astelm/minio
1
0
Fork 0
mirror of https://github.com/pgsty/minio.git synced 2026-11-10 09:35:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(batch): pause transient authorization failures with owned retries

Browse Source 
Signed-off-by: Feng Ruohang <rh@vonng.com>
This commit is contained in:
Feng Ruohang
2026-11-07 00:42:02 +08:00
parent ade15ea5d0
commit bdd17b0f47
14 changed files with 911 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/batch-authz-review6_test.go
+23 -4
View File
@@ -75,9 +75,8 @@ func (w batchWalkError) Walk(context.Context, string, string, chan<- itemOrErr[O
return w.err
}
// A listing that fails before it returns anything fails the run, as a
// listing error in the results does, and the job is left to a later run.
func TestBatchReviewExpireWalkErrorFailsRun(t *testing.T) {
// A listing outage pauses the run, as a streamed listing error does.
func TestBatchReviewExpireWalkErrorPausesRun(t *testing.T) {
f := newBatchAuthzFixture(t)
rec, job := f.submit(t, globalActiveCred, f.expireYAML("data/"))
if job == nil {
@@ -87,7 +86,7 @@ func TestBatchReviewExpireWalkErrorFailsRun(t *testing.T) {
if err := job.Expire.Start(f.ctx, batchWalkError{ObjectLayer: f.obj, err: listErr}, *job); !errors.Is(err, listErr) {
t.Fatalf("start returned %v, want %v", err, listErr)
}
if ri := f.jobInfo(t, job); !ri.Failed || ri.Complete {
if ri := f.jobInfo(t, job); ri.Failed || ri.Complete || ri.PausedReason == "" {
t.Fatalf("failed listing: complete=%v failed=%v", ri.Complete, ri.Failed)
}
}
@@ -251,6 +250,26 @@ func TestBatchReviewRotationLeavesMovingSource(t *testing.T) {
if after.UserDefined[crypto.MetaSealedKeyS3] != beforeInfo.UserDefined[crypto.MetaSealedKeyS3] {
t.Fatal("rotation rewrote a draining pool")
}
// The job pauses and resumes in-process once the selected pool stops moving.
job := BatchJobRequest{ID: "rotation-moving-resume", Started: UTCNow(), Submitter: batchRootSubmitter(t), KeyRotate: &r}
batchTestJobPool(t.Context(), t, z)
if err := r.Start(t.Context(), z, job); !isBatchJobUnavailable(err) {
t.Fatalf("moving job did not pause: %v", err)
}
ri := &batchJobInfo{}
mustIAM(t, ri.load(t.Context(), z, job))
if ri.PausedReason == "" || ri.Failed || ri.Complete || ri.Object != "" || ri.ObjectsFailed != 0 {
t.Fatalf("moving job report: %+v", ri)
}
z.poolMetaMutex.Lock()
z.poolMeta.Pools[0].Decommission = nil
z.poolMetaMutex.Unlock()
mustIAM(t, r.Start(t.Context(), z, job))
mustIAM(t, ri.load(t.Context(), z, job))
if !ri.Complete || ri.Failed || ri.PausedReason != "" || ri.Objects != 1 {
t.Fatalf("resumed rotation: %+v", ri)
}
}
// Once a move copied a version, the rotation leaves it to a later run, so the