From 841b62a321b3739381b48aeea7364126d1c54520 Mon Sep 17 00:00:00 2001
From: Jeremy Stribling <strib@alum.mit.edu>
Date: Fri, 8 Sep 2017 17:51:38 -0700
Subject: plumbing: the commit walker can skip externally-seen commits

When the revlist is computing the set of hashes needed to transfer, it
doesn't need to walk over commits it has already processed.  So, it
can instruct the commit walker not to walk those commits by passing in
its own `seen` map.

For a 36K object repo, this brought the time for `revlist.Objects`
down from 50s to 30s.
---
 plumbing/object/commit_walker.go      | 22 ++++++++++++++--------
 plumbing/object/commit_walker_test.go | 28 ++++++++++++++++++++++++++--
 plumbing/revlist/revlist.go           |  2 +-
 3 files changed, 41 insertions(+), 11 deletions(-)

(limited to 'plumbing')

diff --git a/plumbing/object/commit_walker.go b/plumbing/object/commit_walker.go
index 797c17a..40ad258 100644
--- a/plumbing/object/commit_walker.go
+++ b/plumbing/object/commit_walker.go
@@ -8,9 +8,10 @@ import (
 )
 
 type commitPreIterator struct {
-	seen  map[plumbing.Hash]bool
-	stack []CommitIter
-	start *Commit
+	seenExternal map[plumbing.Hash]bool
+	seen         map[plumbing.Hash]bool
+	stack        []CommitIter
+	start        *Commit
 }
 
 // NewCommitPreorderIter returns a CommitIter that walks the commit history,
@@ -20,16 +21,21 @@ type commitPreIterator struct {
 // and will return the error. Other errors might be returned if the history
 // cannot be traversed (e.g. missing objects). Ignore allows to skip some
 // commits from being iterated.
-func NewCommitPreorderIter(c *Commit, ignore []plumbing.Hash) CommitIter {
+func NewCommitPreorderIter(
+	c *Commit,
+	seenExternal map[plumbing.Hash]bool,
+	ignore []plumbing.Hash,
+) CommitIter {
 	seen := make(map[plumbing.Hash]bool)
 	for _, h := range ignore {
 		seen[h] = true
 	}
 
 	return &commitPreIterator{
-		seen:  seen,
-		stack: make([]CommitIter, 0),
-		start: c,
+		seenExternal: seenExternal,
+		seen:         seen,
+		stack:        make([]CommitIter, 0),
+		start:        c,
 	}
 }
 
@@ -57,7 +63,7 @@ func (w *commitPreIterator) Next() (*Commit, error) {
 			}
 		}
 
-		if w.seen[c.Hash] {
+		if w.seen[c.Hash] || w.seenExternal[c.Hash] {
 			continue
 		}
 
diff --git a/plumbing/object/commit_walker_test.go b/plumbing/object/commit_walker_test.go
index 48b504d..a27104e 100644
--- a/plumbing/object/commit_walker_test.go
+++ b/plumbing/object/commit_walker_test.go
@@ -16,7 +16,7 @@ func (s *CommitWalkerSuite) TestCommitPreIterator(c *C) {
 	commit := s.commit(c, s.Fixture.Head)
 
 	var commits []*Commit
-	NewCommitPreorderIter(commit, nil).ForEach(func(c *Commit) error {
+	NewCommitPreorderIter(commit, nil, nil).ForEach(func(c *Commit) error {
 		commits = append(commits, c)
 		return nil
 	})
@@ -42,7 +42,7 @@ func (s *CommitWalkerSuite) TestCommitPreIteratorWithIgnore(c *C) {
 	commit := s.commit(c, s.Fixture.Head)
 
 	var commits []*Commit
-	NewCommitPreorderIter(commit, []plumbing.Hash{
+	NewCommitPreorderIter(commit, nil, []plumbing.Hash{
 		plumbing.NewHash("af2d6a6954d532f8ffb47615169c8fdf9d383a1a"),
 	}).ForEach(func(c *Commit) error {
 		commits = append(commits, c)
@@ -60,6 +60,30 @@ func (s *CommitWalkerSuite) TestCommitPreIteratorWithIgnore(c *C) {
 	}
 }
 
+func (s *CommitWalkerSuite) TestCommitPreIteratorWithSeenExternal(c *C) {
+	commit := s.commit(c, s.Fixture.Head)
+
+	var commits []*Commit
+	seenExternal := map[plumbing.Hash]bool{
+		plumbing.NewHash("af2d6a6954d532f8ffb47615169c8fdf9d383a1a"): true,
+	}
+	NewCommitPreorderIter(commit, seenExternal, nil).
+		ForEach(func(c *Commit) error {
+			commits = append(commits, c)
+			return nil
+		})
+
+	c.Assert(commits, HasLen, 2)
+
+	expected := []string{
+		"6ecf0ef2c2dffb796033e5a02219af86ec6584e5",
+		"918c48b83bd081e863dbe1b80f8998f058cd8294",
+	}
+	for i, commit := range commits {
+		c.Assert(commit.Hash.String(), Equals, expected[i])
+	}
+}
+
 func (s *CommitWalkerSuite) TestCommitPostIterator(c *C) {
 	commit := s.commit(c, s.Fixture.Head)
 
diff --git a/plumbing/revlist/revlist.go b/plumbing/revlist/revlist.go
index 10a5813..009fc93 100644
--- a/plumbing/revlist/revlist.go
+++ b/plumbing/revlist/revlist.go
@@ -108,7 +108,7 @@ func reachableObjects(
 	ignore []plumbing.Hash,
 	cb func(h plumbing.Hash),
 ) error {
-	i := object.NewCommitPreorderIter(commit, ignore)
+	i := object.NewCommitPreorderIter(commit, seen, ignore)
 	for {
 		commit, err := i.Next()
 		if err == io.EOF {
-- 
cgit