feat(T2.5): implement git operation batching
- Add internal/batching package for git operation batching - Implement GitBatcher with configurable batch size and age - Queue git operations (commit, push, merge) - Auto-flush on max batch size - Manual flush on demand - Time-based flush (max batch age) - Batch status tracking (pending, executing, completed, failed) - Network savings calculation - Statistics tracking per batch and aggregated - 24 batching tests, all passing Features: - Enqueue() for adding operations to queue - Flush() for manual batch creation - GetPendingBatch() for next pending batch - MarkBatchExecuting/Completed/Failed() for status tracking - GetStats() for batching statistics - CalculateNetworkSavings() for round trip savings - GetExecutedBatches() for completed batch history - TimeSinceLastFlush() for age checking - ShouldFlush() for time-based decisions Performance Benefits: - N commits batched into 1 push saves N-1 round trips - Example: 10 commits in 2 batches saves 8 round trips - Configurable batch size (default 10) - Configurable max age (default 5s) - FIFO queue processing Network Savings Example: - 10 operations in 2 batches of 5 each - Network savings: 8 round trips (vs 10 individual operations) - Verified in TestGetStats Status Tracking: - pending: queued and ready to execute - executing: currently being executed - completed: finished successfully - failed: execution failed (kept for retry) Test Coverage: - 24 batching tests (enqueue, flush, status, stats) - Auto-flush on max size verified - Time-based flush behavior tested - Network savings calculation verified - Error handling and state management - Concurrent safe operations (RWMutex) Next: T2.6 (LLM request batching)
This commit is contained in:
Test
@@ -0,0 +1,331 @@
|
||||
package batching
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
// GitOp represents a git operation to be batched
|
||||
type GitOp struct {
|
||||
OpType string // "commit", "push", "merge"
|
||||
Branch string
|
||||
Message string
|
||||
Files []string
|
||||
Timestamp time.Time
|
||||
ID string
|
||||
}
|
||||
|
||||
// GitBatch represents a batch of git operations
|
||||
type GitBatch struct {
|
||||
ID string
|
||||
Operations []*GitOp
|
||||
CreatedAt time.Time
|
||||
ExecutedAt time.Time
|
||||
Status string // "pending", "executing", "completed", "failed"
|
||||
Error error
|
||||
}
|
||||
|
||||
// GitBatcher batches git operations for efficient execution
|
||||
type GitBatcher struct {
|
||||
mu sync.RWMutex
|
||||
queue []*GitOp
|
||||
maxBatchSize int
|
||||
maxBatchAge time.Duration
|
||||
lastFlushTime time.Time
|
||||
executedBatches []*GitBatch
|
||||
pendingBatches []*GitBatch
|
||||
stats *BatchStats
|
||||
flushChan chan struct{}
|
||||
stopChan chan struct{}
|
||||
}
|
||||
|
||||
// BatchStats tracks batching statistics
|
||||
type BatchStats struct {
|
||||
TotalOps int
|
||||
TotalBatches int
|
||||
AvgOpsPerBatch float64
|
||||
NetworkSavings int // Estimated network round trips saved
|
||||
TotalExecuteTime time.Duration
|
||||
}
|
||||
|
||||
// NewGitBatcher creates a new git batcher
|
||||
func NewGitBatcher(maxBatchSize int, maxBatchAge time.Duration) *GitBatcher {
|
||||
if maxBatchSize <= 0 {
|
||||
maxBatchSize = 10
|
||||
}
|
||||
if maxBatchAge <= 0 {
|
||||
maxBatchAge = 5 * time.Second
|
||||
}
|
||||
|
||||
return &GitBatcher{
|
||||
queue: make([]*GitOp, 0),
|
||||
maxBatchSize: maxBatchSize,
|
||||
maxBatchAge: maxBatchAge,
|
||||
lastFlushTime: time.Now(),
|
||||
executedBatches: make([]*GitBatch, 0),
|
||||
pendingBatches: make([]*GitBatch, 0),
|
||||
stats: &BatchStats{
|
||||
TotalOps: 0,
|
||||
TotalBatches: 0,
|
||||
},
|
||||
flushChan: make(chan struct{}, 1),
|
||||
stopChan: make(chan struct{}),
|
||||
}
|
||||
}
|
||||
|
||||
// Enqueue adds a git operation to the queue
|
||||
func (gb *GitBatcher) Enqueue(op *GitOp) {
|
||||
if op == nil {
|
||||
return
|
||||
}
|
||||
|
||||
op.Timestamp = time.Now()
|
||||
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
gb.queue = append(gb.queue, op)
|
||||
gb.stats.TotalOps++
|
||||
|
||||
// Auto-flush if batch is full
|
||||
if len(gb.queue) >= gb.maxBatchSize {
|
||||
gb.flushLocked()
|
||||
}
|
||||
}
|
||||
|
||||
// flushLocked creates a batch from queued operations (must be called with lock held)
|
||||
func (gb *GitBatcher) flushLocked() {
|
||||
if len(gb.queue) == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
batch := &GitBatch{
|
||||
ID: fmt.Sprintf("batch-%d", gb.stats.TotalBatches),
|
||||
Operations: make([]*GitOp, len(gb.queue)),
|
||||
CreatedAt: time.Now(),
|
||||
Status: "pending",
|
||||
}
|
||||
|
||||
copy(batch.Operations, gb.queue)
|
||||
|
||||
gb.pendingBatches = append(gb.pendingBatches, batch)
|
||||
gb.queue = make([]*GitOp, 0)
|
||||
gb.lastFlushTime = time.Now()
|
||||
gb.stats.TotalBatches++
|
||||
}
|
||||
|
||||
// Flush manually flushes the current batch
|
||||
func (gb *GitBatcher) Flush() {
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
gb.flushLocked()
|
||||
}
|
||||
|
||||
// GetPendingBatch returns the next pending batch without removing it
|
||||
func (gb *GitBatcher) GetPendingBatch() *GitBatch {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
if len(gb.pendingBatches) == 0 {
|
||||
return nil
|
||||
}
|
||||
|
||||
return gb.pendingBatches[0]
|
||||
}
|
||||
|
||||
// MarkBatchExecuting marks a batch as executing
|
||||
func (gb *GitBatcher) MarkBatchExecuting(batchID string) {
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
for _, batch := range gb.pendingBatches {
|
||||
if batch.ID == batchID {
|
||||
batch.Status = "executing"
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// MarkBatchCompleted marks a batch as completed and removes from pending
|
||||
func (gb *GitBatcher) MarkBatchCompleted(batchID string) {
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
var idx int
|
||||
var found *GitBatch
|
||||
for i, batch := range gb.pendingBatches {
|
||||
if batch.ID == batchID {
|
||||
idx = i
|
||||
found = batch
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
if found != nil {
|
||||
found.Status = "completed"
|
||||
found.ExecutedAt = time.Now()
|
||||
|
||||
// Move to executed batches
|
||||
gb.executedBatches = append(gb.executedBatches, found)
|
||||
|
||||
// Remove from pending
|
||||
gb.pendingBatches = append(gb.pendingBatches[:idx], gb.pendingBatches[idx+1:]...)
|
||||
}
|
||||
}
|
||||
|
||||
// MarkBatchFailed marks a batch as failed with an error
|
||||
func (gb *GitBatcher) MarkBatchFailed(batchID string, err error) {
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
var found *GitBatch
|
||||
for _, batch := range gb.pendingBatches {
|
||||
if batch.ID == batchID {
|
||||
found = batch
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
if found != nil {
|
||||
found.Status = "failed"
|
||||
found.Error = err
|
||||
found.ExecutedAt = time.Now()
|
||||
|
||||
// Keep in pending (for retry logic)
|
||||
// Could also move to failed queue
|
||||
}
|
||||
}
|
||||
|
||||
// QueueSize returns the current queue size
|
||||
func (gb *GitBatcher) QueueSize() int {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
return len(gb.queue)
|
||||
}
|
||||
|
||||
// PendingBatchCount returns the number of pending batches
|
||||
func (gb *GitBatcher) PendingBatchCount() int {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
return len(gb.pendingBatches)
|
||||
}
|
||||
|
||||
// GetStats returns batching statistics
|
||||
func (gb *GitBatcher) GetStats() *BatchStats {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
stats := *gb.stats
|
||||
if stats.TotalBatches > 0 {
|
||||
stats.AvgOpsPerBatch = float64(stats.TotalOps) / float64(stats.TotalBatches)
|
||||
// Estimated savings: each batch saves (ops-1) round trips
|
||||
stats.NetworkSavings = stats.TotalOps - stats.TotalBatches
|
||||
}
|
||||
|
||||
return &stats
|
||||
}
|
||||
|
||||
// GetExecutedBatches returns all executed batches
|
||||
func (gb *GitBatcher) GetExecutedBatches() []*GitBatch {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
result := make([]*GitBatch, len(gb.executedBatches))
|
||||
copy(result, gb.executedBatches)
|
||||
|
||||
return result
|
||||
}
|
||||
|
||||
// GetBatchByID returns a specific batch by ID
|
||||
func (gb *GitBatcher) GetBatchByID(batchID string) *GitBatch {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
for _, batch := range gb.pendingBatches {
|
||||
if batch.ID == batchID {
|
||||
return batch
|
||||
}
|
||||
}
|
||||
|
||||
for _, batch := range gb.executedBatches {
|
||||
if batch.ID == batchID {
|
||||
return batch
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// TimeSinceLastFlush returns time since last flush
|
||||
func (gb *GitBatcher) TimeSinceLastFlush() time.Duration {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
return time.Since(gb.lastFlushTime)
|
||||
}
|
||||
|
||||
// ShouldFlush checks if batch should be flushed based on age
|
||||
func (gb *GitBatcher) ShouldFlush() bool {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
if len(gb.queue) == 0 {
|
||||
return false
|
||||
}
|
||||
|
||||
return time.Since(gb.lastFlushTime) >= gb.maxBatchAge
|
||||
}
|
||||
|
||||
// Clear clears all pending operations and batches
|
||||
func (gb *GitBatcher) Clear() {
|
||||
gb.mu.Lock()
|
||||
defer gb.mu.Unlock()
|
||||
|
||||
gb.queue = make([]*GitOp, 0)
|
||||
gb.pendingBatches = make([]*GitBatch, 0)
|
||||
gb.executedBatches = make([]*GitBatch, 0)
|
||||
}
|
||||
|
||||
// GetQueuedOps returns a copy of queued operations
|
||||
func (gb *GitBatcher) GetQueuedOps() []*GitOp {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
ops := make([]*GitOp, len(gb.queue))
|
||||
copy(ops, gb.queue)
|
||||
|
||||
return ops
|
||||
}
|
||||
|
||||
// CalculateNetworkSavings calculates estimated network round trips saved
|
||||
func (gb *GitBatcher) CalculateNetworkSavings() int {
|
||||
gb.mu.RLock()
|
||||
defer gb.mu.RUnlock()
|
||||
|
||||
totalSavings := 0
|
||||
// Each batch of N operations saves N-1 round trips
|
||||
for _, batch := range gb.executedBatches {
|
||||
if len(batch.Operations) > 1 {
|
||||
totalSavings += len(batch.Operations) - 1
|
||||
}
|
||||
}
|
||||
|
||||
return totalSavings
|
||||
}
|
||||
|
||||
// GetBatchInfo returns human-readable batch information
|
||||
func (batch *GitBatch) GetInfo() map[string]interface{} {
|
||||
return map[string]interface{}{
|
||||
"id": batch.ID,
|
||||
"status": batch.Status,
|
||||
"op_count": len(batch.Operations),
|
||||
"created_at": batch.CreatedAt,
|
||||
"executed_at": batch.ExecutedAt,
|
||||
"duration": batch.ExecutedAt.Sub(batch.CreatedAt),
|
||||
"error": batch.Error,
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user