Skip to content
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

Jump to bottom

[redshift,s3,snowflake] Improve temporary table write performance #713

Merged
merged 3 commits into from
Jun 18, 2024
Merged

[redshift,s3,snowflake] Improve temporary table write performance #713

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
99cbf9d
[] Improve performance
nathan-artie Jun 7, 2024
a66acf8
Merge branch 'master' into nv/optimize-reading-columns
Tang8330 Jun 8, 2024
b520224
Merge branch 'master' into nv/optimize-reading-columns
nathan-artie Jun 18, 2024
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
6 changes: 3 additions & 3 deletions clients/redshift/staging.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,11 +91,11 @@ func (s *Store) loadTemporaryTable(tableData *optimization.TableData, newTableID
writer.Comma = '\t'

additionalDateFmts := s.config.SharedTransferConfig.TypingSettings.AdditionalDateFormats
columns := tableData.ReadOnlyInMemoryCols().ValidColumns()
for _, value := range tableData.Rows() {
var row []string
for _, col := range tableData.ReadOnlyInMemoryCols().GetColumnsToUpdate() {
colKind, _ := tableData.ReadOnlyInMemoryCols().GetColumn(col)
castedValue, castErr := s.CastColValStaging(value[col], colKind, additionalDateFmts)
for _, col := range columns {
castedValue, castErr := s.CastColValStaging(value[col.Name()], col, additionalDateFmts)
if castErr != nil {
return "", castErr
}
Expand Down
14 changes: 5 additions & 9 deletions clients/s3/s3.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,20 +106,16 @@ func (s *Store) Merge(tableData *optimization.TableData) error {

additionalDateFmts := s.config.SharedTransferConfig.TypingSettings.AdditionalDateFormats
pw.CompressionType = parquet.CompressionCodec_GZIP
columns := tableData.ReadOnlyInMemoryCols().ValidColumns()
for _, val := range tableData.Rows() {
row := make(map[string]any)
for _, col := range tableData.ReadOnlyInMemoryCols().GetColumnsToUpdate() {
colKind, isOk := tableData.ReadOnlyInMemoryCols().GetColumn(col)
if !isOk {
return fmt.Errorf("expected column: %v to exist in readOnlyInMemoryCols(...) but it does not", col)
}

value, err := parquetutil.ParseValue(val[col], colKind, additionalDateFmts)
for _, col := range columns {
value, err := parquetutil.ParseValue(val[col.Name()], col, additionalDateFmts)
if err != nil {
return fmt.Errorf("failed to parse value, err: %w, value: %v, column: %v", err, val[col], col)
return fmt.Errorf("failed to parse value, err: %w, value: %v, column: %q", err, val[col.Name()], col.Name())
}

row[col] = value
row[col.Name()] = value
}

rowBytes, err := json.Marshal(row)
Expand Down
6 changes: 3 additions & 3 deletions clients/snowflake/staging.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,11 +121,11 @@ func (s *Store) writeTemporaryTableFile(tableData *optimization.TableData, newTa
writer.Comma = '\t'

additionalDateFmts := s.config.SharedTransferConfig.TypingSettings.AdditionalDateFormats
columns := tableData.ReadOnlyInMemoryCols().ValidColumns()
for _, value := range tableData.Rows() {
var row []string
for _, col := range tableData.ReadOnlyInMemoryCols().GetColumnsToUpdate() {
column, _ := tableData.ReadOnlyInMemoryCols().GetColumn(col)
castedValue, castErr := castColValStaging(value[col], column, additionalDateFmts)
for _, col := range columns {
castedValue, castErr := castColValStaging(value[col.Name()], col, additionalDateFmts)
if castErr != nil {
return "", castErr
}
Expand Down