view tests/pdiff @ 52060:8b7123c8947b

update: add a Rust fast-path when updating from null (and clean)

This case is easy to detect and we have all we need to generate a valid
working copy and dirstate entirely in Rust, which speeds things up
considerably:

On my machine updating a repo of ~300k files goes from 10.00s down to 4.2s,
all while consuming 50% less system time, with all caches hot.
Something to note is that further improvements will probably happen
with the upcoming `InnerRevlog` series that does smarter
mmap hanlding, especially for filelogs.

Here are benchmark numbers on a machine with only 4 cores (and no SMT enabled)

```
### data-env-vars.name               = heptapod-public-2024-03-25-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 5.328762  ~~~~~
rust: 1.308654  (-75.44%, -4.02)
### data-env-vars.name               = mercurial-devel-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 1.693271  ~~~~~
rust: 1.151053  (-32.02%, -0.54)
### data-env-vars.name               = mozilla-unified-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 38.901613  ~~~~~
rust: 11.637880 (-70.08%, -27.26)
### data-env-vars.name               = netbsd-xsrc-public-2024-09-19-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 4.793727  ~~~~~
rust: 1.505905  (-68.59%, -3.29)
```

#!/bin/sh

# Script to get stable diff output on any platform.
#
# Output of this script is almost equivalent to GNU diff with "-Nru".
#
# Use this script as "hg pdiff" via extdiff extension with preparation
# below in test scripts:
#
#   $ cat >> $HGRCPATH <<EOF
#   > [extdiff]
#   > pdiff = sh "$RUNTESTDIR/pdiff"
#   > EOF

filediff(){
    # USAGE: filediff file1 file2 [header]

    # compare with /dev/null if file doesn't exist (as "-N" option)
    file1="$1"
    if test ! -f "$file1"; then
        file1=/dev/null
    fi
    file2="$2"
    if test ! -f "$file2"; then
        file2=/dev/null
    fi

    if cmp -s "$file1" "$file2" 2> /dev/null; then
        # Return immediately, because comparison isn't needed. This
        # also avoids redundant message of diff like "No differences
        # encountered" (on Solaris)
        return
    fi

    if test -n "$3"; then
        # show header only in recursive case
        echo "$3"
    fi

    # replace "/dev/null" by corresponded filename (as "-N" option)
    diff -u "$file1" "$file2" |
    sed "s@^--- /dev/null\(.*\)\$@--- $1\1@" |
    sed "s@^\+\+\+ /dev/null\(.*\)\$@+++ $2\1@"

    # in this case, files differ from each other
    return 1
}

if test -d "$1" -o -d "$2"; then
    # ensure comparison in dictionary order
    (
    if test -d "$1"; then (cd "$1" && find . -type f); fi
    if test -d "$2"; then (cd "$2" && find . -type f); fi
    ) |
    sed 's@^\./@@g' | sort | uniq |
    while read file; do
        filediff "$1/$file" "$2/$file" "diff -Nru $1/$file $2/$file"
    done

    # TODO: there is no portable way for current while-read based
    # implementation to return 1 at detecting changes.
    #
    # On bash and dash, assignment to variable inside while-block
    # doesn't affect outside, because inside while-block is executed
    # in sub-shell. BTW, it affects outside while-block on ksh (as sh
    # on Solaris).
else
    filediff "$1" "$2"
fi