From: Jeff Hostetler <jeffhost@xxxxxxxxxxxxx>
Created t/perf/repos/many-files.sh to generate large, but
artificial repositories.
Created t/perf/inflate-repo.sh to alter an EXISTING repo
to have a set of large commits. This can be used to create
a branch with 1M+ files in repositories like git.git or
linux.git, but with more realistic content. It does this
by making multiple copies of the entire worktree in a series
of sub-directories.
The branch name and ballast structure created by both scripts
match, so either script can be used to generate very large
test repositories for the following perf test.
Created t/perf/p0006-read-tree-checkout.sh to measure
performance on various read-tree, checkout, and update-index
operations. This test can run using either normal repos or
ones from the above scripts.
Signed-off-by: Jeff Hostetler <jeffhost@xxxxxxxxxxxxx>
---
t/perf/p0006-read-tree-checkout.sh | 67 ++++++++++++++++++++++
t/perf/repos/.gitignore | 1 +
t/perf/repos/inflate-repo.sh | 86 +++++++++++++++++++++++++++++
t/perf/repos/many-files.sh | 110 +++++++++++++++++++++++++++++++++++++
4 files changed, 264 insertions(+)
create mode 100755 t/perf/p0006-read-tree-checkout.sh
create mode 100644 t/perf/repos/.gitignore
create mode 100755 t/perf/repos/inflate-repo.sh
create mode 100755 t/perf/repos/many-files.sh
diff --git a/t/perf/p0006-read-tree-checkout.sh b/t/perf/p0006-read-tree-checkout.sh
new file mode 100755
index 0000000..78cc23f
--- /dev/null
+++ b/t/perf/p0006-read-tree-checkout.sh
@@ -0,0 +1,67 @@
+#!/bin/sh
+#
+# This test measures the performance of various read-tree
+# and checkout operations. It is primarily interested in
+# the algorithmic costs of index operations and recursive
+# tree traversal -- and NOT disk I/O on thousands of files.
+
+test_description="Tests performance of read-tree"
+
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+# If the test repo was generated by ./repos/many-files.sh
+# then we know something about the data shape and branches,
+# so we can isolate testing to the ballast-related commits
+# and setup sparse-checkout so we don't have to populate
+# the ballast files and directories.
+#
+# Otherwise, we make some general assumptions about the
+# repo and consider the entire history of the current
+# branch to be the ballast.
+
+test_expect_success "setup repo" '
+ if git rev-parse --verify refs/heads/p0006-ballast^{commit}
+ then
+ echo Assuming synthetic repo from many-files.sh
+ git branch br_base master
+ git branch br_ballast p0006-ballast^
+ git branch br_ballast_alias p0006-ballast^
+ git branch br_ballast_plus_1 p0006-ballast
+ git config --local core.sparsecheckout 1
+ cat >.git/info/sparse-checkout <<-EOF
+ /*
+ !ballast/*
+ EOF
+ else
+ echo Assuming non-synthetic repo...
+ git branch br_base $(git rev-list HEAD | tail -n 1)
+ git branch br_ballast HEAD^ || error "no ancestor commit from current head"
+ git branch br_ballast_alias HEAD^
+ git branch br_ballast_plus_1 HEAD
+ fi &&
+ git checkout -q br_ballast &&
+ nr_files=$(git ls-files | wc -l)
+'
+
+test_perf "read-tree br_base br_ballast ($nr_files)" '
+ git read-tree -m br_base br_ballast -n
+'
+
+test_perf "switch between br_base br_ballast ($nr_files)" '
+ git checkout -q br_base &&
+ git checkout -q br_ballast
+'
+
+test_perf "switch between br_ballast br_ballast_plus_1 ($nr_files)" '
+ git checkout -q br_ballast_plus_1 &&
+ git checkout -q br_ballast
+'
+
+test_perf "switch between aliases ($nr_files)" '
+ git checkout -q br_ballast_alias &&
+ git checkout -q br_ballast
+'
+
+test_done
diff --git a/t/perf/repos/.gitignore b/t/perf/repos/.gitignore
new file mode 100644
index 0000000..72e3dc3
--- /dev/null
+++ b/t/perf/repos/.gitignore
@@ -0,0 +1 @@
+gen-*/
diff --git a/t/perf/repos/inflate-repo.sh b/t/perf/repos/inflate-repo.sh
new file mode 100755
index 0000000..64f5d7a
--- /dev/null
+++ b/t/perf/repos/inflate-repo.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+# Inflate the size of an EXISTING repo.
+#
+# This script should be run inside the worktree of a TEST repo.
+# It will use the contents of the current HEAD to generate a
+# commit containing copies of the current worktree such that the
+# total size of the commit has at least <target_size> files.
+#
+# Usage: [-t target_size] [-b branch_name]
+
+set -e
+
+target_size=10000
+branch_name=p0006-ballast
+ballast=ballast
+
+while test "$#" -ne 0
+do
+ case "$1" in
+ -b)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -b requires an argument' >&2; exit 1; }
+ branch_name=$1;
+ shift ;;
+ -t)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -t requires an argument' >&2; exit 1; }
+ target_size=$1;
+ shift ;;
+ *)
+ echo "error: unknown option '$1'" >&2; exit 1 ;;
+ esac
+done
+
+git ls-tree -r HEAD >GEN_src_list
+nr_src_files=$(cat GEN_src_list | wc -l)
+
+src_branch=$(git symbolic-ref --short HEAD)
+
+echo "Branch $src_branch initially has $nr_src_files files."
+
+if test $target_size -le $nr_src_files
+then
+ echo "Repository already exceeds target size $target_size."
+ rm GEN_src_list
+ exit 1
+fi
+
+# Create well-known branch and add 1 file change to start
+# if off before the ballast.
+git checkout -b $branch_name HEAD
+echo "$target_size" > inflate-repo.params
+git add inflate-repo.params
+git commit -q -m params
+
+# Create ballast for in our branch.
+copy=1
+nr_files=$nr_src_files
+while test $nr_files -lt $target_size
+do
+ sed -e "s| | $ballast/$copy/|" <GEN_src_list |
+ git update-index --index-info
+
+ nr_files=$(expr $nr_files + $nr_src_files)
+ copy=$(expr $copy + 1)
+done
+rm GEN_src_list
+git commit -q -m "ballast"
+
+# Modify 1 file and commit.
+echo "$target_size" >> inflate-repo.params
+git add inflate-repo.params
+git commit -q -m "ballast plus 1"
+
+nr_files=$(git ls-files | wc -l)
+
+# Checkout master to put repo in canonical state (because
+# the perf test may need to clone and enable sparse-checkout
+# before attempting to checkout a commit with the ballast
+# (because it may contain 100K directories and 1M files)).
+git checkout $src_branch
+
+echo "Repository inflated. Branch $branch_name has $nr_files files."
+
+exit 0
+
diff --git a/t/perf/repos/many-files.sh b/t/perf/repos/many-files.sh
new file mode 100755
index 0000000..28720e4
--- /dev/null
+++ b/t/perf/repos/many-files.sh
@@ -0,0 +1,110 @@
+#!/bin/sh
+# Generate test data repository using the given parameters.
+# When omitted, we create "gen-many-files-d-w-f.git".
+#
+# Usage: [-r repo] [-d depth] [-w width] [-f files]
+#
+# -r repo: path to the new repo to be generated
+# -d depth: the depth of sub-directories
+# -w width: the number of sub-directories at each level
+# -f files: the number of files created in each directory
+#
+# Note that all files will have the same SHA-1 and each
+# directory at a level will have the same SHA-1, so we
+# will potentially have a large index, but not a large
+# ODB.
+#
+# Ballast will be created under "ballast/".
+
+EMPTY_BLOB=e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+
+set -e
+
+# (5, 10, 9) will create 999,999 ballast files.
+# (4, 10, 9) will create 99,999 ballast files.
+depth=5
+width=10
+files=9
+
+while test "$#" -ne 0
+do
+ case "$1" in
+ -r)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -r requires an argument' >&2; exit 1; }
+ repo=$1;
+ shift ;;
+ -d)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -d requires an argument' >&2; exit 1; }
+ depth=$1;
+ shift ;;
+ -w)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -w requires an argument' >&2; exit 1; }
+ width=$1;
+ shift ;;
+ -f)
+ shift;
+ test "$#" -ne 0 || { echo 'error: -f requires an argument' >&2; exit 1; }
+ files=$1;
+ shift ;;
+ *)
+ echo "error: unknown option '$1'" >&2; exit 1 ;;
+ esac
+done
+
+# Inflate the index with thousands of empty files.
+# usage: dir depth width files
+fill_index() {
+ awk -v arg_dir=$1 -v arg_depth=$2 -v arg_width=$3 -v arg_files=$4 '
+ function make_paths(dir, depth, width, files, f, w) {
+ for (f = 1; f <= files; f++) {
+ print dir "/file" f
+ }
+ if (depth > 0) {
+ for (w = 1; w <= width; w++) {
+ make_paths(dir "/dir" w, depth - 1, width, files)
+ }
+ }
+ }
+ END { make_paths(arg_dir, arg_depth, arg_width, arg_files) }
+ ' </dev/null |
+ sed "s/^/100644 $EMPTY_BLOB /" |
+ git update-index --index-info
+ return 0
+}
+
+[ -z "$repo" ] && repo=gen-many-files-$depth.$width.$files.git
+
+mkdir $repo
+cd $repo
+git init .
+
+# Create an initial commit just to define master.
+touch many-files.empty
+echo "$depth $width $files" >many-files.params
+git add many-files.*
+git commit -q -m params
+
+# Create ballast for p0006 based upon the given params and
+# inflate the index with thousands of empty files and commit.
+git checkout -b p0006-ballast
+fill_index "ballast" $depth $width $files
+git commit -q -m "ballast"
+
+nr_files=$(git ls-files | wc -l)
+
+# Modify 1 file and commit.
+echo "$depth $width $files" >>many-files.params
+git add many-files.params
+git commit -q -m "ballast plus 1"
+
+# Checkout master to put repo in canonical state (because
+# the perf test may need to clone and enable sparse-checkout
+# before attempting to checkout a commit with the ballast
+# (because it may contain 100K directories and 1M files)).
+git checkout master
+
+echo "Repository "$repo" ($depth, $width, $files) created. Ballast $nr_files."
+exit 0
--
2.9.3