Files
beads/internal/storage/sqlite/sqlite_bench_test.go
Ryan 335887e000 perf: fix stale startlock delay and add comprehensive benchmarks (#484)
* fix(daemon): check for stale startlock before waiting 5 seconds

When a previous daemon startup left behind a bd.sock.startlock file
(e.g., from a crashed process), the code was waiting 5 seconds before
checking if the lock was stale. This caused unnecessary delays on
every bd command when the daemon wasn't running.

Now checks if the PID in the startlock file is alive BEFORE waiting.
If the PID is dead or unreadable, the stale lock is cleaned up
immediately and lock acquisition is retried.

Fixes ~5s delay when startlock file exists from crashed process.

* perf: add benchmarks for large descriptions, bulk operations, and sync merge

Added three new performance benchmarks to identify bottlenecks in common operations:

1. BenchmarkLargeDescription - Tests handling of 100KB+ issue descriptions
   - Measures string allocation/parsing overhead
   - Result: 3.3ms/op, 874KB/op allocation

2. BenchmarkBulkCloseIssues - Tests closing 100 issues sequentially
   - Measures batch write performance
   - Result: 1.9s total, shows write amplification

3. BenchmarkSyncMerge - Tests JSONL merge cycle with creates/updates
   - Simulates real sync operations (10 creates + 10 updates per iteration)
   - Result: 29ms/op, identifies sync bottlenecks

Added BENCHMARKS.md documentation describing:
- How to run benchmarks with various options
- All available benchmark categories
- Performance targets on M2 Pro hardware
- Dataset caching strategy
- CPU profiling integration
- Optimization workflow

This completes performance testing coverage for previously unmeasured scenarios.

* docs: clarify daemon lock acquisition logic in comments

Improve comments to clarify that acquireStartLock does both:
1. Immediately check for stale locks from crashed processes (avoids 5s delay)
2. If PID is alive, properly wait for legitimate daemon startup (5s timeout)

No code changes - only clarified comment documentation for maintainability.

---------

Co-authored-by: Steve Yegge <steve.yegge@gmail.com>
2025-12-13 06:57:11 -08:00

243 lines
7.0 KiB
Go

//go:build bench
package sqlite
import (
"context"
"testing"
"github.com/steveyegge/beads/internal/types"
)
// Benchmark size rationale:
// We only benchmark Large (10K) and XLarge (20K) databases because:
// - Small databases (<1K issues) perform acceptably without optimization
// - Performance issues only manifest at scale (10K+ issues)
// - Smaller benchmarks add code weight without providing optimization insights
// - Target users manage repos with thousands of issues, not hundreds
// runBenchmark sets up a benchmark with consistent configuration and runs the provided test function.
// It handles store setup/cleanup, timer management, and allocation reporting uniformly across all benchmarks.
func runBenchmark(b *testing.B, setupFunc func(*testing.B) (*SQLiteStorage, func()), testFunc func(*SQLiteStorage, context.Context) error) {
b.Helper()
store, cleanup := setupFunc(b)
defer cleanup()
ctx := context.Background()
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
if err := testFunc(store, ctx); err != nil {
b.Fatalf("benchmark failed: %v", err)
}
}
}
// BenchmarkGetReadyWork_Large benchmarks GetReadyWork on 10K issue database
func BenchmarkGetReadyWork_Large(b *testing.B) {
runBenchmark(b, setupLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
_, err := store.GetReadyWork(ctx, types.WorkFilter{})
return err
})
}
// BenchmarkGetReadyWork_XLarge benchmarks GetReadyWork on 20K issue database
func BenchmarkGetReadyWork_XLarge(b *testing.B) {
runBenchmark(b, setupXLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
_, err := store.GetReadyWork(ctx, types.WorkFilter{})
return err
})
}
// BenchmarkSearchIssues_Large_NoFilter benchmarks searching all open issues
func BenchmarkSearchIssues_Large_NoFilter(b *testing.B) {
openStatus := types.StatusOpen
filter := types.IssueFilter{
Status: &openStatus,
}
runBenchmark(b, setupLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
_, err := store.SearchIssues(ctx, "", filter)
return err
})
}
// BenchmarkSearchIssues_Large_ComplexFilter benchmarks complex filtered search
func BenchmarkSearchIssues_Large_ComplexFilter(b *testing.B) {
openStatus := types.StatusOpen
filter := types.IssueFilter{
Status: &openStatus,
PriorityMin: intPtr(0),
PriorityMax: intPtr(2),
}
runBenchmark(b, setupLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
_, err := store.SearchIssues(ctx, "", filter)
return err
})
}
// BenchmarkCreateIssue_Large benchmarks issue creation in large database
func BenchmarkCreateIssue_Large(b *testing.B) {
runBenchmark(b, setupLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
issue := &types.Issue{
Title: "Benchmark issue",
Description: "Test description",
Status: types.StatusOpen,
Priority: 2,
IssueType: types.TypeTask,
}
return store.CreateIssue(ctx, issue, "bench")
})
}
// BenchmarkUpdateIssue_Large benchmarks issue updates in large database
func BenchmarkUpdateIssue_Large(b *testing.B) {
// Setup phase: get an issue to update (not timed)
store, cleanup := setupLargeBenchDB(b)
defer cleanup()
ctx := context.Background()
openStatus := types.StatusOpen
issues, err := store.SearchIssues(ctx, "", types.IssueFilter{
Status: &openStatus,
})
if err != nil || len(issues) == 0 {
b.Fatalf("Failed to get issues for update test: %v", err)
}
targetID := issues[0].ID
// Benchmark phase: measure update operations
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
updates := map[string]interface{}{
"status": types.StatusInProgress,
}
if err := store.UpdateIssue(ctx, targetID, updates, "bench"); err != nil {
b.Fatalf("UpdateIssue failed: %v", err)
}
// reset back to open for next iteration
updates["status"] = types.StatusOpen
if err := store.UpdateIssue(ctx, targetID, updates, "bench"); err != nil {
b.Fatalf("UpdateIssue failed: %v", err)
}
}
}
// BenchmarkGetReadyWork_FromJSONL benchmarks ready work on JSONL-imported database
func BenchmarkGetReadyWork_FromJSONL(b *testing.B) {
runBenchmark(b, setupLargeFromJSONL, func(store *SQLiteStorage, ctx context.Context) error {
_, err := store.GetReadyWork(ctx, types.WorkFilter{})
return err
})
}
// BenchmarkLargeDescription benchmarks handling of issues with very large descriptions (100KB+)
func BenchmarkLargeDescription(b *testing.B) {
runBenchmark(b, setupLargeBenchDB, func(store *SQLiteStorage, ctx context.Context) error {
// Create issue with 100KB description
largeDesc := make([]byte, 100*1024)
for i := range largeDesc {
largeDesc[i] = byte('a' + (i % 26))
}
issue := &types.Issue{
Title: "Issue with large description",
Description: string(largeDesc),
Status: types.StatusOpen,
Priority: 2,
IssueType: types.TypeTask,
}
return store.CreateIssue(ctx, issue, "bench")
})
}
// BenchmarkBulkCloseIssues benchmarks closing 100 issues in sequence
func BenchmarkBulkCloseIssues(b *testing.B) {
store, cleanup := setupLargeBenchDB(b)
defer cleanup()
ctx := context.Background()
// Get 100 open issues to close
openStatus := types.StatusOpen
issues, err := store.SearchIssues(ctx, "", types.IssueFilter{
Status: &openStatus,
Limit: 100,
})
if err != nil || len(issues) < 100 {
b.Fatalf("Failed to get 100 issues for bulk close test: got %d, err %v", len(issues), err)
}
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
for j, issue := range issues {
if err := store.CloseIssue(ctx, issue.ID, "Bulk closed", "bench"); err != nil {
b.Fatalf("CloseIssue failed: %v", err)
}
// Re-open for next iteration (except last one)
if j < len(issues)-1 {
updates := map[string]interface{}{"status": types.StatusOpen}
if err := store.UpdateIssue(ctx, issue.ID, updates, "bench"); err != nil {
b.Fatalf("UpdateIssue failed: %v", err)
}
}
}
}
}
// BenchmarkSyncMerge benchmarks JSONL merge operations (simulating full sync cycle)
func BenchmarkSyncMerge(b *testing.B) {
store, cleanup := setupLargeBenchDB(b)
defer cleanup()
ctx := context.Background()
// For each iteration, simulate a sync by creating and updating issues
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
// Simulate incoming changes: create 10 new issues, update 10 existing
for j := 0; j < 10; j++ {
issue := &types.Issue{
Title: "Synced issue",
Description: "Incoming change",
Status: types.StatusOpen,
Priority: 2,
IssueType: types.TypeTask,
}
if err := store.CreateIssue(ctx, issue, "sync"); err != nil {
b.Fatalf("CreateIssue failed: %v", err)
}
}
// Update 10 existing issues
openStatus := types.StatusOpen
issues, err := store.SearchIssues(ctx, "", types.IssueFilter{
Status: &openStatus,
Limit: 10,
})
if err == nil && len(issues) > 0 {
for _, issue := range issues {
updates := map[string]interface{}{
"title": "Updated from sync",
}
_ = store.UpdateIssue(ctx, issue.ID, updates, "sync")
}
}
}
}
// Helper function
func intPtr(i int) *int {
return &i
}