Github-Mirror/seaweedfs
1
0 Fork 0
mirror of https://github.com/seaweedfs/seaweedfs.git synced 2026-11-13 15:29:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

volume: let evacuation proceed on a server in maintenance mode (#11145)

Browse Source 
Maintenance mode exists to fence a volume server so it can be evacuated
without taking new writes (#7977), but the gate added in #8115 also
rejected the RPCs evacuation issues against the source: VolumeMarkReadonly
(the first step of every move, and the failure reported in #11066),
VolumeDelete (the last step), and VolumeEcShardsDelete (the last step for
EC shards). volumeServer.evacuate, volume.move and ec.balance therefore
all failed on exactly the server they were meant to drain.

Those three RPCs only remove data or restrict the server further, the same
class as DeleteCollection and the unmount RPCs that were never gated, so
they are exempted from the maintenance check in both the Go and Rust
volume servers. Everything that adds data or reopens the server for
writes (AllocateVolume, WriteNeedleBlob, BatchDelete, VolumeCopy,
ReceiveFile, EC generate/copy/rebuild, vacuum, tiering, VolumeMarkWritable)
stays blocked. A side effect is that scrub can now fence broken volumes
readonly on a server already in maintenance.

Fixes #11066

Generated with [Devin](https://devin.ai)

Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Chris LuandDevin authored and GitHub committed 2026-09-03 18:39:45 -07:00
1 parent c9c6e6fb1d
commit 24b8646ec3
8 files changed
+198 -61
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

test/volume_server/grpc/admin_lifecycle_test.go
+9 -15
View File
@@ -179,7 +179,9 @@ func TestAllocateDuplicateAndMountUnmountMissingVariants(t *testing.T) {
}
}
func TestMaintenanceModeRejectsVolumeDelete(t *testing.T) {
// Evacuating a server in maintenance mode ends each move by deleting the source
// volume, so VolumeDelete must stay available in that mode (issue #11066).
func TestMaintenanceModeAllowsVolumeDelete(t *testing.T) {
if testing.Short() {
t.Skip("skipping integration test in short mode")
}
@@ -194,22 +196,14 @@ func TestMaintenanceModeRejectsVolumeDelete(t *testing.T) {
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
stateResp, err := client.GetState(ctx, &volume_server_pb.GetStateRequest{})
if err != nil {
t.Fatalf("GetState failed: %v", err)
}
_, err = client.SetState(ctx, &volume_server_pb.SetStateRequest{
State: &volume_server_pb.VolumeServerState{Maintenance: true, Version: stateResp.GetState().GetVersion()},
})
if err != nil {
t.Fatalf("SetState maintenance=true failed: %v", err)
framework.EnableMaintenanceMode(t, ctx, client)
if _, err := client.VolumeDelete(ctx, &volume_server_pb.VolumeDeleteRequest{VolumeId: volumeID, OnlyEmpty: true}); err != nil {
t.Fatalf("VolumeDelete should succeed in maintenance mode, got: %v", err)
}
_, err = client.VolumeDelete(ctx, &volume_server_pb.VolumeDeleteRequest{VolumeId: volumeID, OnlyEmpty: true})
_, err := client.VolumeStatus(ctx, &volume_server_pb.VolumeStatusRequest{VolumeId: volumeID})
if err == nil {
t.Fatalf("VolumeDelete should fail when maintenance mode is enabled")
}
if !strings.Contains(err.Error(), "maintenance mode") {
t.Fatalf("expected maintenance mode error, got: %v", err)
t.Fatalf("VolumeStatus should fail once the volume is deleted")
}
}