convert git-remote-annex to not include old pushed refs in new bundle
Rather than requiring the last listed bundle in the manifest include all refs that are in the remote, build up refs from each bundle listed in the manifest. This fixes a bug where pushing first a new branch foo from one clone, and then pushing a new branch bar from another clone, caused the second push to lose branch foo. Now the second push will add a new bundle, but the foo ref in the bundle from the first push will still be used. Pushing a deletion of a ref now has to delete all bundles and push a new bundle with only the remaining refs in it. In a "list for-push", it now has to unbundle all bundles, in order for a deletion repush to have available all objects. (And a non-deletion push can also rely on refs/namespaces/mine/ being up-to-date.) It would have been possible to fix the bug by only making it do that unbundling in "list for-push", without changing what's stored in the bundles. But I think I prefer to populate the bundles this way. For one thing, deleting a pushed ref now really deletes all data relating to it, rather than leaving it present in old bundles. For another, it's easier to explain since there is no special case for the last bundle. And, it will often result in smaller bundles. Note that further efficiency gains are possible with respect to what objects are included in an incremental bundle. Two XXX comments document how to reduce excess objects. It didn't seem worth implementing those optimisations in this proof of concept code. Sponsored-by: Brock Spratlen on Patreon
This commit is contained in:
parent
e5cfaf003c
commit
fc37243ffe
2 changed files with 104 additions and 96 deletions
|
@ -9,27 +9,30 @@ GITBUNDLE--sha256 is a git bundle.
|
|||
|
||||
An ordered list of bundle keys, one per line.
|
||||
|
||||
The last bundle in the list provides all refs that are currently stored in
|
||||
the repository. The bundles before it in the list can incrementally provide
|
||||
objects, but not refs.
|
||||
|
||||
# fetching
|
||||
|
||||
1. download GITMANIFEST for the uuid of the special remote
|
||||
2. download each listed GITBUNDLE object that we don't have
|
||||
3. `git bundle unpack` each bundle in order
|
||||
4. `git fetch` from the last bundle listed in the manifest
|
||||
3. `git fetch` from each new bundle in order
|
||||
(note that later bundles can update refs from the versions in previous
|
||||
bundles)
|
||||
|
||||
# pushing (incrementally)
|
||||
|
||||
1. create git bundle all refs that will be stored in the repository,
|
||||
This is how pushes are usually done.
|
||||
|
||||
1. create git bundle of all refs that are being pushed and have changed,
|
||||
and objects since the previously pushed refs
|
||||
2. hash to calculate GITBUNDLE key
|
||||
3. upload GITBUNDLE object
|
||||
4. download current manifest
|
||||
5. append GITBUNDLE key to manifest
|
||||
|
||||
# pushing (replacing incrementals with single bundle)
|
||||
# pushing (full)
|
||||
|
||||
Note that this can be used to replace incrementals with a single bundle for
|
||||
performance. It is also the only way to handle a push that deletes a
|
||||
previously pushed ref.
|
||||
|
||||
1. create git bundle containing all refs stored in the repository, and all
|
||||
objects
|
||||
|
|
181
git-remote-annex
181
git-remote-annex
|
@ -1,21 +1,9 @@
|
|||
#!/bin/sh
|
||||
|
||||
# BUG:
|
||||
# In one repo, make a new commit on master, and git push remote master
|
||||
# In a second repo, make a new branch foo, make a new commit in foo, and
|
||||
# git push remote foo
|
||||
# This second push overwrites the master branch pushed from the first repo
|
||||
# with an old version.
|
||||
# Need to fetch new revs before push or rethink including all revs in most
|
||||
# recent bundle.
|
||||
|
||||
TOPDIR=..
|
||||
|
||||
set -x
|
||||
|
||||
# remember the refs that were uploaded already
|
||||
git for-each-ref refs/namespaces/mine/ > .git/old-refs
|
||||
|
||||
rm -f .git/push-response
|
||||
|
||||
# Unfortunately, git bundle omits prerequisites that are omitted once,
|
||||
|
@ -26,12 +14,12 @@ rm -f .git/push-response
|
|||
check_prereq () {
|
||||
# So, if a sha is one of the other refs that will be included in the
|
||||
# bundle, it cannot be treated as a prerequisite.
|
||||
if git for-each-ref refs/namespaces/mine/ | grep -Pv "\t$2$" | awk '{print $1}' | grep -q "$1"; then
|
||||
if git show-ref $push_refs | grep -v " $2$" | awk '{print $1}' | grep -q "$1"; then
|
||||
echo "$2"
|
||||
else
|
||||
# And, if one of the other refs that will be included in the bundle
|
||||
# is an ancestor of the sha, it cannot be treated as a prerequisite.
|
||||
if [ -n "$(for x in $(git for-each-ref refs/namespaces/mine/ | grep -Pv "\t$2$" | awk '{print $1}'); do git log --oneline -n1 $x..$1; done)" ]; then
|
||||
if [ -n "$(for x in $(git show-ref $push_refs | grep -v " $2$" | awk '{print $1}'); do git log --oneline -n1 $x..$1; done)" ]; then
|
||||
echo "$2"
|
||||
else
|
||||
echo "$1..$2"
|
||||
|
@ -39,6 +27,12 @@ check_prereq () {
|
|||
fi
|
||||
}
|
||||
|
||||
addnewbundle () {
|
||||
sha1=$(sha1sum $TOPDIR/new.bundle | awk '{print $1}')
|
||||
mv $TOPDIR/new.bundle "$TOPDIR/$sha1.bundle"
|
||||
echo "$sha1.bundle" >> $TOPDIR/MANIFEST
|
||||
}
|
||||
|
||||
while read foo; do
|
||||
case "$foo" in
|
||||
capabilities)
|
||||
|
@ -48,19 +42,41 @@ while read foo; do
|
|||
;;
|
||||
list*)
|
||||
if [ -e "$TOPDIR/MANIFEST" ]; then
|
||||
# Only list the refs in the last bundle
|
||||
# listed in the manifest. Each push
|
||||
# includes all refs in its bundle.
|
||||
f=$(tail -n 1 $TOPDIR/MANIFEST)
|
||||
if [ -n "$f" ]; then
|
||||
# stash the listed refs for later
|
||||
# checking in push
|
||||
git bundle list-heads $TOPDIR/$f > .git/listed-refs
|
||||
# refs in the bundle may end up prefixed with refs/namespaces/mine/
|
||||
# when the intent is for the bundle to include a
|
||||
# ref with the name that comes after that.
|
||||
sed 's/refs\/namespaces\/mine\///' .git/listed-refs
|
||||
for f in $(cat $TOPDIR/MANIFEST); do
|
||||
git bundle list-heads $TOPDIR/$f >> .git/listed-refs-new
|
||||
if [ "$foo" = "list for-push" ]; then
|
||||
# Get all the objects from the bundle. This is done here so that
|
||||
# refs/namespaces/mine can be updated with what was listed,
|
||||
# and so what when a full repush needs to be done, everything
|
||||
# gets pushed.
|
||||
git bundle unbundle "$TOPDIR/$f" >/dev/null 2>&1
|
||||
fi
|
||||
done
|
||||
perl -e 'while (<>) { if (m/(.*) (.*)/) { $seen{$2}=$1 } }; foreach my $k (keys %seen) { print "$seen{$k} $k\n" }' < .git/listed-refs-new > .git/listed-refs
|
||||
rm -f .git/listed-refs-new
|
||||
|
||||
# when listing for a push, update refs/namespaces/mine to match what was
|
||||
# listed. This is necessary in order for a full repush to know what to push.
|
||||
if [ "$foo" = "list for-push" ]; then
|
||||
for r in $(git for-each-ref refs/namespaces/mine/ | awk '{print $3}'); do
|
||||
git update-ref -d "$r"
|
||||
done
|
||||
IFS="
|
||||
"
|
||||
for x in $(cat .git/listed-refs); do
|
||||
sha="$(echo "$x" | cut -d ' ' -f 1)"
|
||||
r="$(echo "$x" | cut -d ' ' -f 2)"
|
||||
git update-ref "$r" "$sha"
|
||||
done
|
||||
unset IFS
|
||||
fi
|
||||
|
||||
# respond to git with a list of refs
|
||||
sed 's/refs\/namespaces\/mine\///' .git/listed-refs
|
||||
# .git/listed-refs is later checked in push
|
||||
else
|
||||
rm -f .git/listed-refs
|
||||
touch .git/listed-refs
|
||||
fi
|
||||
echo
|
||||
;;
|
||||
|
@ -87,6 +103,9 @@ while read foo; do
|
|||
# bundle.
|
||||
mydstref=refs/namespaces/mine/"$dstref"
|
||||
if [ -z "$srcref" ]; then
|
||||
# To delete a ref, have to do a repush of
|
||||
# all remaining refs.
|
||||
REPUSH=1
|
||||
git update-ref -d "$mydstref"
|
||||
touch .git/push-response
|
||||
echo "ok $dstref" >> .git/push-response
|
||||
|
@ -104,11 +123,13 @@ while read foo; do
|
|||
touch .git/push-response
|
||||
echo "ok $dstref" >> .git/push-response
|
||||
git update-ref "$mydstref" "$srcref"
|
||||
push_refs="$mydstref $push_refs"
|
||||
fi
|
||||
else
|
||||
git update-ref "$mydstref" "$srcref"
|
||||
touch .git/push-response
|
||||
echo "ok $dstref" >> .git/push-response
|
||||
push_refs="$mydstref $push_refs"
|
||||
fi
|
||||
fi
|
||||
dopush=1
|
||||
|
@ -128,72 +149,56 @@ while read foo; do
|
|||
dofetch=""
|
||||
fi
|
||||
if [ "$dopush" ]; then
|
||||
# if some refs cannot be pushed, refuse to
|
||||
# push anything. It would be difficult to
|
||||
# push only some refs, because the bundle
|
||||
# needs to contain all refs, and some refs
|
||||
# on the remote may contain objects we have
|
||||
# not fetched yet.
|
||||
if egrep -q "^error" .git/push-response; then
|
||||
sed 's/^ok \(.*\)/error \1 unable to push this due to other pushed ref being non-fast-forward/' .git/push-response > .git/push-response.new
|
||||
mv .git/push-response.new .git/push-response
|
||||
if [ -z "$(git for-each-ref refs/namespaces/mine/)" ]; then
|
||||
# deleted all refs
|
||||
if [ -e "$TOPDIR/MANIFEST" ]; then
|
||||
for f in $(cat $TOPDIR/MANIFEST); do
|
||||
rm "$TOPDIR/$f"
|
||||
done
|
||||
rm $TOPDIR/MANIFEST
|
||||
touch $TOPDIR/MANIFEST
|
||||
fi
|
||||
else
|
||||
if [ -z "$(git for-each-ref refs/namespaces/mine/)" ]; then
|
||||
# deleted all refs
|
||||
if [ -e "$TOPDIR/MANIFEST" ]; then
|
||||
for f in $(cat $TOPDIR/MANIFEST); do
|
||||
rm "$TOPDIR/$f"
|
||||
done
|
||||
rm $TOPDIR/MANIFEST
|
||||
touch $TOPDIR/MANIFEST
|
||||
fi
|
||||
# set REPUSH=1 to do a full push
|
||||
# rather than incremental
|
||||
if [ "$REPUSH" ]; then
|
||||
rm $TOPDIR/MANIFEST
|
||||
rm $TOPDIR/*.bundle
|
||||
git for-each-ref refs/namespaces/mine/ | awk '{print $3}' | \
|
||||
git bundle create --quiet $TOPDIR/new.bundle --stdin
|
||||
addnewbundle
|
||||
else
|
||||
# set REPUSH=1 to do a full push
|
||||
# rather than incremental
|
||||
if [ "$REPUSH" ]; then
|
||||
rm $TOPDIR/MANIFEST
|
||||
rm $TOPDIR/*.bundle
|
||||
git for-each-ref refs/namespaces/mine/ | awk '{print $3}' | \
|
||||
git bundle create --quiet $TOPDIR/new.bundle --stdin
|
||||
else
|
||||
# incremental bundle
|
||||
IFS="
|
||||
"
|
||||
(for l in $(git for-each-ref refs/namespaces/mine/); do
|
||||
r=$(echo "$l" | awk '{print $3}')
|
||||
newsha=$(echo "$l" | awk '{print $1}')
|
||||
oldsha=$(grep -P "\t$r$" .git/old-refs | awk '{print $1}')
|
||||
if [ -n "$oldsha" ]; then
|
||||
# include changes from $oldsha to $r when there are some
|
||||
if [ -n "$(git log --oneline $oldsha..$r)" ]; then
|
||||
check_prereq "$oldsha" "$r"
|
||||
else
|
||||
if [ "$oldsha" = "$newsha" ]; then
|
||||
# $r is unchanged from last push, so include
|
||||
# the minimum data to make the bundle contain $r
|
||||
rparentsha=$(git log -n 2 "$r" --format='%H' | tail -n+2)
|
||||
if [ -n "$rparentsha" ]; then
|
||||
check_prereq "$rparentsha" "$r"
|
||||
else
|
||||
# $r has no parent so include it as is
|
||||
echo "$r"
|
||||
fi
|
||||
else
|
||||
# $oldsha is not a parent of $r, so
|
||||
# include $r and all its parents
|
||||
echo "$r"
|
||||
fi
|
||||
fi
|
||||
# incremental bundle
|
||||
for r in $push_refs; do
|
||||
newsha=$(git show-ref "$r" | awk '{print $1}')
|
||||
oldsha=$(grep " $r$" .git/listed-refs | awk '{print $1}')
|
||||
if [ -n "$oldsha" ]; then
|
||||
# include changes from $oldsha to $r when there are some
|
||||
if [ -n "$(git log --oneline $oldsha..$r)" ]; then
|
||||
check_prereq "$oldsha" "$r"
|
||||
else
|
||||
# no old version was pushed so include $r and all its parents
|
||||
echo "$r"
|
||||
fi
|
||||
done) \
|
||||
| git bundle create --quiet $TOPDIR/new.bundle --stdin
|
||||
if [ "$oldsha" = "$newsha" ]; then
|
||||
# $r is unchanged from last push, so no need to push it
|
||||
:
|
||||
else
|
||||
# $oldsha is not a parent of $r, so
|
||||
# include $r and all its parents
|
||||
# XXX (this could be improved by checking other refs that were pushed
|
||||
# and only including changes from them)
|
||||
echo "$r"
|
||||
fi
|
||||
fi
|
||||
else
|
||||
# no old version was pushed so include $r and all its parents
|
||||
# XXX (this could be improved by checking other refs that were pushed
|
||||
# and only including changes from them)
|
||||
echo "$r"
|
||||
fi
|
||||
done > .git/tobundle
|
||||
if [ -s ".git/tobundle" ]; then
|
||||
git bundle create --quiet $TOPDIR/new.bundle --stdin < ".git/tobundle"
|
||||
addnewbundle
|
||||
fi
|
||||
sha1=$(sha1sum $TOPDIR/new.bundle | awk '{print $1}')
|
||||
mv $TOPDIR/new.bundle "$TOPDIR/$sha1.bundle"
|
||||
echo "$sha1.bundle" >> $TOPDIR/MANIFEST
|
||||
fi
|
||||
fi
|
||||
cat .git/push-response
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue