-
Notifications
You must be signed in to change notification settings - Fork 26
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #120 from bryanhuhta/batch-import
Add batching functionality
- Loading branch information
Showing
4 changed files
with
235 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,68 @@ | ||
| package grpcutil | ||
|
|
||
| import ( | ||
| "context" | ||
| "errors" | ||
| "fmt" | ||
| "runtime" | ||
|
|
||
| "golang.org/x/sync/errgroup" | ||
| "golang.org/x/sync/semaphore" | ||
| ) | ||
|
|
||
| func min(a int, b int) int { | ||
| if a <= b { | ||
| return a | ||
| } | ||
| return b | ||
| } | ||
|
|
||
| // EachFunc is a callback function that is called for each batch. no is the | ||
| // batch number, start is the starting index of this batch in the slice, and | ||
| // end is the ending index of this batch in the slice. | ||
| type EachFunc func(ctx context.Context, no int, start int, end int) error | ||
|
|
||
| // ConcurrentBatch will calculate the minimum number of batches to required to batch n items | ||
| // with batchSize batches. For each batch, it will execute the each function. | ||
| // These functions will be processed in parallel using maxWorkers number of | ||
| // goroutines. If maxWorkers is 1, then batching will happen sychronously. If | ||
| // maxWorkers is 0, then GOMAXPROCS number of workers will be used. | ||
| // | ||
| // If an error occurs during a batch, all the worker's contexts are cancelled | ||
| // and the original error is returned. | ||
| func ConcurrentBatch(ctx context.Context, n int, batchSize int, maxWorkers int, each EachFunc) error { | ||
| if n < 0 { | ||
| return errors.New("cannot batch items of length < 0") | ||
| } else if n == 0 { | ||
| // Batching zero items is a noop. | ||
| return nil | ||
| } | ||
|
|
||
| if batchSize < 1 { | ||
| return errors.New("cannot batch items with batch size < 1") | ||
| } | ||
|
|
||
| if maxWorkers < 0 { | ||
| return errors.New("cannot batch items with workers < 0") | ||
| } else if maxWorkers == 0 { | ||
| maxWorkers = runtime.GOMAXPROCS(0) | ||
| } | ||
|
|
||
| sem := semaphore.NewWeighted(int64(maxWorkers)) | ||
| g, ctx := errgroup.WithContext(ctx) | ||
| numBatches := (n + batchSize - 1) / batchSize | ||
| for i := 0; i < numBatches; i++ { | ||
| if err := sem.Acquire(ctx, 1); err != nil { | ||
| return fmt.Errorf("failed to acquire semaphore for batch number %d: %w", i, err) | ||
| } | ||
|
|
||
| batchNum := i | ||
| g.Go(func() error { | ||
| defer sem.Release(1) | ||
| start := batchNum * batchSize | ||
| end := min(start+batchSize, n) | ||
| return each(ctx, batchNum, start, end) | ||
| }) | ||
| } | ||
| return g.Wait() | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,140 @@ | ||
| package grpcutil | ||
|
|
||
| import ( | ||
| "context" | ||
| "fmt" | ||
| "sync/atomic" | ||
| "testing" | ||
|
|
||
| "github.com/stretchr/testify/require" | ||
| ) | ||
|
|
||
| type batch struct { | ||
| no int | ||
| start int | ||
| end int | ||
| } | ||
|
|
||
| func generateItems(n int) []string { | ||
| items := make([]string, n) | ||
| for i := 0; i < n; i++ { | ||
| items[i] = fmt.Sprintf("item %d", i) | ||
| } | ||
| return items | ||
| } | ||
|
|
||
| func TestConcurrentBatchOrdering(t *testing.T) { | ||
| const batchSize = 3 | ||
| const workers = 1 // Set to one to keep everything synchronous. | ||
|
|
||
| tests := []struct { | ||
| name string | ||
| items []string | ||
| want []batch | ||
| }{ | ||
| { | ||
| name: "1 item", | ||
| items: generateItems(1), | ||
| want: []batch{ | ||
| {0, 0, 1}, | ||
| }, | ||
| }, | ||
| { | ||
| name: "3 items", | ||
| items: generateItems(3), | ||
| want: []batch{ | ||
| {0, 0, 3}, | ||
| }, | ||
| }, | ||
| { | ||
| name: "5 items", | ||
| items: generateItems(5), | ||
| want: []batch{ | ||
| {0, 0, 3}, | ||
| {1, 3, 5}, | ||
| }, | ||
| }, | ||
| } | ||
|
|
||
| for _, tt := range tests { | ||
| t.Run(tt.name, func(t *testing.T) { | ||
| require := require.New(t) | ||
|
|
||
| gotCh := make(chan batch, len(tt.items)) | ||
| fn := func(ctx context.Context, no, start, end int) error { | ||
| gotCh <- batch{no, start, end} | ||
| return nil | ||
| } | ||
|
|
||
| err := ConcurrentBatch(context.Background(), len(tt.items), batchSize, workers, fn) | ||
| require.NoError(err) | ||
|
|
||
| got := make([]batch, len(gotCh)) | ||
| i := 0 | ||
| for span := range gotCh { | ||
| got[i] = span | ||
| i++ | ||
|
|
||
| if i == len(got) { | ||
| break | ||
| } | ||
| } | ||
| require.Equal(tt.want, got) | ||
| }) | ||
| } | ||
| } | ||
|
|
||
| func TestConcurrentBatch(t *testing.T) { | ||
| tests := []struct { | ||
| name string | ||
| items []string | ||
| batchSize int | ||
| workers int | ||
| wantCalls int | ||
| }{ | ||
| { | ||
| name: "5 batches", | ||
| items: generateItems(50), | ||
| batchSize: 10, | ||
| workers: 3, | ||
| wantCalls: 5, | ||
| }, | ||
| { | ||
| name: "0 batches", | ||
| items: []string{}, | ||
| batchSize: 10, | ||
| workers: 3, | ||
| wantCalls: 0, | ||
| }, | ||
| { | ||
| name: "1 batch", | ||
| items: generateItems(10), | ||
| batchSize: 10, | ||
| workers: 3, | ||
| wantCalls: 1, | ||
| }, | ||
| { | ||
| name: "1 full batch, 1 partial batch", | ||
| items: generateItems(15), | ||
| batchSize: 10, | ||
| workers: 3, | ||
| wantCalls: 2, | ||
| }, | ||
| } | ||
|
|
||
| for _, tt := range tests { | ||
| t.Run(tt.name, func(t *testing.T) { | ||
| require := require.New(t) | ||
|
|
||
| var calls int64 | ||
| fn := func(ctx context.Context, no, start, end int) error { | ||
| atomic.AddInt64(&calls, 1) | ||
| return nil | ||
| } | ||
| err := ConcurrentBatch(context.Background(), len(tt.items), tt.batchSize, tt.workers, fn) | ||
|
|
||
| require.NoError(err) | ||
| require.Equal(tt.wantCalls, int(calls)) | ||
| }) | ||
| } | ||
| } |