Skip to content

Improve cherryPickOnto performance #1248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pjbgf merged 3 commits into from
May 22, 2026
Merged

Improve cherryPickOnto performance #1248

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fb33132
Improve cherryPickOnto performance
pjbgf May 21, 2026
cc702fa
Fix lint issue
pjbgf May 21, 2026
765f634
Fix invalid tree on test
pjbgf May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion cmd/entire/cli/checkpoint/v2_generation_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,11 +129,14 @@ func TestAddGenerationJSONToTree(t *testing.T) {
store := NewV2GitStore(repo)

// Start with a root tree that has a shard directory entry (simulating checkpoint data)
transcriptBlobHash, err := CreateBlobFromContent(repo, []byte("test transcript"))
require.NoError(t, err)

shardEntries := map[string]object.TreeEntry{}
shardEntries["aa/bbccddeeff/0/"+paths.V2RawTranscriptFileName] = object.TreeEntry{
Name: paths.V2RawTranscriptFileName,
Mode: 0o100644,
Hash: plumbing.ZeroHash, // dummy
Hash: transcriptBlobHash,
Comment thread
pjbgf marked this conversation as resolved.
}
rootTreeHash, err := BuildTreeFromEntries(context.Background(), repo, shardEntries)
require.NoError(t, err)
Expand Down
123 changes: 64 additions & 59 deletions cmd/entire/cli/strategy/metadata_reconcile.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ import (
"github.com/go-git/go-git/v6"
"github.com/go-git/go-git/v6/plumbing"
"github.com/go-git/go-git/v6/plumbing/object"
"github.com/go-git/go-git/v6/utils/merkletrie"
)

// disconnectedOnce ensures the disconnection warning runs at most once per process.
Expand Down Expand Up @@ -491,76 +492,22 @@ func cherryPickOnto(ctx context.Context, repo *git.Repository, base plumbing.Has
currentTip := base

for _, commit := range commits {
// Get the commit's tree entries
commitTree, err := commit.Tree()
changes, err := treeChangesForCherryPick(ctx, repo, commit)
if err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to get tree for commit %s: %w", commit.Hash, err)
return plumbing.ZeroHash, err
}

commitEntries := make(map[string]object.TreeEntry)
if err := checkpoint.FlattenTree(repo, commitTree, "", commitEntries); err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to flatten commit tree: %w", err)
}

// Get parent's tree entries (empty if root commit)
parentEntries := make(map[string]object.TreeEntry)
if len(commit.ParentHashes) > 0 {
parentCommit, pErr := repo.CommitObject(commit.ParentHashes[0])
if pErr != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to get parent commit %s: %w", commit.ParentHashes[0], pErr)
}
parentTree, ptErr := parentCommit.Tree()
if ptErr != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to get parent tree for commit %s: %w", commit.ParentHashes[0], ptErr)
}
if err := checkpoint.FlattenTree(repo, parentTree, "", parentEntries); err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to flatten parent tree for commit %s: %w", commit.ParentHashes[0], err)
}
}

// Compute full delta: additions, modifications, and deletions
added := make(map[string]object.TreeEntry)
for path, entry := range commitEntries {
parentEntry, exists := parentEntries[path]
if !exists || parentEntry.Hash != entry.Hash {
added[path] = entry // New or modified
}
}
var deleted []string
for path := range parentEntries {
if _, exists := commitEntries[path]; !exists {
deleted = append(deleted, path) // Removed in this commit
}
}

if len(added) == 0 && len(deleted) == 0 {
if len(changes) == 0 {
continue // Skip no-op commits
}

// Get current tip's tree and apply delta
tipCommit, err := repo.CommitObject(currentTip)
if err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to get tip commit: %w", err)
}
tipTree, err := tipCommit.Tree()
if err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to get tip tree: %w", err)
}

mergedEntries := make(map[string]object.TreeEntry)
if err := checkpoint.FlattenTree(repo, tipTree, "", mergedEntries); err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to flatten tip tree: %w", err)
}
for path, entry := range added {
mergedEntries[path] = entry
}
for _, path := range deleted {
delete(mergedEntries, path)
}

mergedTreeHash, err := checkpoint.BuildTreeFromEntries(ctx, repo, mergedEntries)
mergedTreeHash, err := checkpoint.ApplyTreeChanges(ctx, repo, tipCommit.TreeHash, changes)
if err != nil {
return plumbing.ZeroHash, fmt.Errorf("failed to build merged tree: %w", err)
return plumbing.ZeroHash, fmt.Errorf("failed to apply cherry-pick changes: %w", err)
}

// Create new commit on top of current tip, preserving original message/author
Expand All @@ -575,6 +522,64 @@ func cherryPickOnto(ctx context.Context, repo *git.Repository, base plumbing.Has
return currentTip, nil
}

func treeChangesForCherryPick(ctx context.Context, repo *git.Repository, commit *object.Commit) ([]checkpoint.TreeChange, error) {
commitTree, err := commit.Tree()
if err != nil {
return nil, fmt.Errorf("failed to get tree for commit %s: %w", commit.Hash, err)
}

var parentTree *object.Tree
if len(commit.ParentHashes) > 0 {
parentCommit, pErr := repo.CommitObject(commit.ParentHashes[0])
if pErr != nil {
return nil, fmt.Errorf("failed to get parent commit %s: %w", commit.ParentHashes[0], pErr)
}
parentTree, err = parentCommit.Tree()
if err != nil {
return nil, fmt.Errorf("failed to get parent tree for commit %s: %w", commit.ParentHashes[0], err)
}
}

changes, err := object.DiffTreeContext(ctx, parentTree, commitTree)
if err != nil {
return nil, fmt.Errorf("failed to diff commit %s against parent: %w", commit.Hash, err)
}

treeChanges := make([]checkpoint.TreeChange, 0, len(changes))
for _, change := range changes {
treeChange, changeErr := changeToTreeChange(change)
if changeErr != nil {
return nil, fmt.Errorf("failed to convert change in commit %s: %w", commit.Hash, changeErr)
}
treeChanges = append(treeChanges, treeChange)
}
return treeChanges, nil
}

func changeToTreeChange(change *object.Change) (checkpoint.TreeChange, error) {
action, err := change.Action()
if err != nil {
return checkpoint.TreeChange{}, fmt.Errorf("change action: %w", err)
}

switch action {
case merkletrie.Insert, merkletrie.Modify:
entry := change.To.TreeEntry
return checkpoint.TreeChange{
Path: change.To.Name,
Entry: &object.TreeEntry{
Name: entry.Name,
Mode: entry.Mode,
Hash: entry.Hash,
},
}, nil
case merkletrie.Delete:
return checkpoint.TreeChange{Path: change.From.Name}, nil
default:
return checkpoint.TreeChange{}, fmt.Errorf("unsupported action %s", action)
}
}

// createCherryPickCommit creates a new commit on top of parent, preserving the
// original commit's message and author.
func createCherryPickCommit(ctx context.Context, repo *git.Repository, treeHash, parent plumbing.Hash, original *object.Commit) (plumbing.Hash, error) {
Expand Down
6 changes: 3 additions & 3 deletions go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ require (
github.com/charmbracelet/x/ansi v0.11.7
github.com/creack/pty v1.1.24
github.com/denisbrodbeck/machineid v1.0.1
github.com/go-git/go-billy/v6 v6.0.0-alpha.1
github.com/go-git/go-git/v6 v6.0.0-alpha.3.0.20260507221227-c9084f20dee2
github.com/go-git/go-billy/v6 v6.0.0-alpha.1.0.20260519112248-0095b064a6c6
github.com/go-git/go-git/v6 v6.0.0-alpha.4.0.20260521161150-3af8745c291b
github.com/go-git/x/plugin/objectsigner/auto v0.1.0
github.com/go-git/x/plugin/objectsigner/program v0.0.0-20260506121155-e7fc238fcab6
github.com/google/uuid v1.6.0
Expand Down Expand Up @@ -130,7 +130,7 @@ require (
go.yaml.in/yaml/v3 v3.0.4 // indirect
go4.org v0.0.0-20260112195520-a5071408f32f // indirect
golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa // indirect
golang.org/x/net v0.53.0 // indirect
golang.org/x/net v0.54.0 // indirect
golang.org/x/text v0.37.0 // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20251202230838-ff82c1b0f217 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20251222181119-0a764e51fe1b // indirect
Expand Down
16 changes: 8 additions & 8 deletions go.sum
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,12 +121,12 @@ github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
github.com/go-git/gcfg/v2 v2.0.2 h1:MY5SIIfTGGEMhdA7d7JePuVVxtKL7Hp+ApGDJAJ7dpo=
github.com/go-git/gcfg/v2 v2.0.2/go.mod h1:/lv2NsxvhepuMrldsFilrgct6pxzpGdSRC13ydTLSLs=
github.com/go-git/go-billy/v6 v6.0.0-alpha.1 h1:xVjAR4oUvrKy7/Xuw/lLlV3gkxR3KO2H8W+MamuVVsQ=
github.com/go-git/go-billy/v6 v6.0.0-alpha.1/go.mod h1:eaCUpHbedW7//EwcYmUDfJe2N6sJC9O12AT0OTqJR1E=
github.com/go-git/go-git-fixtures/v6 v6.0.0-20260422085740-0c07409f52ec h1:FpCNUs50xfQyJJs31uO3mDnqU855OhzAzfkkTgE6/DI=
github.com/go-git/go-git-fixtures/v6 v6.0.0-20260422085740-0c07409f52ec/go.mod h1:F1SpxOny2UYXu62DzjEH4UqBjk4AoGs27cA8I9buK+o=
github.com/go-git/go-git/v6 v6.0.0-alpha.3.0.20260507221227-c9084f20dee2 h1:WGQWikXciN5yYwTtPiJkbmrUqJX07tWbBVV6VeSo19A=
github.com/go-git/go-git/v6 v6.0.0-alpha.3.0.20260507221227-c9084f20dee2/go.mod h1:DGnqu+twdAgtDx/4tQTWFrVE1an+2ACph3W9yOfSJZM=
github.com/go-git/go-billy/v6 v6.0.0-alpha.1.0.20260519112248-0095b064a6c6 h1:AaQOU2NVLxnBGWkv5YSoxomcDCqlaqfCW0t00pNKtnk=
github.com/go-git/go-billy/v6 v6.0.0-alpha.1.0.20260519112248-0095b064a6c6/go.mod h1:eaCUpHbedW7//EwcYmUDfJe2N6sJC9O12AT0OTqJR1E=
github.com/go-git/go-git-fixtures/v6 v6.0.0-alpha.1 h1:gmqi2jvsreu0s8JMLylYDFq4sbjHwwlhktMw0DUg3mA=
github.com/go-git/go-git-fixtures/v6 v6.0.0-alpha.1/go.mod h1:ECf1MqJlBdYpKggBrOXjo/0EnvRZx6D++I86UYjPgAQ=
github.com/go-git/go-git/v6 v6.0.0-alpha.4.0.20260521161150-3af8745c291b h1:99k+na4J/y/rKvB21GFeFhIf/Rqskfc4a6mvTf4wbJA=
github.com/go-git/go-git/v6 v6.0.0-alpha.4.0.20260521161150-3af8745c291b/go.mod h1:OTUSi3RzPFoC0j/+uxHdVG1X/xXz84QCxLzYvXRvyXk=
github.com/go-git/x/plugin/objectsigner/auto v0.1.0 h1:RcLW29RgwSCmqrNSs7QOxvWkRbM1vPu0Vp9TCECZjMs=
github.com/go-git/x/plugin/objectsigner/auto v0.1.0/go.mod h1:iP2cXPyXc//9v9THS3y/MLi0jnt7vEqwUDj11qQfFPg=
github.com/go-git/x/plugin/objectsigner/gpg v0.1.0 h1:NEGVSOD+LPnus6j4iNkAZaHVTc4DNY223y1/I2Jq2yI=
Expand Down Expand Up @@ -309,8 +309,8 @@ golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa h1:t2QcU6V556bFjYgu4L6C+6VrC
golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
golang.org/x/mod v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
golang.org/x/net v0.54.0 h1:2zJIZAxAHV/OHCDTCOHAYehQzLfSXuf/5SoL/Dv6w/w=
golang.org/x/net v0.54.0/go.mod h1:Sj4oj8jK6XmHpBZU/zWHw3BV3abl4Kvi+Ut7cQcY+cQ=
golang.org/x/oauth2 v0.34.0 h1:hqK/t4AKgbqWkdkcAeI8XLmbK+4m4G5YeQRrmiotGlw=
golang.org/x/oauth2 v0.34.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
Expand Down
Loading