dirstate.walk: don't keep track of normalized files in parallel
Rev 2bb13f2b778c changed the semantics of the work list to store (normalized,
non-normalized) pairs. All the tuple creation and destruction hurts perf: on a
large repo on OS X, 'hg status' went from 3.62 seconds to 3.78.
It also is unnecessary in most cases:
- it is clearly unnecessary on case-sensitive filesystems.
- it is also unnecessary when filenames have been read off of disk rather than
being supplied by the user.
The only case where the non-normalized case is required at all is when the file
is unknown.
To eliminate most of the perf cost, keep trace of whether the directory needs
to be normalized at all with a boolean called 'alreadynormed'. Pay the cost of
directory normalization only when necessary.
For the above large repo, 'hg status' goes to 3.63 seconds.
$ hg init t
$ cd t
$ mkdir -p beans
$ for b in kidney navy turtle borlotti black pinto; do
> echo $b > beans/$b
> done
$ mkdir -p mammals/Procyonidae
$ for m in cacomistle coatimundi raccoon; do
> echo $m > mammals/Procyonidae/$m
> done
$ echo skunk > mammals/skunk
$ echo fennel > fennel
$ echo fenugreek > fenugreek
$ echo fiddlehead > fiddlehead
$ hg addremove
adding beans/black
adding beans/borlotti
adding beans/kidney
adding beans/navy
adding beans/pinto
adding beans/turtle
adding fennel
adding fenugreek
adding fiddlehead
adding mammals/Procyonidae/cacomistle
adding mammals/Procyonidae/coatimundi
adding mammals/Procyonidae/raccoon
adding mammals/skunk
$ hg commit -m "commit #0"
$ hg debugwalk
f beans/black beans/black
f beans/borlotti beans/borlotti
f beans/kidney beans/kidney
f beans/navy beans/navy
f beans/pinto beans/pinto
f beans/turtle beans/turtle
f fennel fennel
f fenugreek fenugreek
f fiddlehead fiddlehead
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
f mammals/skunk mammals/skunk
$ hg debugwalk -I.
f beans/black beans/black
f beans/borlotti beans/borlotti
f beans/kidney beans/kidney
f beans/navy beans/navy
f beans/pinto beans/pinto
f beans/turtle beans/turtle
f fennel fennel
f fenugreek fenugreek
f fiddlehead fiddlehead
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
f mammals/skunk mammals/skunk
$ cd mammals
$ hg debugwalk
f beans/black ../beans/black
f beans/borlotti ../beans/borlotti
f beans/kidney ../beans/kidney
f beans/navy ../beans/navy
f beans/pinto ../beans/pinto
f beans/turtle ../beans/turtle
f fennel ../fennel
f fenugreek ../fenugreek
f fiddlehead ../fiddlehead
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
f mammals/skunk skunk
$ hg debugwalk -X ../beans
f fennel ../fennel
f fenugreek ../fenugreek
f fiddlehead ../fiddlehead
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
f mammals/skunk skunk
$ hg debugwalk -I '*k'
f mammals/skunk skunk
$ hg debugwalk -I 'glob:*k'
f mammals/skunk skunk
$ hg debugwalk -I 'relglob:*k'
f beans/black ../beans/black
f fenugreek ../fenugreek
f mammals/skunk skunk
$ hg debugwalk -I 'relglob:*k' .
f mammals/skunk skunk
$ hg debugwalk -I 're:.*k$'
f beans/black ../beans/black
f fenugreek ../fenugreek
f mammals/skunk skunk
$ hg debugwalk -I 'relre:.*k$'
f beans/black ../beans/black
f fenugreek ../fenugreek
f mammals/skunk skunk
$ hg debugwalk -I 'path:beans'
f beans/black ../beans/black
f beans/borlotti ../beans/borlotti
f beans/kidney ../beans/kidney
f beans/navy ../beans/navy
f beans/pinto ../beans/pinto
f beans/turtle ../beans/turtle
$ hg debugwalk -I 'relpath:detour/../../beans'
f beans/black ../beans/black
f beans/borlotti ../beans/borlotti
f beans/kidney ../beans/kidney
f beans/navy ../beans/navy
f beans/pinto ../beans/pinto
f beans/turtle ../beans/turtle
$ hg debugwalk .
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
f mammals/skunk skunk
$ hg debugwalk -I.
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
f mammals/skunk skunk
$ hg debugwalk Procyonidae
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
$ cd Procyonidae
$ hg debugwalk .
f mammals/Procyonidae/cacomistle cacomistle
f mammals/Procyonidae/coatimundi coatimundi
f mammals/Procyonidae/raccoon raccoon
$ hg debugwalk ..
f mammals/Procyonidae/cacomistle cacomistle
f mammals/Procyonidae/coatimundi coatimundi
f mammals/Procyonidae/raccoon raccoon
f mammals/skunk ../skunk
$ cd ..
$ hg debugwalk ../beans
f beans/black ../beans/black
f beans/borlotti ../beans/borlotti
f beans/kidney ../beans/kidney
f beans/navy ../beans/navy
f beans/pinto ../beans/pinto
f beans/turtle ../beans/turtle
$ hg debugwalk .
f mammals/Procyonidae/cacomistle Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi Procyonidae/coatimundi
f mammals/Procyonidae/raccoon Procyonidae/raccoon
f mammals/skunk skunk
$ hg debugwalk .hg
abort: path 'mammals/.hg' is inside nested repo 'mammals' (glob)
[255]
$ hg debugwalk ../.hg
abort: path contains illegal component: .hg
[255]
$ cd ..
$ hg debugwalk -Ibeans
f beans/black beans/black
f beans/borlotti beans/borlotti
f beans/kidney beans/kidney
f beans/navy beans/navy
f beans/pinto beans/pinto
f beans/turtle beans/turtle
$ hg debugwalk -I '{*,{b,m}*/*}k'
f beans/black beans/black
f fenugreek fenugreek
f mammals/skunk mammals/skunk
$ hg debugwalk 'glob:mammals/../beans/b*'
f beans/black beans/black
f beans/borlotti beans/borlotti
$ hg debugwalk '-X*/Procyonidae' mammals
f mammals/skunk mammals/skunk
$ hg debugwalk path:mammals
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
f mammals/skunk mammals/skunk
$ hg debugwalk ..
abort: .. not under root '$TESTTMP/t' (glob)
[255]
$ hg debugwalk beans/../..
abort: beans/../.. not under root '$TESTTMP/t' (glob)
[255]
$ hg debugwalk .hg
abort: path contains illegal component: .hg
[255]
$ hg debugwalk beans/../.hg
abort: path contains illegal component: .hg
[255]
$ hg debugwalk beans/../.hg/data
abort: path contains illegal component: .hg/data (glob)
[255]
$ hg debugwalk beans/.hg
abort: path 'beans/.hg' is inside nested repo 'beans' (glob)
[255]
Test absolute paths:
$ hg debugwalk `pwd`/beans
f beans/black beans/black
f beans/borlotti beans/borlotti
f beans/kidney beans/kidney
f beans/navy beans/navy
f beans/pinto beans/pinto
f beans/turtle beans/turtle
$ hg debugwalk `pwd`/..
abort: $TESTTMP/t/.. not under root '$TESTTMP/t' (glob)
[255]
Test patterns:
$ hg debugwalk glob:\*
f fennel fennel
f fenugreek fenugreek
f fiddlehead fiddlehead
#if eol-in-paths
$ echo glob:glob > glob:glob
$ hg addremove
adding glob:glob
warning: filename contains ':', which is reserved on Windows: 'glob:glob'
$ hg debugwalk glob:\*
f fennel fennel
f fenugreek fenugreek
f fiddlehead fiddlehead
f glob:glob glob:glob
$ hg debugwalk glob:glob
glob: No such file or directory
$ hg debugwalk glob:glob:glob
f glob:glob glob:glob exact
$ hg debugwalk path:glob:glob
f glob:glob glob:glob exact
$ rm glob:glob
$ hg addremove
removing glob:glob
#endif
$ hg debugwalk 'glob:**e'
f beans/turtle beans/turtle
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
$ hg debugwalk 're:.*[kb]$'
f beans/black beans/black
f fenugreek fenugreek
f mammals/skunk mammals/skunk
$ hg debugwalk path:beans/black
f beans/black beans/black exact
$ hg debugwalk path:beans//black
f beans/black beans/black exact
$ hg debugwalk relglob:Procyonidae
$ hg debugwalk 'relglob:Procyonidae/**'
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
$ hg debugwalk 'relglob:Procyonidae/**' fennel
f fennel fennel exact
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
$ hg debugwalk beans 'glob:beans/*'
f beans/black beans/black
f beans/borlotti beans/borlotti
f beans/kidney beans/kidney
f beans/navy beans/navy
f beans/pinto beans/pinto
f beans/turtle beans/turtle
$ hg debugwalk 'glob:mamm**'
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
f mammals/skunk mammals/skunk
$ hg debugwalk 'glob:mamm**' fennel
f fennel fennel exact
f mammals/Procyonidae/cacomistle mammals/Procyonidae/cacomistle
f mammals/Procyonidae/coatimundi mammals/Procyonidae/coatimundi
f mammals/Procyonidae/raccoon mammals/Procyonidae/raccoon
f mammals/skunk mammals/skunk
$ hg debugwalk 'glob:j*'
$ hg debugwalk NOEXIST
NOEXIST: * (glob)
#if fifo
$ mkfifo fifo
$ hg debugwalk fifo
fifo: unsupported file type (type is fifo)
#endif
$ rm fenugreek
$ hg debugwalk fenugreek
f fenugreek fenugreek exact
$ hg rm fenugreek
$ hg debugwalk fenugreek
f fenugreek fenugreek exact
$ touch new
$ hg debugwalk new
f new new exact
$ mkdir ignored
$ touch ignored/file
$ echo '^ignored$' > .hgignore
$ hg debugwalk ignored
$ hg debugwalk ignored/file
f ignored/file ignored/file exact
Test listfile and listfile0
$ $PYTHON -c "file('listfile0', 'wb').write('fenugreek\0new\0')"
$ hg debugwalk -I 'listfile0:listfile0'
f fenugreek fenugreek
f new new
$ $PYTHON -c "file('listfile', 'wb').write('fenugreek\nnew\r\nmammals/skunk\n')"
$ hg debugwalk -I 'listfile:listfile'
f fenugreek fenugreek
f mammals/skunk mammals/skunk
f new new
$ cd ..
$ hg debugwalk -R t t/mammals/skunk
f mammals/skunk t/mammals/skunk exact
$ mkdir t2
$ cd t2
$ hg debugwalk -R ../t ../t/mammals/skunk
f mammals/skunk ../t/mammals/skunk exact
$ hg debugwalk --cwd ../t mammals/skunk
f mammals/skunk mammals/skunk exact
$ cd ..
Test split patterns on overflow
$ cd t
$ echo fennel > overflow.list
$ $PYTHON -c "for i in xrange(20000 / 100): print 'x' * 100" >> overflow.list
$ echo fenugreek >> overflow.list
$ hg debugwalk 'listfile:overflow.list' 2>&1 | grep -v '^xxx'
f fennel fennel exact
f fenugreek fenugreek exact
$ cd ..