admin: include EC volumes in bucket size reporting (#9058)

* admin: include EC volumes in bucket size reporting

The Object Store buckets page computed per-collection size by iterating
only regular volumes, so once a bucket's data was EC-encoded it silently
disappeared from the reported size — breaking usage-based billing.

Walk EcShardInfos alongside VolumeInfos in collectCollectionStats: add
raw shard bytes to PhysicalSize, and the parity-stripped value
(shardBytes * DataShardsCount / TotalShardsCount) to LogicalSize,
matching the normalization used by `weed shell` cluster.status.

* admin: derive EC logical size from shard bitmap, not constants

Use ShardsInfoFromVolumeEcShardInformationMessage + MinusParityShards
to sum actual data-shard bytes instead of scaling raw bytes by the
DataShardsCount/TotalShardsCount ratio. Keeps the data/parity split
encapsulated in the erasure_coding package and is exact when shard
sizes differ (e.g. last shard).

* admin: regression test for EC shard size aggregation

Cover the uneven-tail-shard case (data shard 9 < 1000 bytes) and the
empty-collection-name path to pin PhysicalSize/LogicalSize behavior
for collectCollectionStats against future changes.

weed/admin/dash/admin_server.go

@@ -23,6 +23,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
 	"github.com/seaweedfs/seaweedfs/weed/pb/schema_pb"
 	"github.com/seaweedfs/seaweedfs/weed/security"
+	"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
 	"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
 	"github.com/seaweedfs/seaweedfs/weed/util"
 	"github.com/seaweedfs/seaweedfs/weed/wdclient"
@@ -1698,6 +1699,17 @@ func collectCollectionStats(topologyInfo *master_pb.TopologyInfo) map[string]col
 						}
 						collectionMap[collection] = data
 					}
+					for _, ecShardInfo := range diskInfo.EcShardInfos {
+						collection := ecShardInfo.Collection
+						if collection == "" {
+							collection = "default"
+						}
+						shards := erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(ecShardInfo)
+						data := collectionMap[collection]
+						data.PhysicalSize += int64(shards.TotalSize())
+						data.LogicalSize += int64(shards.MinusParityShards().TotalSize())
+						collectionMap[collection] = data
+					}
 				}
 			}
 		}

weed/admin/dash/collect_collection_stats_test.go

@@ -0,0 +1,124 @@
+package dash
+
+import (
+	"testing"
+
+	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+)
+
+// TestCollectCollectionStatsECUnevenShards verifies that EC shards spread
+// across multiple disks are aggregated correctly, including the case where
+// the last data shard is smaller than the rest.
+func TestCollectCollectionStatsECUnevenShards(t *testing.T) {
+	// Standard 10+4 EC layout. Shards 0..9 are data, 10..13 are parity.
+	// Data shards 0..8 are 1000 bytes; data shard 9 is 500 bytes (uneven tail).
+	// Parity shards 10..13 are 1000 bytes each.
+	//
+	// Physical (raw) = 9*1000 + 500 + 4*1000 = 13500
+	// Logical (data only) = 9*1000 + 500 = 9500
+
+	nodeA := &master_pb.DataNodeInfo{
+		DiskInfos: map[string]*master_pb.DiskInfo{
+			"disk1": {
+				EcShardInfos: []*master_pb.VolumeEcShardInformationMessage{
+					{
+						Id:         42,
+						Collection: "bucket-a",
+						// Shards 0..6 held here.
+						EcIndexBits: (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4) | (1 << 5) | (1 << 6),
+						ShardSizes:  []int64{1000, 1000, 1000, 1000, 1000, 1000, 1000},
+					},
+				},
+			},
+		},
+	}
+	nodeB := &master_pb.DataNodeInfo{
+		DiskInfos: map[string]*master_pb.DiskInfo{
+			"disk1": {
+				EcShardInfos: []*master_pb.VolumeEcShardInformationMessage{
+					{
+						Id:         42,
+						Collection: "bucket-a",
+						// Shards 7..13 held here. Shard 9 (data) is the short tail.
+						EcIndexBits: (1 << 7) | (1 << 8) | (1 << 9) | (1 << 10) | (1 << 11) | (1 << 12) | (1 << 13),
+						ShardSizes:  []int64{1000, 1000, 500, 1000, 1000, 1000, 1000},
+					},
+				},
+			},
+		},
+	}
+
+	topo := &master_pb.TopologyInfo{
+		DataCenterInfos: []*master_pb.DataCenterInfo{
+			{
+				RackInfos: []*master_pb.RackInfo{
+					{
+						DataNodeInfos: []*master_pb.DataNodeInfo{nodeA, nodeB},
+					},
+				},
+			},
+		},
+	}
+
+	stats := collectCollectionStats(topo)
+
+	got, ok := stats["bucket-a"]
+	if !ok {
+		t.Fatalf("expected collection bucket-a in stats, got: %v", stats)
+	}
+
+	const wantPhysical int64 = 13500
+	const wantLogical int64 = 9500
+
+	if got.PhysicalSize != wantPhysical {
+		t.Errorf("PhysicalSize: got %d, want %d", got.PhysicalSize, wantPhysical)
+	}
+	if got.LogicalSize != wantLogical {
+		t.Errorf("LogicalSize: got %d, want %d", got.LogicalSize, wantLogical)
+	}
+}
+
+// TestCollectCollectionStatsECEmptyCollection verifies that EC shards with
+// an empty collection name are bucketed under "default".
+func TestCollectCollectionStatsECEmptyCollection(t *testing.T) {
+	topo := &master_pb.TopologyInfo{
+		DataCenterInfos: []*master_pb.DataCenterInfo{
+			{
+				RackInfos: []*master_pb.RackInfo{
+					{
+						DataNodeInfos: []*master_pb.DataNodeInfo{
+							{
+								DiskInfos: map[string]*master_pb.DiskInfo{
+									"disk1": {
+										EcShardInfos: []*master_pb.VolumeEcShardInformationMessage{
+											{
+												Id:          1,
+												Collection:  "",
+												EcIndexBits: (1 << 0) | (1 << 10),
+												ShardSizes:  []int64{2000, 2000},
+											},
+										},
+									},
+								},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+
+	stats := collectCollectionStats(topo)
+
+	got, ok := stats["default"]
+	if !ok {
+		t.Fatalf("expected collection default in stats, got: %v", stats)
+	}
+	if got.PhysicalSize != 4000 {
+		t.Errorf("PhysicalSize: got %d, want 4000", got.PhysicalSize)
+	}
+	// Only shard 0 is a data shard; shard 10 is parity.
+	if got.LogicalSize != 2000 {
+		t.Errorf("LogicalSize: got %d, want 2000", got.LogicalSize)
+	}
+}