mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-31 01:10:41 +01:00
Javier de la Torreanduser.email
edf2b0f5ee
* iceberg maintenance: an unreadable parquet file fails the job, not the process parquet.NewReader panics on any file it cannot open (wrong magic, a truncated footer, zero bytes), and parquet-go's row decoder panics on a corrupt page under a valid footer. Maintenance runs in the worker's goroutines with no recover, so one bad delete or data file in any table ended the whole process. - Every parquet open in compaction goes through newParquetReader, which opens with parquet.OpenFile and returns the error. - A panic while decoding a delete file or a data file's rows is recovered into an error naming the file (recoverRead/guardRead). - As a backstop, detection recovers per table and Execute per operation: the table is skipped or the operation fails, and the worker keeps running. A failed delete file still fails the table's compaction (no commit), as a read error did before; a failed data file still skips only its bin. * iceberg maintenance: test a corrupt page inside a merge fails it naming the file * iceberg maintenance: assert a skipped bin's files stay in the snapshot --------- Co-authored-by: user.email <chrislusf@users.noreply.github.com>
23 lines
657 B
Go
23 lines
657 B
Go
package iceberg
|
|
|
|
import (
|
|
"errors"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestGuardReadTurnsAPanicIntoAnError(t *testing.T) {
|
|
v, err := guardRead("data/x.parquet", func() (int, error) {
|
|
var s []int
|
|
return s[3], nil // index out of range
|
|
})
|
|
if v != 0 || err == nil || !strings.Contains(err.Error(), "data/x.parquet") || !strings.Contains(err.Error(), "panic") {
|
|
t.Fatalf("v = %d, err = %v: want a zero value and an error naming the file", v, err)
|
|
}
|
|
|
|
want := errors.New("plain error")
|
|
if _, err := guardRead("data/y.parquet", func() (int, error) { return 0, want }); err != want {
|
|
t.Fatalf("err = %v, want the function's own error unchanged", err)
|
|
}
|
|
}
|