view tests/test-eol-patch.t @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

Test EOL patching

  $ cat >> $HGRCPATH <<EOF
  > [diff]
  > git = 1
  > EOF

Set up helpers

  $ seteol () {
  >     if [ $1 = "LF" ]; then
  >         EOL='\n'
  >     else
  >         EOL='\r\n'
  >     fi
  > }

  $ makerepo () {
  >     seteol $1
  >     echo
  >     echo "# ==== setup $1 repository ===="
  >     echo '% hg init'
  >     hg init repo
  >     cd repo
  >     cat > .hgeol <<EOF
  > [repository]
  > native = $1
  > [patterns]
  > unix.txt = LF
  > win.txt = CRLF
  > **.txt = native
  > EOF
  >     printf "first\r\nsecond\r\nthird\r\n" > win.txt
  >     printf "first\nsecond\nthird\n" > unix.txt
  >     printf "first${EOL}second${EOL}third${EOL}" > native.txt
  >     hg commit --addremove -m 'checkin'
  >     cd ..
  > }

  $ dotest () {
  >     seteol $1
  >     echo
  >     echo "% hg clone repo repo-$1"
  >     hg clone --noupdate repo repo-$1
  >     cd repo-$1
  >     cat > .hg/hgrc <<EOF
  > [extensions]
  > eol =
  > [eol]
  > native = $1
  > EOF
  >     hg update
  >     echo '% native.txt'
  >     cat native.txt
  >     echo '% unix.txt'
  >     cat unix.txt
  >     echo '% win.txt'
  >     cat win.txt
  >     printf "first${EOL}third${EOL}" > native.txt
  >     printf "first\r\nthird\r\n" > win.txt
  >     printf "first\nthird\n" > unix.txt
  >     echo '% hg diff'
  >     hg diff > p
  >     cat p
  >     echo '% hg revert'
  >     hg revert --all
  >     echo '% hg import'
  >     hg import -m 'patch' p
  >     echo '% native.txt'
  >     cat native.txt
  >     echo '% unix.txt'
  >     cat unix.txt
  >     echo '% win.txt'
  >     cat win.txt
  >     echo '% hg diff -c tip'
  >     hg diff -c tip
  >     cd ..
  >     rm -r repo-$1
  > }

Run tests

  $ makerepo LF
  
  # ==== setup LF repository ====
  % hg init
  adding .hgeol
  adding native.txt
  adding unix.txt
  adding win.txt
  $ dotest LF
  
  % hg clone repo repo-LF
  4 files updated, 0 files merged, 0 files removed, 0 files unresolved
  % native.txt
  first
  second
  third
  % unix.txt
  first
  second
  third
  % win.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % hg diff
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  % hg revert
  reverting native.txt
  reverting unix.txt
  reverting win.txt
  % hg import
  applying p
  % native.txt
  first
  third
  % unix.txt
  first
  third
  % win.txt
  first\r (esc)
  third\r (esc)
  % hg diff -c tip
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  $ dotest CRLF
  
  % hg clone repo repo-CRLF
  4 files updated, 0 files merged, 0 files removed, 0 files unresolved
  % native.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % unix.txt
  first
  second
  third
  % win.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % hg diff
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  % hg revert
  reverting native.txt
  reverting unix.txt
  reverting win.txt
  % hg import
  applying p
  % native.txt
  first\r (esc)
  third\r (esc)
  % unix.txt
  first
  third
  % win.txt
  first\r (esc)
  third\r (esc)
  % hg diff -c tip
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  $ rm -r repo
  $ makerepo CRLF
  
  # ==== setup CRLF repository ====
  % hg init
  adding .hgeol
  adding native.txt
  adding unix.txt
  adding win.txt
  $ dotest LF
  
  % hg clone repo repo-LF
  4 files updated, 0 files merged, 0 files removed, 0 files unresolved
  % native.txt
  first
  second
  third
  % unix.txt
  first
  second
  third
  % win.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % hg diff
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  % hg revert
  reverting native.txt
  reverting unix.txt
  reverting win.txt
  % hg import
  applying p
  % native.txt
  first
  third
  % unix.txt
  first
  third
  % win.txt
  first\r (esc)
  third\r (esc)
  % hg diff -c tip
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  $ dotest CRLF
  
  % hg clone repo repo-CRLF
  4 files updated, 0 files merged, 0 files removed, 0 files unresolved
  % native.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % unix.txt
  first
  second
  third
  % win.txt
  first\r (esc)
  second\r (esc)
  third\r (esc)
  % hg diff
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  % hg revert
  reverting native.txt
  reverting unix.txt
  reverting win.txt
  % hg import
  applying p
  % native.txt
  first\r (esc)
  third\r (esc)
  % unix.txt
  first
  third
  % win.txt
  first\r (esc)
  third\r (esc)
  % hg diff -c tip
  diff --git a/native.txt b/native.txt
  --- a/native.txt
  +++ b/native.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  diff --git a/unix.txt b/unix.txt
  --- a/unix.txt
  +++ b/unix.txt
  @@ -1,3 +1,2 @@
   first
  -second
   third
  diff --git a/win.txt b/win.txt
  --- a/win.txt
  +++ b/win.txt
  @@ -1,3 +1,2 @@
   first\r (esc)
  -second\r (esc)
   third\r (esc)
  $ rm -r repo