf7b 100644
--- a/src/copy.h
+++ b/src/copy.h
@@ -302,6 +302,9 @@ struct cp_options
 
   /* FIXME */
   Hash_table *src_info;
+
+  /* Request to discard cache for the source files. */
+  bool src_nocache;
 };
 
 bool copy (char const *src_name, char const *dst_name,
diff --git a/src/cp.c b/src/cp.c
index 127b5603f..10d66fd80 100644
--- a/src/cp.c
+++ b/src/cp.c
@@ -63,6 +63,8 @@ enum
   COPY_CONTENTS_OPTION,
   DEBUG_OPTION,
   NO_PRESERVE_ATTRIBUTES_OPTION,
+  NOCACHE_DESTINATION_OPTION,
+  NOCACHE_SOURCE_OPTION,
   PARENTS_OPTION,
   PRESERVE_ATTRIBUTES_OPTION,
   REFLINK_OPTION,
@@ -127,6 +129,8 @@ static struct option const long_opts[] =
   {"no-dereference", no_argument, nullptr, 'P'},
   {"no-preserve", required_argument, nullptr, NO_PRESERVE_ATTRIBUTES_OPTION},
   {"no-target-directory", no_argument, nullptr, 'T'},
+  {"nocache-destination", no_argument, nullptr, NOCACHE_DESTINATION_OPTION},
+  {"nocache-source", no_argument, nullptr, NOCACHE_SOURCE_OPTION},
   {"one-file-system", no_argument, nullptr, 'x'},
   {"parents", no_argument, nullptr, PARENTS_OPTION},
   {"path", no_argument, nullptr, PARENTS_OPTION},   /* Deprecated.  */
@@ -197,6 +201,9 @@ Copy SOURCE to DEST, or multiple SOURCE(s) to DIRECTORY.\n\
       fputs (_("\
   -n, --no-clobber             (deprecated) silently skip existing files.\n\
                                  See also --update\n\
+"), stdout);
+      fputs (_("\
+      --nocache-source         request to discard the cache for the source 
files.\n\
 "), stdout);
       fputs (_("\
   -P, --no-dereference         never follow symbolic links in SOURCE\n\
@@ -875,6 +882,8 @@ cp_option_init (struct cp_options *x)
 
   x->dest_info = nullptr;
   x->src_info = nullptr;
+
+  x->src_nocache = false;
 }
 
 /* Given a string, ARG, containing a comma-separated list of arguments
@@ -1088,6 +1097,10 @@ main (int argc, char **argv)
           decode_preserve_arg (optarg, &x, false);
           break;
 
+        case NOCACHE_SOURCE_OPTION:
+          x.src_nocache = true;
+          break;
+
         case PRESERVE_ATTRIBUTES_OPTION:
           if (optarg == nullptr)
             {
-- 
2.46.2