feat(balance): replica placement validation for volume moves (#8622)

* feat(balance): add replica placement validation for volume moves

When the volume balance detection proposes moving a volume, validate
that the move does not violate the volume's replication policy (e.g.,
ReplicaPlacement=010 requires replicas on different racks). If the
preferred destination violates the policy, fall back to score-based
planning; if that also violates, skip the volume entirely.

- Add ReplicaLocation type and VolumeReplicaMap to ClusterInfo
- Build replica map from all volumes before collection filtering
- Port placement validation logic from command_volume_fix_replication.go
- Thread replica map through collectVolumeMetrics call chain
- Add IsGoodMove check in createBalanceTask before destination use

* address PR review: extract validation closure, add defensive checks

- Extract validateMove closure to eliminate duplicated ReplicaLocation
  construction and IsGoodMove calls
- Add defensive check for empty replica map entries (len(replicas) == 0)
- Add bounds check for int-to-byte cast on ExpectedReplicas (0-255)

* address nitpick: rp test helper accepts *testing.T and fails on error

Prevents silent failures from typos in replica placement codes.

* address review: add composite replica placement tests (011, 110)

Test multi-constraint placement policies where both rack and DC
rules must be satisfied simultaneously.

* address review: use struct keys instead of string concatenation

Replace string-concatenated map keys with typed rackKey/nodeKey
structs to eliminate allocations and avoid ambiguity if IDs
contain spaces.

* address review: simplify bounds check, log fallback error, guard source

- Remove unreachable ExpectedReplicas < 0 branch (outer condition
  already guarantees > 0), fold bounds check into single condition
- Log error from planBalanceDestination in replica validation fallback
- Return false from IsGoodMove when sourceNodeID not found in
  existing replicas (inconsistent cluster state)

* address review: use slices.Contains instead of hand-rolled helpers

Replace isAmongDC and isAmongRack with slices.Contains from the
standard library, reducing boilerplate.
This commit is contained in:
Chris Lu
2026-03-13 17:39:25 -07:00
committed by GitHub
parent 47ddf05d95
commit 8056b702ba
9 changed files with 364 additions and 30 deletions

View File

@@ -10,6 +10,7 @@ import (
"github.com/seaweedfs/seaweedfs/weed/admin/topology"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/base"
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/util"
"github.com/seaweedfs/seaweedfs/weed/worker/types"
@@ -389,6 +390,46 @@ func createBalanceTask(diskType string, selectedVolume *types.VolumeHealthMetric
}
}
// Validate move against replica placement policy
if selectedVolume.ExpectedReplicas > 0 && selectedVolume.ExpectedReplicas <= 255 && clusterInfo.VolumeReplicaMap != nil {
rpBytes, rpErr := super_block.NewReplicaPlacementFromByte(byte(selectedVolume.ExpectedReplicas))
if rpErr == nil && rpBytes.HasReplication() {
replicas := clusterInfo.VolumeReplicaMap[selectedVolume.VolumeID]
if len(replicas) == 0 {
glog.V(1).Infof("BALANCE [%s]: No replica locations found for volume %d, skipping placement validation",
diskType, selectedVolume.VolumeID)
} else {
validateMove := func(plan *topology.DestinationPlan) bool {
if plan == nil {
return false
}
target := types.ReplicaLocation{
DataCenter: plan.TargetDC,
Rack: plan.TargetRack,
NodeID: plan.TargetNode,
}
return IsGoodMove(rpBytes, replicas, selectedVolume.Server, target)
}
if !validateMove(destinationPlan) {
glog.V(1).Infof("BALANCE [%s]: Destination %s violates replica placement for volume %d (rp=%03d), falling back",
diskType, destinationPlan.TargetNode, selectedVolume.VolumeID, selectedVolume.ExpectedReplicas)
// Fall back to score-based planning
destinationPlan, err = planBalanceDestination(clusterInfo.ActiveTopology, selectedVolume)
if err != nil {
glog.Warningf("BALANCE [%s]: Failed to plan fallback destination for volume %d: %v", diskType, selectedVolume.VolumeID, err)
return nil, ""
}
if !validateMove(destinationPlan) {
glog.V(1).Infof("BALANCE [%s]: Fallback destination %s also violates replica placement for volume %d",
diskType, destinationPlan.TargetNode, selectedVolume.VolumeID)
return nil, ""
}
}
}
}
}
// Find the actual disk containing the volume on the source server
sourceDisk, found := base.FindVolumeDisk(clusterInfo.ActiveTopology, selectedVolume.VolumeID, selectedVolume.Collection, selectedVolume.Server)
if !found {