Skip to content

Commit

Permalink
set max row group length and add note about issue
Browse files Browse the repository at this point in the history
  • Loading branch information
joellubi committed Jan 25, 2024
1 parent ee13822 commit 2beaccf
Showing 1 changed file with 3 additions and 0 deletions.
3 changes: 3 additions & 0 deletions go/adbc/driver/snowflake/bulk_ingestion.go
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ import (
"errors"
"fmt"
"io"
"math"
"runtime"
"strings"
"sync"
Expand Down Expand Up @@ -276,6 +277,7 @@ func newWriterProps(mem memory.Allocator, opts *ingestOptions) (*parquet.WriterP
parquet.WithDictionaryDefault(false),
// Stats won't be used since the file is dropped after ingestion completes
parquet.WithStats(false),
parquet.WithMaxRowGroupLength(math.MaxInt64),
)
arrowProps := pqarrow.NewArrowWriterProperties(pqarrow.WithAllocator(mem))

Expand Down Expand Up @@ -560,6 +562,7 @@ func (bp *bufferPool) PutBuffer(buf *bytes.Buffer) {

// Wraps an io.Writer and specifies a limit.
// Keeps track of how many bytes have been written and can report whether the limit has been exceeded.
// TODO(ARROW-39789): We prefer to use RowGroupTotalBytesWritten on the ParquetWriter, but there seems to be a discrepency with the count.
type limitWriter struct {
w io.Writer
limit int
Expand Down

0 comments on commit 2beaccf

Please sign in to comment.