view Makefile @ 29830:92ac2baaea86

revlog: use an LRU cache for delta chain bases

Profiling using statprof revealed a hotspot during changegroup
application calculating delta chain bases on generaldelta repos.
Essentially, revlog._addrevision() was performing a lot of redundant
work tracing the delta chain as part of determining when the chain
distance was acceptable. This was most pronounced when adding
revisions to manifests, which can have delta chains thousands of
revisions long.

There was a delta chain base cache on revlogs before, but it only
captured a single revision. This was acceptable before generaldelta,
when _addrevision would build deltas from the previous revision and
thus we'd pretty much guarantee a cache hit when resolving the delta
chain base on a subsequent _addrevision call. However, it isn't
suitable for generaldelta because parent revisions aren't necessarily
the last processed revision.

This patch converts the delta chain base cache to an LRU dict cache.
The cache can hold multiple entries, so generaldelta repos have a
higher chance of getting a cache hit.

The impact of this change when processing changegroup additions is
significant. On a generaldelta conversion of the "mozilla-unified"
repo (which contains heads of the main Firefox repositories in
chronological order - this means there are lots of transitions between
heads in revlog order), this change has the following impact when
performing an `hg unbundle` of an uncompressed bundle of the repo:

before: 5:42 CPU time
after:  4:34 CPU time

Most of this time is saved when applying the changelog and manifest
revlogs:

before: 2:30 CPU time
after:  1:17 CPU time

That nearly a 50% reduction in CPU time applying changesets and
manifests!

Applying a gzipped bundle of the same repo (effectively simulating a
`hg clone` over HTTP) showed a similar speedup:

before: 5:53 CPU time
after:  4:46 CPU time

Wall time improvements were basically the same as CPU time.

I didn't measure explicitly, but it feels like most of the time
is saved when processing manifests. This makes sense, as large
manifests tend to have very long delta chains and thus benefit the
most from this cache.

So, this change effectively makes changegroup application (which is
used by `hg unbundle`, `hg clone`, `hg pull`, `hg unshelve`, and
various other commands) significantly faster when delta chains are
long (which can happen on repos with large numbers of files and thus
large manifests).

In theory, this change can result in more memory utilization. However,
we're caching a dict of ints. At most we have 200 ints + Python object
overhead per revlog. And, the cache is really only populated when
performing read-heavy operations, such as adding changegroups or
scanning an individual revlog. For memory bloat to be an issue, we'd
need to scan/read several revisions from several revlogs all while
having active references to several revlogs. I don't think there are
many operations that do this, so I don't think memory bloat from the
cache will be an issue.

# If you want to change PREFIX, do not just edit it below. The changed
# value wont get passed on to recursive make calls. You should instead
# override the variable on the command like:
#
# % make PREFIX=/opt/ install

export PREFIX=/usr/local
PYTHON=python
$(eval HGROOT := $(shell pwd))
HGPYTHONS ?= $(HGROOT)/build/pythons
PURE=
PYFILES:=$(shell find mercurial hgext doc -name '*.py')
DOCFILES=mercurial/help/*.txt
export LANGUAGE=C
export LC_ALL=C
TESTFLAGS ?= $(shell echo $$HGTESTFLAGS)

# Set this to e.g. "mingw32" to use a non-default compiler.
COMPILER=

COMPILERFLAG_tmp_ =
COMPILERFLAG_tmp_${COMPILER} ?= -c $(COMPILER)
COMPILERFLAG=${COMPILERFLAG_tmp_${COMPILER}}

help:
	@echo 'Commonly used make targets:'
	@echo '  all          - build program and documentation'
	@echo '  install      - install program and man pages to $$PREFIX ($(PREFIX))'
	@echo '  install-home - install with setup.py install --home=$$HOME ($(HOME))'
	@echo '  local        - build for inplace usage'
	@echo '  tests        - run all tests in the automatic test suite'
	@echo '  test-foo     - run only specified tests (e.g. test-merge1.t)'
	@echo '  dist         - run all tests and create a source tarball in dist/'
	@echo '  clean        - remove files created by other targets'
	@echo '                 (except installed files or dist source tarball)'
	@echo '  update-pot   - update i18n/hg.pot'
	@echo
	@echo 'Example for a system-wide installation under /usr/local:'
	@echo '  make all && su -c "make install" && hg version'
	@echo
	@echo 'Example for a local installation (usable in this directory):'
	@echo '  make local && ./hg version'

all: build doc

local:
	$(PYTHON) setup.py $(PURE) \
	  build_py -c -d . \
	  build_ext $(COMPILERFLAG) -i \
	  build_hgexe $(COMPILERFLAG) -i \
	  build_mo
	env HGRCPATH= $(PYTHON) hg version

build:
	$(PYTHON) setup.py $(PURE) build $(COMPILERFLAG)

wheel:
	FORCE_SETUPTOOLS=1 $(PYTHON) setup.py $(PURE) bdist_wheel $(COMPILERFLAG)

doc:
	$(MAKE) -C doc

cleanbutpackages:
	-$(PYTHON) setup.py clean --all # ignore errors from this command
	find contrib doc hgext hgext3rd i18n mercurial tests \
		\( -name '*.py[cdo]' -o -name '*.so' \) -exec rm -f '{}' ';'
	rm -f $(addprefix mercurial/,$(notdir $(wildcard mercurial/pure/[a-z]*.py)))
	rm -f MANIFEST MANIFEST.in hgext/__index__.py tests/*.err
	rm -f mercurial/__modulepolicy__.py
	if test -d .hg; then rm -f mercurial/__version__.py; fi
	rm -rf build mercurial/locale
	$(MAKE) -C doc clean
	$(MAKE) -C contrib/chg distclean

clean: cleanbutpackages
	rm -rf packages

install: install-bin install-doc

install-bin: build
	$(PYTHON) setup.py $(PURE) install --root="$(DESTDIR)/" --prefix="$(PREFIX)" --force

install-doc: doc
	cd doc && $(MAKE) $(MFLAGS) install

install-home: install-home-bin install-home-doc

install-home-bin: build
	$(PYTHON) setup.py $(PURE) install --home="$(HOME)" --prefix="" --force

install-home-doc: doc
	cd doc && $(MAKE) $(MFLAGS) PREFIX="$(HOME)" install

MANIFEST-doc:
	$(MAKE) -C doc MANIFEST

MANIFEST.in: MANIFEST-doc
	hg manifest | sed -e 's/^/include /' > MANIFEST.in
	echo include mercurial/__version__.py >> MANIFEST.in
	sed -e 's/^/include /' < doc/MANIFEST >> MANIFEST.in

dist:	tests dist-notests

dist-notests:	doc MANIFEST.in
	TAR_OPTIONS="--owner=root --group=root --mode=u+w,go-w,a+rX-s" $(PYTHON) setup.py -q sdist

check: tests

tests:
	cd tests && $(PYTHON) run-tests.py $(TESTFLAGS)

test-%:
	cd tests && $(PYTHON) run-tests.py $(TESTFLAGS) $@

testpy-%:
	@echo Looking for Python $* in $(HGPYTHONS)
	[ -e $(HGPYTHONS)/$*/bin/python ] || ( \
	cd $$(mktemp --directory --tmpdir) && \
        $(MAKE) -f $(HGROOT)/contrib/Makefile.python PYTHONVER=$* PREFIX=$(HGPYTHONS)/$* python )
	cd tests && $(HGPYTHONS)/$*/bin/python run-tests.py $(TESTFLAGS)

check-code:
	hg manifest | xargs python contrib/check-code.py

update-pot: i18n/hg.pot

i18n/hg.pot: $(PYFILES) $(DOCFILES) i18n/posplit i18n/hggettext
	$(PYTHON) i18n/hggettext mercurial/commands.py \
	  hgext/*.py hgext/*/__init__.py \
	  mercurial/fileset.py mercurial/revset.py \
	  mercurial/templatefilters.py mercurial/templatekw.py \
	  mercurial/templater.py \
	  mercurial/filemerge.py \
	  mercurial/hgweb/webcommands.py \
	  $(DOCFILES) > i18n/hg.pot.tmp
        # All strings marked for translation in Mercurial contain
        # ASCII characters only. But some files contain string
        # literals like this '\037\213'. xgettext thinks it has to
        # parse them even though they are not marked for translation.
        # Extracting with an explicit encoding of ISO-8859-1 will make
        # xgettext "parse" and ignore them.
	echo $(PYFILES) | xargs \
	  xgettext --package-name "Mercurial" \
	  --msgid-bugs-address "<[e-mail]>" \
	  --copyright-holder "Matt Mackall <[e-mail]> and others" \
	  --from-code ISO-8859-1 --join --sort-by-file --add-comments=i18n: \
	  -d hg -p i18n -o hg.pot.tmp
	$(PYTHON) i18n/posplit i18n/hg.pot.tmp
        # The target file is not created before the last step. So it never is in
        # an intermediate state.
	mv -f i18n/hg.pot.tmp i18n/hg.pot

%.po: i18n/hg.pot
        # work on a temporary copy for never having a half completed target
	cp $@ $@.tmp
	msgmerge --no-location --update $@.tmp $^
	mv -f $@.tmp $@

# Packaging targets

osx:
	/usr/bin/python2.7 setup.py install --optimize=1 \
	  --root=build/mercurial/ --prefix=/usr/local/ \
	  --install-lib=/Library/Python/2.7/site-packages/
	make -C doc all install DESTDIR="$(PWD)/build/mercurial/"
	mkdir -p $${OUTPUTDIR:-dist}
	HGVER=$$((cat build/mercurial/Library/Python/2.7/site-packages/mercurial/__version__.py; echo 'print(version)') | python) && \
	OSXVER=$$(sw_vers -productVersion | cut -d. -f1,2) && \
	pkgbuild --root build/mercurial/ \
	  --identifier org.mercurial-scm.mercurial \
	  --version "$${HGVER}" \
	  build/mercurial.pkg && \
	productbuild --distribution contrib/macosx/distribution.xml \
	  --package-path build/ \
	  --version "$${HGVER}" \
	  --resources contrib/macosx/ \
	  "$${OUTPUTDIR:-dist/}"/Mercurial-"$${HGVER}"-macosx"$${OSXVER}".pkg

deb:
	contrib/builddeb

ppa:
	contrib/builddeb --source-only

docker-debian-jessie:
	mkdir -p packages/debian-jessie
	contrib/dockerdeb debian jessie

contrib/docker/ubuntu-%: contrib/docker/ubuntu.template
	sed "s/__CODENAME__/$*/" $< > $@

docker-ubuntu-trusty: contrib/docker/ubuntu-trusty
	contrib/dockerdeb ubuntu trusty

docker-ubuntu-trusty-ppa: contrib/docker/ubuntu-trusty
	contrib/dockerdeb ubuntu trusty --source-only

docker-ubuntu-wily: contrib/docker/ubuntu-wily
	contrib/dockerdeb ubuntu wily

docker-ubuntu-wily-ppa: contrib/docker/ubuntu-wily
	contrib/dockerdeb ubuntu wily --source-only

docker-ubuntu-xenial: contrib/docker/ubuntu-xenial
	contrib/dockerdeb ubuntu xenial

docker-ubuntu-xenial-ppa: contrib/docker/ubuntu-xenial
	contrib/dockerdeb ubuntu xenial --source-only

fedora20:
	mkdir -p packages/fedora20
	contrib/buildrpm
	cp rpmbuild/RPMS/*/* packages/fedora20
	cp rpmbuild/SRPMS/* packages/fedora20
	rm -rf rpmbuild

docker-fedora20:
	mkdir -p packages/fedora20
	contrib/dockerrpm fedora20

fedora21:
	mkdir -p packages/fedora21
	contrib/buildrpm
	cp rpmbuild/RPMS/*/* packages/fedora21
	cp rpmbuild/SRPMS/* packages/fedora21
	rm -rf rpmbuild

docker-fedora21:
	mkdir -p packages/fedora21
	contrib/dockerrpm fedora21

centos5:
	mkdir -p packages/centos5
	contrib/buildrpm --withpython
	cp rpmbuild/RPMS/*/* packages/centos5
	cp rpmbuild/SRPMS/* packages/centos5

docker-centos5:
	mkdir -p packages/centos5
	contrib/dockerrpm centos5 --withpython

centos6:
	mkdir -p packages/centos6
	contrib/buildrpm
	cp rpmbuild/RPMS/*/* packages/centos6
	cp rpmbuild/SRPMS/* packages/centos6

docker-centos6:
	mkdir -p packages/centos6
	contrib/dockerrpm centos6

centos7:
	mkdir -p packages/centos7
	contrib/buildrpm
	cp rpmbuild/RPMS/*/* packages/centos7
	cp rpmbuild/SRPMS/* packages/centos7

docker-centos7:
	mkdir -p packages/centos7
	contrib/dockerrpm centos7

.PHONY: help all local build doc cleanbutpackages clean install install-bin \
	install-doc install-home install-home-bin install-home-doc \
	dist dist-notests check tests check-code update-pot \
	osx fedora20 docker-fedora20 fedora21 docker-fedora21 \
	centos5 docker-centos5 centos6 docker-centos6 centos7 docker-centos7