##// END OF EJS Templates
perf: add command for measuring revlog chunk operations...
perf: add command for measuring revlog chunk operations Upcoming commits will teach revlogs to leverage the new compression engine API so that new compression formats can more easily be leveraged in revlogs. We want to be sure this refactoring doesn't regress performance. So this commit introduces "perfrevchunks" to explicitly test performance of reading, decompressing, and recompressing revlog chunks. Here is output when run on the mozilla-unified repo: $ hg perfrevlogchunks -c ! read ! wall 0.346603 comb 0.350000 user 0.340000 sys 0.010000 (best of 28) ! read w/ reused fd ! wall 0.337707 comb 0.340000 user 0.320000 sys 0.020000 (best of 30) ! read batch ! wall 0.013206 comb 0.020000 user 0.000000 sys 0.020000 (best of 221) ! read batch w/ reused fd ! wall 0.013259 comb 0.030000 user 0.010000 sys 0.020000 (best of 222) ! chunk ! wall 1.909939 comb 1.910000 user 1.900000 sys 0.010000 (best of 6) ! chunk batch ! wall 1.750677 comb 1.760000 user 1.740000 sys 0.020000 (best of 6) ! compress ! wall 5.668004 comb 5.670000 user 5.670000 sys 0.000000 (best of 3) $ hg perfrevlogchunks -m ! read ! wall 0.365834 comb 0.370000 user 0.350000 sys 0.020000 (best of 26) ! read w/ reused fd ! wall 0.350160 comb 0.350000 user 0.320000 sys 0.030000 (best of 28) ! read batch ! wall 0.024777 comb 0.020000 user 0.000000 sys 0.020000 (best of 119) ! read batch w/ reused fd ! wall 0.024895 comb 0.030000 user 0.000000 sys 0.030000 (best of 118) ! chunk ! wall 2.514061 comb 2.520000 user 2.480000 sys 0.040000 (best of 4) ! chunk batch ! wall 2.380788 comb 2.380000 user 2.360000 sys 0.020000 (best of 5) ! compress ! wall 9.815297 comb 9.820000 user 9.820000 sys 0.000000 (best of 3) We already see some interesting data, such as how much slower non-batched chunk reading is and that zlib compression appears to be >2x slower than decompression. I didn't have the data when I wrote this commit message, but I ran this on Mozilla's NFS-based Mercurial server and the time for reading with a reused file descriptor was faster. So I think it is worth testing both with and without file descriptor reuse so we can make informed decisions about recycling file descriptors.

File last commit:

r23172:e955549c default
r30451:94ca0e13 default
Show More
test-eol.t
545 lines | 11.8 KiB | text/troff | Tads3Lexer
Test EOL extension
$ cat >> $HGRCPATH <<EOF
> [diff]
> git = True
> EOF
Set up helpers
$ cat > switch-eol.py <<EOF
> import sys
> try:
> import os, msvcrt
> msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)
> msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
> except ImportError:
> pass
> (old, new) = sys.argv[1] == 'LF' and ('\n', '\r\n') or ('\r\n', '\n')
> print "%% switching encoding from %r to %r" % (old, new)
> for path in sys.argv[2:]:
> data = file(path, 'rb').read()
> data = data.replace(old, new)
> file(path, 'wb').write(data)
> EOF
$ seteol () {
> if [ $1 = "LF" ]; then
> EOL='\n'
> else
> EOL='\r\n'
> fi
> }
$ makerepo () {
> seteol $1
> echo "% setup $1 repository"
> hg init repo
> cd repo
> cat > .hgeol <<EOF
> [repository]
> native = $1
> [patterns]
> mixed.txt = BIN
> **.txt = native
> EOF
> printf "first${EOL}second${EOL}third${EOL}" > a.txt
> hg commit --addremove -m 'checkin'
> echo
> cd ..
> }
$ dotest () {
> seteol $1
> echo "% hg clone repo repo-$1"
> hg clone --noupdate repo repo-$1
> cd repo-$1
> cat > .hg/hgrc <<EOF
> [extensions]
> eol =
> [eol]
> native = $1
> EOF
> hg update
> echo '% a.txt'
> cat a.txt
> echo '% hg cat a.txt'
> hg cat a.txt
> printf "fourth${EOL}" >> a.txt
> echo '% a.txt'
> cat a.txt
> hg diff
> python ../switch-eol.py $1 a.txt
> echo '% hg diff only reports a single changed line:'
> hg diff
> echo "% reverting back to $1 format"
> hg revert a.txt
> cat a.txt
> printf "first\r\nsecond\n" > mixed.txt
> hg add mixed.txt
> echo "% hg commit of inconsistent .txt file marked as binary (should work)"
> hg commit -m 'binary file'
> echo "% hg commit of inconsistent .txt file marked as native (should fail)"
> printf "first\nsecond\r\nthird\nfourth\r\n" > a.txt
> hg commit -m 'inconsistent file'
> echo "% hg commit --config eol.only-consistent=False (should work)"
> hg commit --config eol.only-consistent=False -m 'inconsistent file'
> echo "% hg commit of binary .txt file marked as native (binary files always okay)"
> printf "first${EOL}\0${EOL}third${EOL}" > a.txt
> hg commit -m 'binary file'
> cd ..
> rm -r repo-$1
> }
$ makemixedrepo () {
> echo
> echo "# setup $1 repository"
> hg init mixed
> cd mixed
> printf "foo\r\nbar\r\nbaz\r\n" > win.txt
> printf "foo\nbar\nbaz\n" > unix.txt
> #printf "foo\r\nbar\nbaz\r\n" > mixed.txt
> hg commit --addremove -m 'created mixed files'
> echo "# setting repository-native EOLs to $1"
> cat > .hgeol <<EOF
> [repository]
> native = $1
> [patterns]
> **.txt = native
> EOF
> hg commit --addremove -m 'added .hgeol'
> cd ..
> }
$ testmixed () {
> echo
> echo "% hg clone mixed mixed-$1"
> hg clone mixed mixed-$1
> cd mixed-$1
> echo '% hg status (eol extension not yet activated)'
> hg status
> cat > .hg/hgrc <<EOF
> [extensions]
> eol =
> [eol]
> native = $1
> EOF
> echo '% hg status (eol activated)'
> hg status
> echo '% hg commit'
> hg commit -m 'synchronized EOLs'
> echo '% hg status'
> hg status
> cd ..
> rm -r mixed-$1
> }
Basic tests
$ makerepo LF
% setup LF repository
adding .hgeol
adding a.txt
$ dotest LF
% hg clone repo repo-LF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% a.txt
first
second
third
% hg cat a.txt
first
second
third
% a.txt
first
second
third
fourth
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first
second
third
+fourth
% switching encoding from '\n' to '\r\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first
second
third
+fourth
% reverting back to LF format
first
second
third
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt
% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
$ dotest CRLF
% hg clone repo repo-CRLF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% a.txt
first\r (esc)
second\r (esc)
third\r (esc)
% hg cat a.txt
first
second
third
% a.txt
first\r (esc)
second\r (esc)
third\r (esc)
fourth\r (esc)
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first
second
third
+fourth
% switching encoding from '\r\n' to '\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first
second
third
+fourth
% reverting back to CRLF format
first\r (esc)
second\r (esc)
third\r (esc)
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt
% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
$ rm -r repo
$ makerepo CRLF
% setup CRLF repository
adding .hgeol
adding a.txt
$ dotest LF
% hg clone repo repo-LF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% a.txt
first
second
third
% hg cat a.txt
first\r (esc)
second\r (esc)
third\r (esc)
% a.txt
first
second
third
fourth
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first\r (esc)
second\r (esc)
third\r (esc)
+fourth\r (esc)
% switching encoding from '\n' to '\r\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first\r (esc)
second\r (esc)
third\r (esc)
+fourth\r (esc)
% reverting back to LF format
first
second
third
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt
% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
$ dotest CRLF
% hg clone repo repo-CRLF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% a.txt
first\r (esc)
second\r (esc)
third\r (esc)
% hg cat a.txt
first\r (esc)
second\r (esc)
third\r (esc)
% a.txt
first\r (esc)
second\r (esc)
third\r (esc)
fourth\r (esc)
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first\r (esc)
second\r (esc)
third\r (esc)
+fourth\r (esc)
% switching encoding from '\r\n' to '\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
first\r (esc)
second\r (esc)
third\r (esc)
+fourth\r (esc)
% reverting back to CRLF format
first\r (esc)
second\r (esc)
third\r (esc)
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt
% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
$ rm -r repo
Mixed tests
$ makemixedrepo LF
# setup LF repository
adding unix.txt
adding win.txt
# setting repository-native EOLs to LF
adding .hgeol
$ testmixed LF
% hg clone mixed mixed-LF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M win.txt
% hg commit
% hg status
$ testmixed CRLF
% hg clone mixed mixed-CRLF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M win.txt
% hg commit
% hg status
$ rm -r mixed
$ makemixedrepo CRLF
# setup CRLF repository
adding unix.txt
adding win.txt
# setting repository-native EOLs to CRLF
adding .hgeol
$ testmixed LF
% hg clone mixed mixed-LF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M unix.txt
% hg commit
% hg status
$ testmixed CRLF
% hg clone mixed mixed-CRLF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M unix.txt
% hg commit
% hg status
$ rm -r mixed
$ echo '[extensions]' >> $HGRCPATH
$ echo 'eol =' >> $HGRCPATH
#if unix-permissions
Test issue2569 -- eol extension takes write lock on reading:
$ hg init repo
$ cd repo
$ touch .hgeol
$ hg status
? .hgeol
$ chmod -R -w .hg
$ sleep 1
$ touch .hgeol
$ hg status --traceback
? .hgeol
$ chmod -R u+w .hg
$ cd ..
#endif
Test cleverencode: and cleverdecode: aliases for win32text extension
$ cat <<EOF >> $HGRCPATH
> [encode]
> **.txt = cleverencode:
> [decode]
> **.txt = cleverdecode:
> EOF
$ hg init win32compat
$ cd win32compat
$ printf "foo\r\nbar\r\nbaz\r\n" > win.txt
$ printf "foo\nbar\nbaz\n" > unix.txt
$ hg add
adding unix.txt
adding win.txt
$ hg commit -m checkin
Check that both files have LF line-endings in the repository:
$ hg cat win.txt
foo
bar
baz
$ hg cat unix.txt
foo
bar
baz
Test handling of a broken .hgeol file:
$ touch .hgeol
$ hg add .hgeol
$ hg commit -m 'clean version'
$ echo "bad" > .hgeol
$ hg status
warning: ignoring .hgeol file due to parse error at .hgeol:1: bad
M .hgeol
$ hg revert .hgeol
warning: ignoring .hgeol file due to parse error at .hgeol:1: bad
$ hg status
? .hgeol.orig
Test eol.only-consistent can be specified in .hgeol
$ cd $TESTTMP
$ hg init only-consistent
$ cd only-consistent
$ printf "first\nsecond\r\n" > a.txt
$ hg add a.txt
$ cat > .hgeol << EOF
> [eol]
> only-consistent = True
> EOF
$ hg commit -m 'inconsistent'
abort: inconsistent newline style in a.txt
[255]
$ cat > .hgeol << EOF
> [eol]
> only-consistent = False
> EOF
$ hg commit -m 'consistent'
Test trailing newline
$ cat >> $HGRCPATH <<EOF
> [extensions]
> eol=
> EOF
setup repository
$ cd $TESTTMP
$ hg init trailing
$ cd trailing
$ cat > .hgeol <<EOF
> [patterns]
> **.txt = native
> [eol]
> fix-trailing-newline = False
> EOF
add text without trailing newline
$ printf "first\nsecond" > a.txt
$ hg commit --addremove -m 'checking in'
adding .hgeol
adding a.txt
$ rm a.txt
$ hg update -C -q
$ cat a.txt
first
second (no-eol)
$ cat > .hgeol <<EOF
> [patterns]
> **.txt = native
> [eol]
> fix-trailing-newline = True
> EOF
$ printf "third\nfourth" > a.txt
$ hg commit -m 'checking in with newline fix'
$ rm a.txt
$ hg update -C -q
$ cat a.txt
third
fourth
append a line without trailing newline
$ printf "fifth" >> a.txt
$ hg commit -m 'adding another line line'
$ rm a.txt
$ hg update -C -q
$ cat a.txt
third
fourth
fifth
amend of changesets with renamed/deleted files expose new code paths
$ hg mv a.txt b.txt
$ hg ci --amend -q
$ hg diff -c.
diff --git a/a.txt b/b.txt
rename from a.txt
rename to b.txt
--- a/a.txt
+++ b/b.txt
@@ -1,2 +1,3 @@
third
fourth
+fifth
$ cd ..