bdiff: improve worst case behavior by 100x. on 5.8MB (244.000 lines) text file with similar lines, hash before this change made diff against empty file take 75 seconds. this change improves performance to 0.6 seconds. result is that clone of smallish repo (137MB) with some files like this takes 1 minute instead of 10 minutes. common case of diff is 10% slower now, probably because of worse cache locality. but diff does not affect overall performance in common case (less than 1% of runtime is in diff when it is working ok), so this tradeoff looks good.

#!/bin/sh
#
# Corrupt an hg repo with two pulls.
#

# create one repo with a long history
hg init source1
cd source1
touch foo
hg add foo
for i in 1 2 3 4 5 6 7 8 9 10; do
    echo $i >> foo
    hg ci -m $i
done
cd ..

# create a third repo to pull both other repos into it
hg init version2
hg -R version2 pull source1 &
sleep 1

hg clone --pull -U version2 corrupted
wait
hg -R corrupted verify
hg -R version2 verify