Mercurial > hg
view tests/test-diff-unified.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
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Tue, 11 Feb 2020 11:18:52 +0100 |
parents | 22f19da5736e |
children | df44bac9413d |
line wrap: on
line source
$ hg init repo $ cd repo $ cat > a <<EOF > c > c > a > a > b > a > a > c > c > EOF $ hg ci -Am adda adding a $ cat > a <<EOF > c > c > a > a > dd > a > a > c > c > EOF default context $ hg diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -2,7 +2,7 @@ c a a -b +dd a a c invalid --unified $ hg diff --nodates -U foo abort: diff context lines count must be an integer, not 'foo' [255] $ hg diff --nodates -U 2 diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -3,5 +3,5 @@ a a -b +dd a a $ hg --config diff.unified=2 diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -3,5 +3,5 @@ a a -b +dd a a $ hg diff --nodates -U 1 diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -4,3 +4,3 @@ a -b +dd a invalid diff.unified $ hg --config diff.unified=foo diff --nodates abort: diff context lines count must be an integer, not 'foo' [255] noprefix config and option $ hg --config diff.noprefix=True diff --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ hg diff --noprefix --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c noprefix config disabled in plain mode, but option still enabled $ HGPLAIN=1 hg --config diff.noprefix=True diff --nodates diff -r cf9f4ba66af2 a --- a/a +++ b/a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ HGPLAIN=1 hg diff --noprefix --nodates diff -r cf9f4ba66af2 a --- a +++ a @@ -2,7 +2,7 @@ c a a -b +dd a a c $ cd .. 0 lines of context hunk header matches gnu diff hunk header $ hg init diffzero $ cd diffzero $ cat > f1 << EOF > c2 > c4 > c5 > EOF $ hg commit -Am0 adding f1 $ cat > f2 << EOF > c1 > c2 > c3 > c4 > EOF $ mv f2 f1 $ hg diff -U0 --nodates diff -r 55d8ff78db23 f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ +c3 @@ -3,1 +4,0 @@ -c5 $ hg diff -U0 --nodates --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ +c3 @@ -3,1 +4,0 @@ -c5 $ hg diff -U0 --nodates -p diff -r 55d8ff78db23 f1 --- a/f1 +++ b/f1 @@ -0,0 +1,1 @@ +c1 @@ -1,0 +3,1 @@ c2 +c3 @@ -3,1 +4,0 @@ c4 -c5 $ echo a > f1 $ hg ci -m movef2 Test diff headers terminating with TAB when necessary (issue3357) Regular diff --nodates, file creation $ hg mv f1 'f 1' $ echo b > 'f 1' $ hg diff --nodates 'f 1' diff -r 7574207d0d15 f 1 --- /dev/null +++ b/f 1 @@ -0,0 +1,1 @@ +b Git diff, adding space $ hg diff --git diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b Git diff, adding extended headers $ hg diff --git --config experimental.extendedheader.index=7 --config experimental.extendedheader.similarity=True diff --git a/f1 b/f 1 similarity index 0% rename from f1 rename to f 1 index 7898192..6178079 100644 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ hg diff --git --config experimental.extendedheader.index=-1 invalid length for extendedheader.index: '-1' diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ hg diff --git --config experimental.extendedheader.index=whatever invalid value for extendedheader.index: 'whatever' diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b Git diff with noprefix $ hg --config diff.noprefix=True diff --git --nodates diff --git f1 f 1 rename from f1 rename to f 1 --- f1 +++ f 1 @@ -1,1 +1,1 @@ -a +b noprefix config disabled in plain mode, but option still enabled $ HGPLAIN=1 hg --config diff.noprefix=True diff --git --nodates diff --git a/f1 b/f 1 rename from f1 rename to f 1 --- a/f1 +++ b/f 1 @@ -1,1 +1,1 @@ -a +b $ HGPLAIN=1 hg diff --git --noprefix --nodates diff --git f1 f 1 rename from f1 rename to f 1 --- f1 +++ f 1 @@ -1,1 +1,1 @@ -a +b Regular diff --nodates, file deletion $ hg ci -m addspace $ hg mv 'f 1' f1 $ echo a > f1 $ hg diff --nodates 'f 1' diff -r ca50fe67c9c7 f 1 --- a/f 1 +++ /dev/null @@ -1,1 +0,0 @@ -b Git diff, removing space $ hg diff --git diff --git a/f 1 b/f1 rename from f 1 rename to f1 --- a/f 1 +++ b/f1 @@ -1,1 +1,1 @@ -b +a showfunc diff $ cat > f1 << EOF > int main() { > int a = 0; > int b = 1; > int c = 2; > int d = 3; > return a + b + c + d; > } > EOF $ hg commit -m addfunction $ cat > f1 << EOF > int main() { > int a = 0; > int b = 1; > int c = 2; > int e = 3; > return a + b + c + e; > } > EOF $ hg diff --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } $ hg diff --config diff.showfunc=True --git diff --git a/f1 b/f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int main() { int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } If [diff] git is set to true, but the user says --no-git, we should *not* get git diffs $ hg diff --nodates --config diff.git=1 --no-git diff -r f2c7c817fa55 f1 --- a/f1 +++ b/f1 @@ -2,6 +2,6 @@ int a = 0; int b = 1; int c = 2; - int d = 3; - return a + b + c + d; + int e = 3; + return a + b + c + e; } $ cd .. Long function names should be abbreviated, but multi-byte character shouldn't be broken up $ hg init longfunc $ cd longfunc >>> with open('a', 'wb') as f: ... f.write(b'a' * 39 + b'bb' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 b\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'\xc3\xa0' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 a with grave (single code point)\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'a\xcc\x80' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 0 a with grave (composition)\n') and None ... f.write(b' .\n' * 3) and None $ hg ci -qAm0 >>> with open('a', 'wb') as f: ... f.write(b'a' * 39 + b'bb' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 b\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'\xc3\xa0' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 a with grave (single code point)\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b'a' * 39 + b'a\xcc\x80' + b'\n') and None ... f.write(b' .\n' * 3) and None ... f.write(b' 1 a with grave (composition)\n') and None ... f.write(b' .\n' * 3) and None $ hg ci -m1 $ hg diff -c1 --nodates --show-function diff -r 3e92dd6fa812 -r a256341606cb a --- a/a +++ b/a @@ -2,7 +2,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaab . . . - 0 b + 1 b . . . @@ -10,7 +10,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xc3\xa0 (esc) . . . - 0 a with grave (single code point) + 1 a with grave (single code point) . . . @@ -18,7 +18,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xcc\x80 (esc) . . . - 0 a with grave (composition) + 1 a with grave (composition) . . . $ cd ..