IMPORT INTO + global sort didn't handle UK conflict correctly #59650
Description
Bug Report
Please answer these questions before submitting your issue. Thanks!
1. Minimal reproduce step (Required)
diff --git a/tests/realtikvtest/importintotest4/global_sort_test.go b/tests/realtikvtest/importintotest4/global_sort_test.go
index 6734ff65ee..3563ad5c89 100644
--- a/tests/realtikvtest/importintotest4/global_sort_test.go
+++ b/tests/realtikvtest/importintotest4/global_sort_test.go
@@ -156,3 +156,28 @@ func (s *mockGCSSuite) TestGlobalSortMultiFiles() {
s.tk.MustQuery(importSQL)
s.tk.MustQuery("select * from t").Sort().Check(testkit.Rows(allData...))
}
+
+func (s *mockGCSSuite) TestGlobalSortUniqueKeyConflict() {
+ var allData []string
+ for i := 0; i < 10; i++ {
+ var content []byte
+ keyCnt := 1000
+ for j := 0; j < keyCnt; j++ {
+ idx := i*keyCnt + j
+ content = append(content, []byte(fmt.Sprintf("%d,test-%d\n", idx, j))...)
+ }
+ s.server.CreateObject(fakestorage.Object{
+ ObjectAttrs: fakestorage.ObjectAttrs{BucketName: "gs-multi-files-uk", Name: fmt.Sprintf("t.%d.csv", i)},
+ Content: content,
+ })
+ }
+ slices.Sort(allData)
+ s.prepareAndUseDB("gs_multi_files")
+ s.server.CreateBucketWithOpts(fakestorage.CreateBucketOpts{Name: "sorted"})
+ s.tk.MustExec("create table t (a bigint primary key , b varchar(100) unique key);")
+ // 1 subtask, encoding 10 files using 4 threads.
+ sortStorageURI := fmt.Sprintf("gs://sorted/gs_multi_files?endpoint=%s", gcsEndpoint)
+ importSQL := fmt.Sprintf(`import into t FROM 'gs://gs-multi-files-uk/t.*.csv?endpoint=%s'
+ with cloud_storage_uri='%s', __max_engine_size='1', thread=8`, gcsEndpoint, sortStorageURI)
+ s.tk.MustQuery(importSQL)
+}2. What did you expect to see? (Required)
has reasonable output
3. What did you see instead (Required)
in the log we can find
[2025/02/19 20:55:53.969 +08:00] [WARN] [local.go:1255] ["meet retryable error when writing to TiKV"] [category=ddl-ingest] [error="peer 31, store 1, region 30, epoch conf_ver:1 version:11 , when send data: rpc error: code = Unknown desc = EngineTraits(Engine(Status { code: IoError, sub_code: None, sev: NoError, state: \"Invalid argument: Keys must be added in strict ascending order.\" }))"] ["job stage"=needRescan]