[PATCH 2/3] Make filter-branch --glob-filter much faster by not calling 'cat'
From: Avery Pennarun <hidden>
Date: 2016-06-15 22:44:31
Subsystem:
the rest · Maintainer:
Linus Torvalds
The main loop of munge_blobs() had to fork-exec "cat" every time through the loop, even when a blob was already cached. Let's use the sh builtin 'read' instead for a huge speedup. cd git time git filter-branch --blob-filter 'tr a-z A-Z' HEAD~10..HEAD (original --blob-filter) real 3m58.569s user 0m22.900s sys 3m32.030s (with 'cat' calls removed) real 1m11.931s user 0m8.520s sys 1m2.900s (with 'cat' calls removed and blob cache already filled) real 0m19.660s user 0m3.930s sys 0m15.720s Signed-off-by: Avery Pennarun <redacted> --- git-filter-branch.sh | 18 +++++++++++------- 1 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/git-filter-branch.sh b/git-filter-branch.sh
index 980c431..37ac99d 100755
--- a/git-filter-branch.sh
+++ b/git-filter-branch.sh@@ -57,16 +57,18 @@ eval "$functions" munge_blobs() { while read mode sha1 stage path do - if ! test -r "$workdir/../blob-cache/$sha1" + if ! test -r "$cachedir/$sha1" then - new=`git cat-file blob $sha1 | - eval "$filter_blob" | - git hash-object -w --stdin` - printf $new >$workdir/../blob-cache/$sha1 + new=$(git cat-file blob $sha1 | + eval "$filter_blob" | + git hash-object -w --stdin) + printf $new >$cachedir/$sha1 + else + read new <"$cachedir/$sha1" fi printf "%s %s\t%s\n" \ "$mode" \ - $(cat "$workdir/../blob-cache/$sha1") \ + "$new" \ "$path" done }
@@ -108,6 +110,7 @@ USAGE="[--env-filter <command>] [--tree-filter <command>] \ [--index-filter <command>] [--parent-filter <command>] \ [--msg-filter <command>] [--commit-filter <command>] \ [--tag-name-filter <command>] [--subdirectory-filter <directory>] \ +[--blob-filter <command>] \ [--original <namespace>] [-d <directory>] [-f | --force] \ [<rev-list options>...]"
@@ -249,7 +252,8 @@ ret=0 mkdir ../map || die "Could not create map/ directory" # cache rewritten blobs for blob filter -mkdir ../blob-cache || die "Could not create blob-cache/ directory" +cachedir="$workdir/../blob-cache" +mkdir "$cachedir" || die "Could not create blob-cache/ directory" case "$filter_subdir" in "")
--
1.5.4.3