Skip to content

SeaweedFS is a distributed storage system for object storage (S3), file systems, Iceberg table buckets, and Lance vector buckets, designed to handle billions of files with O(1) disk access and effortless horizontal scaling.

Treat co-located volume servers as one fault domain when balancing and allocating (#9854)

Chris Luf0d2a0d417dc
diff --git a/weed/admin/topology/capacity.go b/weed/admin/topology/capacity.go
index a4ad150b4c..4d3eaf4b9b 100644
--- a/weed/admin/topology/capacity.go
+++ b/weed/admin/topology/capacity.go
@@ -162,6 +162,7 @@ func (at *ActiveTopology) GetDisksWithEffectiveCapacity(taskType TaskType, exclu
// Create a new DiskInfo with current capacity information
diskCopy := DiskInfo{
NodeID: disk.DiskInfo.NodeID,
+ Address: disk.DiskInfo.Address,
DiskID: disk.DiskInfo.DiskID,
DiskType: disk.DiskInfo.DiskType,
DataCenter: disk.DiskInfo.DataCenter,
@@ -226,6 +227,7 @@ func (at *ActiveTopology) GetDisksForPlanning(taskType TaskType, excludeNodeID s
// Create a new DiskInfo with planning information
diskCopy := DiskInfo{
NodeID: disk.DiskInfo.NodeID,
+ Address: disk.DiskInfo.Address,
DiskID: disk.DiskInfo.DiskID,
DiskType: disk.DiskInfo.DiskType,
DataCenter: disk.DiskInfo.DataCenter,
diff --git a/weed/admin/topology/structs.go b/weed/admin/topology/structs.go
index ab4941888a..a8417d7c65 100644
--- a/weed/admin/topology/structs.go
+++ b/weed/admin/topology/structs.go
@@ -43,6 +43,7 @@ type taskState struct {
// DiskInfo represents a disk with its current state and ongoing tasks (public for external access)
type DiskInfo struct {
NodeID string `json:"node_id"`
+ Address string `json:"address"` // volume server ip:port; NodeID may be an opaque id, so this is the source for the physical-machine host
DiskID uint32 `json:"disk_id"`
DiskType string `json:"disk_type"`
DataCenter string `json:"data_center"`
diff --git a/weed/admin/topology/topology_management.go b/weed/admin/topology/topology_management.go
index 05acecde8f..72fad39f55 100644
--- a/weed/admin/topology/topology_management.go
+++ b/weed/admin/topology/topology_management.go
@@ -87,6 +87,7 @@ func (at *ActiveTopology) UpdateTopology(topologyInfo *master_pb.TopologyInfo) e
disk := &activeDisk{
DiskInfo: &DiskInfo{
NodeID: nodeInfo.Id,
+ Address: nodeInfo.Address,
DiskID: perDisk.DiskId,
DiskType: diskType,
DataCenter: dc.Id,
diff --git a/weed/plugin/worker/volume_metrics.go b/weed/plugin/worker/volume_metrics.go
index 8452f40c91..0a9ff97a6b 100644
--- a/weed/plugin/worker/volume_metrics.go
+++ b/weed/plugin/worker/volume_metrics.go
@@ -164,6 +164,7 @@ func buildVolumeMetrics(
DataCenter: dc.Id,
Rack: rack.Id,
NodeID: node.Id,
+ Host: pb.NewServerAddressFromDataNode(node).ToHost(),
})
if collectionRegex != nil && !collectionRegex.MatchString(volume.Collection) {
diff --git a/weed/shell/command_ec_common.go b/weed/shell/command_ec_common.go
index 1996414429..d1066d10f8 100644
--- a/weed/shell/command_ec_common.go
+++ b/weed/shell/command_ec_common.go
@@ -802,6 +802,9 @@ func toBalancerTopology(ecNodes []*EcNode, collections []string, diskType types.
for _, en := range ecNodes {
rackKey := string(en.dc) + ":" + string(en.rack)
node := topo.AddNode(en.info.Id, string(en.dc), rackKey, en.freeEcSlot)
+ // Group by physical machine (host) so shards spread across machines, not just
+ // nodes; the id stays the node identity used for moves.
+ node.SetHost(pb.NewServerAddressFromDataNode(en.info).ToHost())
for diskId, d := range en.disks {
node.AddDisk(diskId, d.diskType, d.freeEcSlots, d.ecShardCount)
}
diff --git a/weed/shell/command_volume_balance.go b/weed/shell/command_volume_balance.go
index 616e30b35c..d3c88df9b1 100644
--- a/weed/shell/command_volume_balance.go
+++ b/weed/shell/command_volume_balance.go
@@ -553,6 +553,16 @@ func isGoodMove(placement *super_block.ReplicaPlacement, existingReplicas []*Vol
}
}
+ // Don't move a replica onto a machine (host) that already holds one of this
+ // volume's replicas: servers sharing a host are one fault domain, so both would
+ // die together. Best-effort -- skip and let balancing try the next target.
+ targetHost := pb.NewServerAddressFromDataNode(targetNode.info).ToHost()
+ for _, replica := range existingReplicasExceptSourceNode {
+ if pb.NewServerAddressFromDataNode(replica.location.dataNode).ToHost() == targetHost {
+ return false
+ }
+ }
+
// target location
targetLocation := location{
dc: targetNode.dc,
diff --git a/weed/shell/command_volume_balance_test.go b/weed/shell/command_volume_balance_test.go
index 35600e2b82..fb037e4f82 100644
--- a/weed/shell/command_volume_balance_test.go
+++ b/weed/shell/command_volume_balance_test.go
@@ -227,6 +227,41 @@ func TestIsGoodMove(t *testing.T) {
targetLocation: location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "dn4"}},
expected: false,
},
+
+ {
+ // rep 001 allows two copies in one rack; replica-placement alone would
+ // permit this, but the target shares a host with another replica, so the
+ // machine anti-affinity must reject it.
+ name: "test 001 reject move onto a machine already holding a replica",
+ replication: "001",
+ replicas: []*VolumeReplica{
+ {
+ location: &location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.1:8080"}},
+ },
+ {
+ location: &location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.2:8080"}},
+ },
+ },
+ sourceLocation: location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.2:8080"}},
+ targetLocation: location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.1:8081"}},
+ expected: false,
+ },
+
+ {
+ name: "test 001 allow move onto a different machine in the rack",
+ replication: "001",
+ replicas: []*VolumeReplica{
+ {
+ location: &location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.1:8080"}},
+ },
+ {
+ location: &location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.2:8080"}},
+ },
+ },
+ sourceLocation: location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.2:8080"}},
+ targetLocation: location{"dc1", "r1", &master_pb.DataNodeInfo{Id: "10.0.0.3:8080"}},
+ expected: true,
+ },
}
for _, tt := range tests {
diff --git a/weed/storage/erasure_coding/ecbalancer/balancer.go b/weed/storage/erasure_coding/ecbalancer/balancer.go
index 3793df83c6..7679dada8a 100644
--- a/weed/storage/erasure_coding/ecbalancer/balancer.go
+++ b/weed/storage/erasure_coding/ecbalancer/balancer.go
@@ -32,9 +32,11 @@ type volKey struct {
// Node is a volume server in the snapshot. Fields are set through the builder
// methods; only its identity is read back (via Move).
type Node struct {
- id string
- dc string
- rack string // composite rack key (e.g. "dc1:rack1")
+ id string
+ host string // physical machine (host/IP); nodes sharing a host are one fault domain
+ dc string
+ rack string // composite rack key (e.g. "dc1:rack1")
+
freeSlots int
disks map[uint32]*disk
shards map[volKey]*volumeShards
@@ -116,6 +118,7 @@ func NewTopology() *Topology {
func (t *Topology) AddNode(id, dc, rackKey string, freeSlots int) *Node {
n := &Node{
id: id,
+ host: id, // default: each node is its own machine until SetHost overrides
dc: dc,
rack: rackKey,
freeSlots: freeSlots,
@@ -126,6 +129,14 @@ func (t *Topology) AddNode(id, dc, rackKey string, freeSlots int) *Node {
return n
}
+// SetHost sets the physical machine (host/IP) a node runs on; nodes sharing a host
+// are one fault domain. Defaults to the node id (one machine per node) if unset.
+func (n *Node) SetHost(host string) {
+ if host != "" {
+ n.host = host
+ }
+}
+
// AddDisk registers a physical disk. shardCount is the disk's total EC shard
// count across all volumes (used for disk scoring); freeSlots is the per-disk
// free EC shard slots.
@@ -188,11 +199,13 @@ func Plan(topo *Topology, opts Options) []Move {
}
collections := make([]string, 0, len(byCollection))
dataShardsByCollection := make(map[string]int)
+ parityShardsByCollection := make(map[string]int)
for c := range byCollection {
collections = append(collections, c)
sort.Slice(byCollection[c], func(i, j int) bool { return byCollection[c][i].vid < byCollection[c][j].vid })
- d, _ := ratio(c)
+ d, p := ratio(c)
dataShardsByCollection[c] = d
+ parityShardsByCollection[c] = p
}
sort.Strings(collections)
@@ -217,7 +230,7 @@ func Plan(topo *Topology, opts Options) []Move {
}
}
- all = append(all, detectGlobalImbalance(nodes, racks, opts.DiskType, opts.ImbalanceThreshold, dataShardsByCollection, opts.GlobalMaxMovesPerRack, opts.GlobalUtilizationBased)...)
+ all = append(all, detectGlobalImbalance(nodes, racks, opts.DiskType, opts.ImbalanceThreshold, dataShardsByCollection, parityShardsByCollection, opts.GlobalMaxMovesPerRack, opts.GlobalUtilizationBased)...)
out := make([]Move, 0, len(all))
for _, m := range all {
@@ -405,10 +418,15 @@ func balanceShardTypeAcrossRacks(vk volKey, nodes map[string]*Node, racks map[st
}
func pickNodeInRack(r *rack, vk volKey, rp *super_block.ReplicaPlacement) *Node {
+ return pickBestNodeForVolume(sortedNodeSlice(r.nodes), vk, rp)
+}
+
+// pickBestNodeForVolume returns the node with the fewest shards of the volume that
+// has a free slot and is under the SameRackCount cap, or nil.
+func pickBestNodeForVolume(nodes []*Node, vk volKey, rp *super_block.ReplicaPlacement) *Node {
var best *Node
bestCount := -1
- for _, id := range sortedNodeKeys(r.nodes) {
- node := r.nodes[id]
+ for _, node := range nodes {
if node.freeSlots <= 0 {
continue
}
@@ -423,43 +441,152 @@ func pickNodeInRack(r *rack, vk volKey, rp *super_block.ReplicaPlacement) *Node
return best
}
-// detectWithinRackImbalance spreads a volume's shards across the nodes of each
-// rack, again data then parity with anti-affinity.
+// detectWithinRackImbalance spreads a volume's shards within each rack, data then
+// parity with anti-affinity. It spreads across machines (the fault domain) only when
+// the rack has enough that each can stay within EC's parity tolerance; otherwise
+// machine spreading buys no durability and would only fight capacity (e.g. cramming
+// a 2-server box while a 12-server box sits idle), so it spreads across nodes and
+// lets capacity/global balancing decide.
+// The imbalance threshold gates only the node fallback (cosmetic load distribution
+// that should defer to the global utilization phase). Machine spreading bypasses it:
+// the even cap is a durability bound, and a relative-skew gate would skip e.g. a
+// 5/4/3 machine layout for a 10+4 volume ((5-3)/4 = 0.5), leaving 5 shards -- past
+// parity -- on one machine.
func detectWithinRackImbalance(vk volKey, nodes map[string]*Node, racks map[string]*rack, diskType string, threshold float64, dataShards, parityShards int, rp *super_block.ReplicaPlacement) []*move {
var moves []*move
for _, rackID := range sortedKeys(racks) {
r := racks[rackID]
- if len(r.nodes) <= 1 {
- continue
+ machines := buildMachines(r)
+ numMachines, numNodes := len(machines), len(r.nodes)
+
+ // Feasibility is about this rack's share of the volume (cross-rack spreading
+ // already moved the rest elsewhere), not the whole volume: a rack holding 7 of
+ // a 10+4 volume's shards can keep each of 2 machines within parity even though
+ // all 14 could not.
+ rackShards := rackVolumeShardCount(r, vk)
+ if numMachines > 1 && numMachines < numNodes && parityShards > 0 && ceilDivide(rackShards, numMachines) <= parityShards {
+ moves = append(moves, withinRackMachineSpread(vk, r, machines, diskType, dataShards, rp)...)
+ } else if numNodes > 1 {
+ moves = append(moves, withinRackNodeSpread(vk, r, diskType, threshold, dataShards, rp)...)
}
+ }
+ return moves
+}
- numNodes := len(r.nodes)
- // Gate on per-type spread across the rack's nodes (see cross-rack phase).
- gateData, gateParity := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
- if !typeImbalanced(gateData, numNodes, threshold) && !typeImbalanced(gateParity, numNodes, threshold) {
- continue
+// withinRackMachineSpread spreads a volume's shards across a rack's machines so no
+// machine holds more than ceil(rackShards/numMachines). EC recovers from any loss
+// within parity regardless of shard type, so what matters per machine is the
+// combined count, not data and parity separately: spreading the two independently
+// can stack their remainders onto one machine (ceil(d/M)+ceil(p/M) > ceil(total/M))
+// and push it past parity. Data/parity anti-affinity is kept at the disk level by
+// pickBestDiskOnNode. With one node per machine this reduces to the node spread.
+func withinRackMachineSpread(vk volKey, r *rack, machines map[string][]*Node, diskType string, dataShards int, rp *super_block.ReplicaPlacement) []*move {
+ machineKeys := sortedKeys(machines)
+ shardsPerMachine := make(map[string][]int, len(machines))
+ total := 0
+ for _, host := range machineKeys {
+ for _, n := range machines[host] {
+ if info, ok := n.shards[vk]; ok {
+ for sid := range info.shardBits.All() {
+ shardsPerMachine[host] = append(shardsPerMachine[host], int(sid))
+ }
+ }
}
- nodeShardCount := countShardsByNode(vk, r.nodes)
-
- dataPerNode, _ := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
- moves = append(moves, balanceShardTypeAcrossNodes(vk, r, diskType, dataShards,
- dataPerNode, nodeShardCount, ceilDivide(sumLens(dataPerNode), numNodes), nil, rp)...)
+ sort.Ints(shardsPerMachine[host])
+ total += len(shardsPerMachine[host])
+ }
+ if total == 0 {
+ return nil
+ }
+ // Cap = even share. The move loop below sheds only what exceeds it, so a balanced
+ // rack is a no-op while any machine over the cap (a parity risk) is always fixed.
+ maxPerMachine := ceilDivide(total, len(machines))
+ if maxPerMachine < 1 {
+ maxPerMachine = 1
+ }
- dataPerNode, parityPerNode := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
- antiAffinity := make(map[string]bool)
- for nodeID, shards := range dataPerNode {
- if len(shards) > 0 {
- antiAffinity[nodeID] = true
+ type pending struct {
+ shardID int
+ src *Node
+ }
+ var toMove []pending
+ for _, host := range machineKeys {
+ shards := shardsPerMachine[host]
+ for i := 0; i < len(shards)-maxPerMachine; i++ {
+ if src := nodeHoldingShard(machines[host], vk, shards[i]); src != nil {
+ toMove = append(toMove, pending{shards[i], src})
}
}
- moves = append(moves, balanceShardTypeAcrossNodes(vk, r, diskType, dataShards,
- parityPerNode, nodeShardCount, ceilDivide(sumLens(parityPerNode), numNodes), antiAffinity, rp)...)
}
+ var moves []*move
+ for _, pm := range toMove {
+ // A machine is a viable target only if a node on it can actually take the
+ // shard (free slot, under SameRackCount), so a capped machine is skipped
+ // rather than settled on and the move dropped.
+ destHost, ok := pickTarget(machineKeys, shardsPerMachine, maxPerMachine, nil,
+ func(h string) bool { return h != pm.src.host && pickBestNodeForVolume(machines[h], vk, rp) != nil },
+ func(string) bool { return true })
+ if !ok {
+ continue
+ }
+ destNode := pickBestNodeForVolume(machines[destHost], vk, rp)
+ if destNode == nil {
+ continue
+ }
+ destDisk := pickBestDiskOnNode(destNode, vk, diskType, pm.shardID, dataShards)
+ moves = append(moves, &move{
+ volumeID: vk.vid,
+ shardID: pm.shardID,
+ collection: vk.collection,
+ source: pm.src,
+ sourceDisk: shardDiskID(pm.src, vk, pm.shardID),
+ target: destNode,
+ targetDisk: destDisk,
+ phase: "within_rack",
+ })
+ releaseShard(pm.src, vk, pm.shardID)
+ reserveShard(destNode, vk, pm.shardID, destDisk)
+ shardsPerMachine[destHost] = append(shardsPerMachine[destHost], pm.shardID)
+ shardsPerMachine[pm.src.host] = removeInt(shardsPerMachine[pm.src.host], pm.shardID)
+ pm.src.freeSlots++
+ destNode.freeSlots--
+ }
return moves
}
+// withinRackNodeSpread spreads a volume's shards evenly across a rack's nodes (data
+// then parity, parity anti-affine to data-bearing nodes). This fallback runs when
+// machine fault tolerance is unachievable, so it is cosmetic load distribution:
+// honor the imbalance threshold and defer to the global utilization phase rather than
+// churning a count-balancing move that can worsen utilization (machine spreading,
+// which is durability, bypasses the threshold instead).
+func withinRackNodeSpread(vk volKey, r *rack, diskType string, threshold float64, dataShards int, rp *super_block.ReplicaPlacement) []*move {
+ numNodes := len(r.nodes)
+ gateData, gateParity := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
+ if !typeImbalanced(gateData, numNodes, threshold) && !typeImbalanced(gateParity, numNodes, threshold) {
+ return nil
+ }
+ nodeShardCount := countShardsByNode(vk, r.nodes)
+
+ dataPerNode, _ := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
+ moves := balanceShardTypeAcrossNodes(vk, r, diskType, dataShards,
+ dataPerNode, nodeShardCount, ceilDivide(sumLens(dataPerNode), numNodes), nil, rp)
+
+ dataPerNode, parityPerNode := shardsByGroup(vk, r.nodes, dataShards, func(n *Node) string { return n.id })
+ antiAffinity := make(map[string]bool)
+ for nodeID, shards := range dataPerNode {
+ if len(shards) > 0 {
+ antiAffinity[nodeID] = true
+ }
+ }
+ return append(moves, balanceShardTypeAcrossNodes(vk, r, diskType, dataShards,
+ parityPerNode, nodeShardCount, ceilDivide(sumLens(parityPerNode), numNodes), antiAffinity, rp)...)
+}
+
+// balanceShardTypeAcrossNodes spreads one shard type of a volume across a rack's
+// nodes, moving from nodes over maxPerNode to under-loaded ones.
func balanceShardTypeAcrossNodes(vk volKey, r *rack, diskType string, dataShards int, shardsPerNode map[string][]int, nodeShardCount map[string]int, maxPerNode int, antiAffinity map[string]bool, rp *super_block.ReplicaPlacement) []*move {
if maxPerNode < 1 {
maxPerNode = 1
@@ -523,7 +650,7 @@ func balanceShardTypeAcrossNodes(vk volKey, r *rack, diskType string, dataShards
// detectGlobalImbalance balances total EC shard load across the nodes of each
// rack (across all volumes), using utilization ratios so heterogeneous-capacity
// nodes are compared fairly.
-func detectGlobalImbalance(nodes map[string]*Node, racks map[string]*rack, diskType string, threshold float64, dataShardsByCollection map[string]int, maxMovesPerRack int, byUtilization bool) []*move {
+func detectGlobalImbalance(nodes map[string]*Node, racks map[string]*rack, diskType string, threshold float64, dataShardsByCollection, parityShardsByCollection map[string]int, maxMovesPerRack int, byUtilization bool) []*move {
var moves []*move
for _, rackID := range sortedKeys(racks) {
@@ -531,6 +658,7 @@ func detectGlobalImbalance(nodes map[string]*Node, racks map[string]*rack, diskT
if len(r.nodes) <= 1 {
continue
}
+ rackMachineCount := len(buildMachines(r))
nodeShardCounts := make(map[string]int)
totalShards := 0
@@ -602,9 +730,8 @@ func detectGlobalImbalance(nodes map[string]*Node, racks map[string]*rack, diskT
break
}
- // Prefer moving a shard of a volume the destination does not hold at
- // all (pass 0) before adding another shard of an already-present volume
- // (pass 1), to keep each volume's shards spread across nodes.
+ // Prefer a volume absent from the destination's machine (pass 0) before
+ // adding to one already there (pass 1), to keep volumes spread.
moved := false
for pass := 0; pass < 2 && !moved; pass++ {
for _, vk := range sortedVolumeKeys(maxNode.shards) {
@@ -613,12 +740,26 @@ func detectGlobalImbalance(nodes map[string]*Node, racks map[string]*rack, diskT
}
info := maxNode.shards[vk]
minInfo := minNode.shards[vk]
- volumeOnMin := minInfo != nil && minInfo.shardBits != 0
- if pass == 0 && volumeOnMin {
- continue // pass 0: only volumes absent from the destination
+ volumeOnMinMachine := machineHoldsVolume(r, minNode.host, vk)
+ if pass == 0 && volumeOnMinMachine {
+ continue // pass 0: only volumes absent from the destination machine
}
- if pass == 1 && !volumeOnMin {
- continue // pass 1: only volumes already on the destination
+ if pass == 1 {
+ if !volumeOnMinMachine {
+ continue
+ }
+ // Protect the volume's machine spread only where it's achievable
+ // (enough machines for this rack's shards to each stay within
+ // parity); there a cross-machine load move is allowed only if it
+ // doesn't raise the destination machine's count past the source's.
+ // Where it isn't achievable, capacity rules and any leveling move
+ // is fine. Feasibility uses the rack's shards, not the whole volume.
+ parity := parityShardsByCollection[vk.collection]
+ spreadFeasible := parity > 0 && rackMachineCount >= ceilDivide(rackVolumeShardCount(r, vk), parity)
+ if spreadFeasible && minNode.host != maxNode.host &&
+ machineVolumeCount(r, minNode.host, vk) >= machineVolumeCount(r, maxNode.host, vk) {
+ continue
+ }
}
// Walk the volume's actual shard bitmap so custom ratios with more
// than the standard total (ids 14..MaxShardCount-1) are candidates too.
@@ -893,12 +1034,19 @@ func volumeShardCount(node *Node, vk volKey) int {
}
func nodeInRackHoldingShard(nodes map[string]*Node, rackID string, vk volKey, shardID int) *Node {
- sid := erasure_coding.ShardId(shardID)
+ var inRack []*Node
for _, id := range sortedNodeKeys(nodes) {
- node := nodes[id]
- if node.rack != rackID {
- continue
+ if nodes[id].rack == rackID {
+ inRack = append(inRack, nodes[id])
}
+ }
+ return nodeHoldingShard(inRack, vk, shardID)
+}
+
+// nodeHoldingShard returns the first node holding the given shard of the volume, or nil.
+func nodeHoldingShard(nodes []*Node, vk volKey, shardID int) *Node {
+ sid := erasure_coding.ShardId(shardID)
+ for _, node := range nodes {
if info, ok := node.shards[vk]; ok && info.shardBits.Has(sid) {
return node
}
@@ -906,6 +1054,52 @@ func nodeInRackHoldingShard(nodes map[string]*Node, rackID string, vk volKey, sh
return nil
}
+// buildMachines groups a rack's nodes by host, each slice sorted by node id.
+func buildMachines(r *rack) map[string][]*Node {
+ machines := make(map[string][]*Node)
+ for _, n := range sortedNodeSlice(r.nodes) {
+ machines[n.host] = append(machines[n.host], n)
+ }
+ return machines
+}
+
+// rackVolumeShardCount returns how many of the volume's shards the whole rack holds.
+func rackVolumeShardCount(r *rack, vk volKey) int {
+ count := 0
+ for _, n := range r.nodes {
+ count += volumeShardCount(n, vk)
+ }
+ return count
+}
+
+// machineVolumeCount returns how many of the volume's shards the machine (host) holds.
+func machineVolumeCount(r *rack, host string, vk volKey) int {
+ count := 0
+ for _, n := range r.nodes {
+ if n.host != host {
+ continue
+ }
+ if info, ok := n.shards[vk]; ok {
+ count += info.shardBits.Count()
+ }
+ }
+ return count
+}
+
+// machineHoldsVolume reports whether any node on the machine holds a shard of the volume.
+func machineHoldsVolume(r *rack, host string, vk volKey) bool {
+ return machineVolumeCount(r, host, vk) > 0
+}
+
+func sortedNodeSlice(nodes map[string]*Node) []*Node {
+ ids := sortedNodeKeys(nodes)
+ out := make([]*Node, 0, len(ids))
+ for _, id := range ids {
+ out = append(out, nodes[id])
+ }
+ return out
+}
+
func countShardsByRack(vk volKey, nodes map[string]*Node) map[string]int {
m := make(map[string]int)
for _, node := range nodes {
@@ -916,6 +1110,16 @@ func countShardsByRack(vk volKey, nodes map[string]*Node) map[string]int {
return m
}
+func countShardsByHost(vk volKey, nodes map[string]*Node) map[string]int {
+ m := make(map[string]int)
+ for _, node := range nodes {
+ if info, ok := node.shards[vk]; ok {
+ m[node.host] += info.shardBits.Count()
+ }
+ }
+ return m
+}
+
func countShardsByNode(vk volKey, nodes map[string]*Node) map[string]int {
m := make(map[string]int)
for id, node := range nodes {
diff --git a/weed/storage/erasure_coding/ecbalancer/balancer_test.go b/weed/storage/erasure_coding/ecbalancer/balancer_test.go
index 2fac3a5aeb..677c4b1937 100644
--- a/weed/storage/erasure_coding/ecbalancer/balancer_test.go
+++ b/weed/storage/erasure_coding/ecbalancer/balancer_test.go
@@ -268,7 +268,7 @@ func TestGlobalImbalanceMovesFromFullToEmpty(t *testing.T) {
n2 := topo.AddNode("node2", "dc1", "dc1:rack1", 30)
n2.AddShards(300, "col1", 0, allBits(2))
- moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, 0, true)
+ moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, nil, 0, true)
if len(moves) == 0 {
t.Fatal("expected global balance moves")
}
@@ -288,7 +288,7 @@ func TestGlobalImbalanceHeterogeneousCapacity(t *testing.T) {
n2 := topo.AddNode("node2", "dc1", "dc1:rack1", 2)
n2.AddShards(200, "col1", 0, allBits(3))
- moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, 0, true)
+ moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, nil, 0, true)
if len(moves) == 0 {
t.Fatal("expected moves from high-util node2 to low-util node1")
}
@@ -312,7 +312,7 @@ func TestGlobalImbalanceSkipsFullNodes(t *testing.T) {
n2 := topo.AddNode("node2", "dc1", "dc1:rack1", 0) // full, cannot receive
n2.AddShards(200, "col1", 0, allBits(2))
- if moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, 0, true); len(moves) != 0 {
+ if moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, nil, 0, true); len(moves) != 0 {
t.Fatalf("expected 0 moves (node2 full), got %d", len(moves))
}
}
@@ -361,7 +361,7 @@ func TestGlobalPrefersVolumeAbsentFromDestination(t *testing.T) {
n2 := topo.AddNode("node2", "dc1", "dc1:rack1", 3)
n2.AddShards(100, "col1", 0, bits(2))
- moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, 0, true)
+ moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, nil, 0, true)
if len(moves) == 0 {
t.Fatal("expected a global move from the full node")
}
@@ -429,3 +429,300 @@ func TestDedupFreesCapacityForLaterPhases(t *testing.T) {
t.Error("slot freed by dedup on node2 was not usable by a later phase")
}
}
+
+// TestWithinRackSpreadsAcrossMachines: a 10+4 volume's 14 shards all sit on boxA
+// (two of its servers), with three other machines free. Four machines is enough for
+// the spread to stay within parity, so the within-rack phase must move shards out
+// until no machine holds more than ceil(14/4)=4, even though they looked spread
+// across boxA's two nodes.
+func TestWithinRackSpreadsAcrossMachines(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id, host string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.SetHost(host)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ a1 := mk("a1", "boxA")
+ a2 := mk("a2", "boxA")
+ mk("b1", "boxB")
+ mk("c1", "boxC")
+ mk("d1", "boxD")
+ a1.AddShards(100, "col1", 0, bits(0, 1, 2, 3, 4, 5, 6)) // 7 shards on boxA
+ a2.AddShards(100, "col1", 0, bits(7, 8, 9, 10, 11, 12, 13)) // 7 shards on boxA (all 14)
+
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 10, 4, nil)
+
+ perHost := map[string]int{}
+ for _, n := range topo.nodes {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ perHost[n.host] += info.shardBits.Count()
+ }
+ }
+ if len(perHost) < 3 {
+ t.Fatalf("shards not spread across machines: %v", perHost)
+ }
+ for h, c := range perHost {
+ if c > 4 {
+ t.Errorf("machine %s holds %d shards, want <=4 (ceil(14/4), within parity)", h, c)
+ }
+ }
+}
+
+// TestWithinRackMachineSpreadBalancesCombinedOccupancy: a 5+5 volume on two machines
+// where each shard type is already within its own per-type cap (boxA 3 data + 3
+// parity = 6, boxB 2 data + 2 parity = 4). Spreading data and parity independently
+// would leave boxA at 6, past parity; balancing the combined count must move one
+// shard to reach 5/5 so a machine loss stays recoverable.
+func TestWithinRackMachineSpreadBalancesCombinedOccupancy(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id, host string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.SetHost(host)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ a1 := mk("a1", "boxA")
+ a2 := mk("a2", "boxA") // two nodes on boxA -> numMachines(2) < numNodes(3)
+ b1 := mk("b1", "boxB")
+ a1.AddShards(100, "col1", 0, bits(0, 1, 2)) // 3 data
+ a2.AddShards(100, "col1", 0, bits(5, 6, 7)) // 3 parity (ids >= 5)
+ b1.AddShards(100, "col1", 0, bits(3, 4, 8, 9)) // 2 data + 2 parity
+
+ // dataShards=5, parityShards=5: feasibility ceil(10/2)=5 <= 5, so machine spread runs.
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 5, 5, nil)
+
+ perHost := map[string]int{}
+ for _, n := range topo.nodes {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ perHost[n.host] += info.shardBits.Count()
+ }
+ }
+ if perHost["boxA"] > 5 {
+ t.Errorf("boxA holds %d shards, want <=5 (parity); data and parity spread independently", perHost["boxA"])
+ }
+}
+
+// TestWithinRackMachineSpreadActsOnExactlyHalfSkew: a 5/4/3 machine layout for a 10+4
+// volume is only 50% skewed ((5-3)/4 = 0.5), which a 0.5 relative-imbalance threshold
+// would skip -- but the 5-shard machine is already past parity. The spread must act
+// regardless (the even cap, not a skew threshold, is the bound) and bring every
+// machine to <=ceil(12/3)=4.
+func TestWithinRackMachineSpreadActsOnExactlyHalfSkew(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id, host string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.SetHost(host)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ a1 := mk("a1", "boxA")
+ a2 := mk("a2", "boxA")
+ b1 := mk("b1", "boxB")
+ b2 := mk("b2", "boxB")
+ c1 := mk("c1", "boxC")
+ c2 := mk("c2", "boxC")
+ a1.AddShards(100, "col1", 0, bits(0, 1, 2))
+ a2.AddShards(100, "col1", 0, bits(3, 4)) // boxA = 5
+ b1.AddShards(100, "col1", 0, bits(5, 6))
+ b2.AddShards(100, "col1", 0, bits(7, 8)) // boxB = 4
+ c1.AddShards(100, "col1", 0, bits(9, 10))
+ c2.AddShards(100, "col1", 0, bits(11)) // boxC = 3
+
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 10, 4, nil)
+
+ perHost := map[string]int{}
+ for _, n := range topo.nodes {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ perHost[n.host] += info.shardBits.Count()
+ }
+ }
+ for h, c := range perHost {
+ if c > 4 {
+ t.Errorf("machine %s holds %d shards, want <=4 (ceil(12/3)); a 50%% skew was skipped", h, c)
+ }
+ }
+}
+
+// TestWithinRackSpreadUsesRackLocalShardCount: a rack holds only 7 shards of a 10+4
+// volume (cross-rack spreading moved the rest to other racks). Two machines can hold
+// those 7 within parity (ceil(7/2)=4), so machine spread must apply -- gating on the
+// full 14-shard total would wrongly fall back to node spread and pile 6 onto boxA's
+// two nodes, exceeding parity.
+func TestWithinRackSpreadUsesRackLocalShardCount(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id, host string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.SetHost(host)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ a1 := mk("a1", "boxA")
+ a2 := mk("a2", "boxA")
+ mk("b1", "boxB")
+ a1.AddShards(100, "col1", 0, bits(0, 1, 2, 3))
+ a2.AddShards(100, "col1", 0, bits(4, 5, 6)) // boxA holds all 7 of this rack's shards
+
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 10, 4, nil)
+
+ perHost := map[string]int{}
+ for _, n := range topo.nodes {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ perHost[n.host] += info.shardBits.Count()
+ }
+ }
+ if perHost["boxA"] > 4 {
+ t.Errorf("boxA holds %d shards, want <=4 (parity); rack-local feasibility not used", perHost["boxA"])
+ }
+ if perHost["boxB"] == 0 {
+ t.Error("no shards moved to boxB; machine spread did not apply")
+ }
+}
+
+// TestWithinRackNodeFallbackHonorsThreshold: one server per host with a 6/4 data
+// split is the cosmetic node fallback (a 2-node rack can't be machine-fault-tolerant
+// for a 10+4 volume). At 40% skew it's below the 0.5 threshold, so it must be left to
+// the global utilization phase rather than churned -- a count move here can worsen
+// utilization on unequal-capacity nodes.
+func TestWithinRackNodeFallbackHonorsThreshold(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ n1 := mk("n1") // distinct hosts (default host = id) -> node fallback
+ n2 := mk("n2")
+ n1.AddShards(100, "col1", 0, bits(0, 1, 2, 3, 4, 5)) // 6 data
+ n2.AddShards(100, "col1", 0, bits(6, 7, 8, 9)) // 4 data
+
+ moves := detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0.5, 10, 4, nil)
+ if len(moves) != 0 {
+ t.Errorf("node fallback moved %d shards on a 40%%-skewed 6/4 layout at threshold 0.5; want 0", len(moves))
+ }
+}
+
+// TestWithinRackSpreadDefaultsToNodes: with no SetHost each node is its own
+// machine, so the within-rack phase still spreads a volume off an overloaded node
+// exactly as before (machine grouping reduces to node grouping).
+func TestWithinRackSpreadDefaultsToNodes(t *testing.T) {
+ topo := NewTopology()
+ mk := func(id string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ n1 := mk("n1")
+ mk("n2")
+ mk("n3")
+ n1.AddShards(100, "col1", 0, allBits(14)) // all 14 piled on one node
+
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 10, 4, nil)
+
+ perNode := map[string]int{}
+ for id, n := range topo.nodes {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ perNode[id] = info.shardBits.Count()
+ }
+ }
+ if perNode["n1"] == 14 {
+ t.Fatal("no within-rack spread happened with one server per host")
+ }
+ if len(perNode) < 3 {
+ t.Errorf("shards not spread across all three nodes: %v", perNode)
+ }
+ // Per-type even caps: ceil(10/3) data + ceil(4/3) parity = 4+2 per node.
+ for id, c := range perNode {
+ if c > 6 {
+ t.Errorf("node %s holds %d shards, want <=6 (dataCap+parityCap)", id, c)
+ }
+ }
+}
+
+// TestGlobalDoesNotConcentrateVolumeAcrossMachines: when the volume's machine spread
+// is achievable (here 2 machines, a 2+2 volume, one machine can hold <= parity), a
+// load move must not raise a machine's shard count of the volume past the source's.
+// boxA's only volume is also on boxB, so pass 0 finds nothing and the sole pass-1
+// option is the cross-machine boxA->boxB move, which must be rejected (boxB already
+// holds as many shards as boxA). Same-machine node rebalancing would still be fine.
+func TestGlobalDoesNotConcentrateVolumeAcrossMachines(t *testing.T) {
+ topo := NewTopology()
+ a1 := topo.AddNode("a1", "dc1", "dc1:rack1", 0) // full -> high util, the max node
+ a1.SetHost("boxA")
+ a1.AddShards(100, "col1", 0, bits(0, 1))
+ b1 := topo.AddNode("b1", "dc1", "dc1:rack1", 0) // full -> cannot receive
+ b1.SetHost("boxB")
+ b1.AddShards(100, "col1", 0, bits(2, 3))
+ b2 := topo.AddNode("b2", "dc1", "dc1:rack1", 10) // empty -> low util, the min node
+ b2.SetHost("boxB")
+
+ data := map[string]int{"col1": 2}
+ parity := map[string]int{"col1": 2}
+ for _, m := range detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, data, parity, 0, true) {
+ if m.source.host != m.target.host {
+ t.Errorf("cross-machine global move %d.%d from %s to %s concentrates the volume on a machine",
+ m.volumeID, m.shardID, m.source.host, m.target.host)
+ }
+ }
+}
+
+// TestWithinRackMachineSkipsCappedMachine: a machine whose only node is already at
+// the per-node SameRackCount cap is not a viable target, and the within-rack spread
+// must move shards to the next machine that is, rather than picking the capped one
+// and skipping the move. Four machines (boxA has two nodes) make the spread active;
+// boxB's node holds two parity shards (== SameRackCount), so boxA's over-concentrated
+// data shards must land on the viable boxC/boxD.
+func TestWithinRackMachineSkipsCappedMachine(t *testing.T) {
+ rp, _ := super_block.NewReplicaPlacementFromString("002") // SameRackCount=2
+ topo := NewTopology()
+ mk := func(id, host string) *Node {
+ n := topo.AddNode(id, "dc1", "dc1:rack1", 100)
+ n.SetHost(host)
+ n.AddDisk(0, "", 100, 0)
+ return n
+ }
+ a1 := mk("a1", "boxA")
+ mk("a2", "boxA") // boxA's second node makes numMachines(4) < numNodes(5)
+ b1 := mk("b1", "boxB")
+ c1 := mk("c1", "boxC")
+ d1 := mk("d1", "boxD")
+ a1.AddShards(100, "col1", 0, bits(0, 1, 2, 3)) // 4 data shards, over-concentrated on boxA
+ b1.AddShards(100, "col1", 0, bits(10, 11)) // 2 parity -> b1 at SameRackCount cap
+
+ detectWithinRackImbalance(volKey{"col1", 100}, topo.nodes, buildRacks(topo.nodes), "", 0, 10, 4, rp)
+
+ moved := 0
+ for _, n := range []*Node{c1, d1} {
+ if info, ok := n.shards[volKey{"col1", 100}]; ok {
+ moved += info.shardBits.Count()
+ }
+ }
+ if moved == 0 {
+ t.Error("data shards were not moved to the viable machines boxC/boxD; the capped boxB blocked the move")
+ }
+}
+
+// TestGlobalPrefersVolumeAbsentFromDestinationMachine: the global load phase must
+// judge "volume already present" at the machine level. boxB's sibling node holds
+// vol100, so draining boxA onto boxB's empty node should move a vol200 shard first
+// (vol200 is absent from boxB) rather than piling a second vol100 copy onto boxB.
+func TestGlobalPrefersVolumeAbsentFromDestinationMachine(t *testing.T) {
+ topo := NewTopology()
+ n1 := topo.AddNode("n1", "dc1", "dc1:rack1", 0)
+ n1.SetHost("boxA")
+ n1.AddShards(100, "col1", 0, bits(0, 1, 2, 3))
+ n1.AddShards(200, "col1", 0, bits(0, 1, 2, 3))
+ n2 := topo.AddNode("n2", "dc1", "dc1:rack1", 5)
+ n2.SetHost("boxB")
+ n2.AddShards(100, "col1", 0, bits(4)) // vol100 already on boxB (sibling node)
+ n3 := topo.AddNode("n3", "dc1", "dc1:rack1", 5)
+ n3.SetHost("boxB") // empty destination node, but its machine holds vol100
+
+ moves := detectGlobalImbalance(topo.nodes, buildRacks(topo.nodes), "", 0.01, nil, nil, 0, true)
+ if len(moves) == 0 {
+ t.Fatal("expected a global move from the full node")
+ }
+ if moves[0].volumeID != 200 {
+ t.Errorf("first global move is volume %d, want 200 (vol100 already on the destination machine)", moves[0].volumeID)
+ }
+}
diff --git a/weed/storage/erasure_coding/ecbalancer/place.go b/weed/storage/erasure_coding/ecbalancer/place.go
index 9f98f18ba6..c754995e24 100644
--- a/weed/storage/erasure_coding/ecbalancer/place.go
+++ b/weed/storage/erasure_coding/ecbalancer/place.go
@@ -388,9 +388,13 @@ func rackHasFreeDisk(r *rack, eligible func(*disk) bool) bool {
// pickNodeInRackEligible is pickNodeInRack restricted to nodes that have a free
// eligible disk. FromActiveTopology keeps all disk types/tags in the snapshot, so
// without this a node with free volume slots but no eligible disk could be chosen.
+//
+// Among eligible nodes it prefers the one whose machine holds the fewest shards of
+// the volume (tie-broken by the node's own count), spreading shards across machines.
func pickNodeInRackEligible(r *rack, vk volKey, rp *super_block.ReplicaPlacement, eligible func(*disk) bool) *Node {
+ machineShards := countShardsByHost(vk, r.nodes)
var best *Node
- bestCount := -1
+ bestMachineCount, bestNodeCount := -1, -1
for _, id := range sortedNodeKeys(r.nodes) {
node := r.nodes[id]
if node.freeSlots <= 0 {
@@ -403,8 +407,9 @@ func pickNodeInRackEligible(r *rack, vk volKey, rp *super_block.ReplicaPlacement
if rp != nil && rp.SameRackCount > 0 && count >= rp.SameRackCount {
continue
}
- if best == nil || count < bestCount {
- best, bestCount = node, count
+ mCount := machineShards[node.host]
+ if best == nil || mCount < bestMachineCount || (mCount == bestMachineCount && count < bestNodeCount) {
+ best, bestMachineCount, bestNodeCount = node, mCount, count
}
}
return best
diff --git a/weed/storage/erasure_coding/ecbalancer/place_test.go b/weed/storage/erasure_coding/ecbalancer/place_test.go
index 6af01a331c..4b2814270e 100644
--- a/weed/storage/erasure_coding/ecbalancer/place_test.go
+++ b/weed/storage/erasure_coding/ecbalancer/place_test.go
@@ -73,6 +73,44 @@ func TestPlaceStrictSpreadAndCaps(t *testing.T) {
}
}
+// TestPlaceSpreadsAcrossMachines: one rack runs two physical machines (each with
+// four volume servers). Placing a 10+4 volume must spread its shards across both
+// machines so no single machine holds more than ceil(14/2)=7, otherwise losing one
+// box would take out more shards than EC can recover even though they look spread
+// across distinct nodes.
+func TestPlaceSpreadsAcrossMachines(t *testing.T) {
+ topo := NewTopology()
+ host := map[string]string{}
+ add := func(id, h string) {
+ n := topo.AddNode(id, "dc1", "dc1:rack0", 50)
+ n.SetHost(h)
+ n.AddDisk(0, "", 50, 0)
+ host[id] = h
+ }
+ for i := 0; i < 4; i++ {
+ add(fmt.Sprintf("a%d", i), "10.0.0.1")
+ add(fmt.Sprintf("b%d", i), "10.0.0.2")
+ }
+
+ res, err := topo.Place(1, "c1", allShards(), Constraints{}, PlaceStrict)
+ if err != nil {
+ t.Fatalf("Place: %v", err)
+ }
+ perMachine := map[string]int{}
+ for _, d := range res.Destinations {
+ perMachine[host[d.Node]]++
+ }
+ if len(perMachine) < 2 {
+ t.Fatalf("shards not spread across machines: %v", perMachine)
+ }
+ maxPerMachine := ceilDivide(erasure_coding.TotalShardsCount, 2)
+ for h, c := range perMachine {
+ if c > maxPerMachine {
+ t.Errorf("machine %s holds %d shards, want <=%d (ceil(14/2))", h, c, maxPerMachine)
+ }
+ }
+}
+
// TestPlaceStrictFailsAndRollsBack: a single tiny disk cannot hold 14 shards, so
// strict Place fails and leaves the snapshot untouched.
func TestPlaceStrictFailsAndRollsBack(t *testing.T) {
diff --git a/weed/storage/erasure_coding/ecbalancer/snapshot.go b/weed/storage/erasure_coding/ecbalancer/snapshot.go
index 9d5c81103a..a8380caacc 100644
--- a/weed/storage/erasure_coding/ecbalancer/snapshot.go
+++ b/weed/storage/erasure_coding/ecbalancer/snapshot.go
@@ -2,6 +2,7 @@ package ecbalancer
import (
"github.com/seaweedfs/seaweedfs/weed/admin/topology"
+ "github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
)
@@ -32,6 +33,7 @@ func FromActiveTopology(at *topology.ActiveTopology, dataShards int) *Topology {
nodeFree := make(map[string]int)
nodeDC := make(map[string]string)
nodeRack := make(map[string]string)
+ nodeAddr := make(map[string]string)
byNode := make(map[string][]*topology.DiskInfo)
for _, d := range disks {
if d == nil || d.DiskInfo == nil {
@@ -42,11 +44,19 @@ func FromActiveTopology(at *topology.ActiveTopology, dataShards int) *Topology {
}
nodeDC[d.NodeID] = d.DataCenter
nodeRack[d.NodeID] = d.DataCenter + ":" + d.Rack
+ nodeAddr[d.NodeID] = d.Address
byNode[d.NodeID] = append(byNode[d.NodeID], d)
}
for nodeID, ds := range byNode {
node := topo.AddNode(nodeID, nodeDC[nodeID], nodeRack[nodeID], nodeFree[nodeID])
+ // Group by physical machine: derive the host from the address (NodeID may be
+ // an opaque id), falling back to the id when no address is recorded.
+ addr := nodeAddr[nodeID]
+ if addr == "" {
+ addr = nodeID
+ }
+ node.SetHost(pb.ServerAddress(addr).ToHost())
for _, d := range ds {
free := perDiskFreeECSlots(at, d, dataShards)
if free < 0 {
diff --git a/weed/storage/erasure_coding/ecbalancer/snapshot_test.go b/weed/storage/erasure_coding/ecbalancer/snapshot_test.go
index a7e54dbcf9..4376beb176 100644
--- a/weed/storage/erasure_coding/ecbalancer/snapshot_test.go
+++ b/weed/storage/erasure_coding/ecbalancer/snapshot_test.go
@@ -102,6 +102,47 @@ func TestFromActiveTopology(t *testing.T) {
}
}
+// TestFromActiveTopologyGroupsByAddressHost verifies the snapshot derives a node's
+// machine from its address, not its (possibly opaque) id: two volume servers with
+// distinct ids but the same host must land on one machine so EC placement spreads
+// shards across boxes even when explicit node ids are configured.
+func TestFromActiveTopologyGroupsByAddressHost(t *testing.T) {
+ at := topology.NewActiveTopology(10)
+ mk := func(id, addr string) *master_pb.DataNodeInfo {
+ return &master_pb.DataNodeInfo{
+ Id: id,
+ Address: addr,
+ DiskInfos: map[string]*master_pb.DiskInfo{"hdd": {DiskId: 0, MaxVolumeCount: 100, VolumeCount: 0}},
+ }
+ }
+ // vs-a and vs-b are two servers on the same physical host; vs-c is another box.
+ nodes := []*master_pb.DataNodeInfo{
+ mk("vs-a", "10.0.0.9:8080"),
+ mk("vs-b", "10.0.0.9:8081"),
+ mk("vs-c", "10.0.0.10:8080"),
+ }
+ if err := at.UpdateTopology(&master_pb.TopologyInfo{
+ DataCenterInfos: []*master_pb.DataCenterInfo{{
+ Id: "dc1",
+ RackInfos: []*master_pb.RackInfo{{Id: "rack1", DataNodeInfos: nodes}},
+ }},
+ }); err != nil {
+ t.Fatalf("UpdateTopology: %v", err)
+ }
+
+ topo := FromActiveTopology(at, 0)
+ if topo.nodes["vs-a"].host != topo.nodes["vs-b"].host {
+ t.Errorf("vs-a host %q != vs-b host %q; same-machine servers not grouped",
+ topo.nodes["vs-a"].host, topo.nodes["vs-b"].host)
+ }
+ if topo.nodes["vs-a"].host == topo.nodes["vs-c"].host {
+ t.Errorf("vs-a and vs-c share host %q but are different machines", topo.nodes["vs-a"].host)
+ }
+ if got := topo.nodes["vs-a"].host; got != "10.0.0.9" {
+ t.Errorf("vs-a host = %q, want 10.0.0.9", got)
+ }
+}
+
// TestEcShardSlotsOnDiskRoundsUp covers the mixed-ratio (targetDataShards <
// existingDataShards) conversion: an existing shard's fractional footprint must
// round up so it is never floored to zero, which would overstate free capacity.
diff --git a/weed/topology/node.go b/weed/topology/node.go
index f6073326f5..d1d1214711 100644
--- a/weed/topology/node.go
+++ b/weed/topology/node.go
@@ -144,11 +144,11 @@ type Node interface {
}
type NodeImpl struct {
- diskUsages *DiskUsages
- id NodeId
- parent Node
+ diskUsages *DiskUsages
+ id NodeId
+ parent Node
sync.RWMutex // lock children
- children map[NodeId]Node
+ children map[NodeId]Node
// maxVolumeId uses atomic ops so UpAdjustMaxVolumeId (called from the
// volume server heartbeat path) and GetMaxVolumeId (called from the
// master's assign / warmup checks) can run concurrently without a
@@ -167,6 +167,38 @@ func (n *NodeImpl) GetDiskUsages() *DiskUsages {
return n.diskUsages
}
+// nodeHost returns the host a node runs on, or "" for non-data-node tiers (data
+// centers, racks).
+func nodeHost(node Node) string {
+ if dn, ok := node.(*DataNode); ok {
+ return dn.Ip
+ }
+ return ""
+}
+
+// preferDistinctHosts reorders candidates so the first node of each not-yet-used
+// host comes first (preserving weighted order), then the same-host leftovers, so a
+// prefix covers the most distinct machines. usedHost seeds the set. No-op when
+// hosts are empty (non-data-node tiers).
+func preferDistinctHosts(usedHost string, candidates []Node) []Node {
+ used := map[string]bool{}
+ if usedHost != "" {
+ used[usedHost] = true
+ }
+ distinct := make([]Node, 0, len(candidates))
+ dup := make([]Node, 0, len(candidates))
+ for _, node := range candidates {
+ h := nodeHost(node)
+ if h != "" && !used[h] {
+ used[h] = true
+ distinct = append(distinct, node)
+ } else {
+ dup = append(dup, node)
+ }
+ }
+ return append(distinct, dup...)
+}
+
// the first node must satisfy filterFirstNodeFn(), the rest nodes must have one free slot
func (n *NodeImpl) PickNodesByWeight(numberOfNodes int, option *VolumeGrowOption, filterFirstNodeFn func(dn Node) error) (firstNode Node, restNodes []Node, err error) {
var totalWeights int64
@@ -215,12 +247,17 @@ func (n *NodeImpl) PickNodesByWeight(numberOfNodes int, option *VolumeGrowOption
for k, node := range sortedCandidates {
if err := filterFirstNodeFn(node); err == nil {
firstNode = node
- if k >= numberOfNodes-1 {
- restNodes = sortedCandidates[:numberOfNodes-1]
- } else {
- restNodes = append(restNodes, sortedCandidates[:k]...)
- restNodes = append(restNodes, sortedCandidates[k+1:numberOfNodes]...)
+ // Fill the rest preferring not-yet-used hosts, so replicas spread across
+ // machines; falls back to same-host when too few. No-op for dc/rack tiers
+ // (empty host), which keep the weighted order.
+ pool := make([]Node, 0, len(sortedCandidates)-1)
+ pool = append(pool, sortedCandidates[:k]...)
+ pool = append(pool, sortedCandidates[k+1:]...)
+ pool = preferDistinctHosts(nodeHost(firstNode), pool)
+ if len(pool) > numberOfNodes-1 {
+ pool = pool[:numberOfNodes-1]
}
+ restNodes = pool
ret = true
break
} else {
diff --git a/weed/topology/volume_growth_test.go b/weed/topology/volume_growth_test.go
index d0b30c2ca2..11e3ba0829 100644
--- a/weed/topology/volume_growth_test.go
+++ b/weed/topology/volume_growth_test.go
@@ -475,3 +475,40 @@ func TestPickForWrite(t *testing.T) {
}
}
}
+
+// TestPickNodesByWeightPrefersDistinctHosts: a rack runs two physical machines
+// with two volume servers each. Picking two nodes (e.g. for a same-rack replica
+// pair) must land them on distinct hosts so a single machine failure cannot take
+// out both replicas, even though the four data nodes are independent.
+func TestPickNodesByWeightPrefersDistinctHosts(t *testing.T) {
+ rack := NewRack("rack1")
+ mk := func(id, ip string, maxVol int64) *DataNode {
+ dn := NewDataNode(id)
+ dn.Ip = ip
+ rack.LinkChildNode(dn)
+ disk := dn.getOrCreateDisk("")
+ disk.UpAdjustDiskUsageDelta("", &DiskUsageCounts{maxVolumeCount: maxVol})
+ return dn
+ }
+ mk("s1a", "10.0.0.1", 10)
+ mk("s1b", "10.0.0.1", 10)
+ mk("s2a", "10.0.0.2", 10)
+ mk("s2b", "10.0.0.2", 10)
+
+ option := &VolumeGrowOption{DiskType: types.HardDriveType}
+
+ // Selection is weighted-random, so exercise it repeatedly: with two machines
+ // available the chosen pair must always span both.
+ for i := 0; i < 50; i++ {
+ first, rest, err := rack.PickNodesByWeight(2, option, func(node Node) error { return nil })
+ if err != nil {
+ t.Fatalf("PickNodesByWeight: %v", err)
+ }
+ if len(rest) != 1 {
+ t.Fatalf("got %d rest nodes, want 1", len(rest))
+ }
+ if nodeHost(first) == nodeHost(rest[0]) {
+ t.Errorf("both picks on host %s; expected distinct machines", nodeHost(first))
+ }
+ }
+}
diff --git a/weed/worker/tasks/balance/detection.go b/weed/worker/tasks/balance/detection.go
index d0d73df724..3d5154fbaf 100644
--- a/weed/worker/tasks/balance/detection.go
+++ b/weed/worker/tasks/balance/detection.go
@@ -662,6 +662,7 @@ func planBalanceDestination(activeTopology *topology.ActiveTopology, selectedVol
DataCenter: disk.DataCenter,
Rack: disk.Rack,
NodeID: disk.NodeID,
+ Host: hostFromAddress(disk.Address, disk.NodeID),
}
if !IsGoodMove(rp, replicas, selectedVolume.Server, target) {
continue
@@ -771,6 +772,7 @@ func isValidBalanceDestination(plan *topology.DestinationPlan, allowedServers ma
DataCenter: plan.TargetDC,
Rack: plan.TargetRack,
NodeID: plan.TargetNode,
+ Host: hostFromAddress(plan.TargetAddress, plan.TargetNode),
}
return IsGoodMove(rp, replicas, sourceNodeID, target)
}
diff --git a/weed/worker/tasks/balance/replica_placement.go b/weed/worker/tasks/balance/replica_placement.go
index c90ad6fb00..d84333ec31 100644
--- a/weed/worker/tasks/balance/replica_placement.go
+++ b/weed/worker/tasks/balance/replica_placement.go
@@ -3,10 +3,21 @@ package balance
import (
"slices"
+ "github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
"github.com/seaweedfs/seaweedfs/weed/worker/types"
)
+// hostFromAddress returns the physical machine (host/IP) of a server address,
+// falling back to the node id (== ip:port in the common case) when no address is
+// known. Servers sharing a host are one fault domain.
+func hostFromAddress(address, nodeID string) string {
+ if address == "" {
+ address = nodeID
+ }
+ return pb.ServerAddress(address).ToHost()
+}
+
// rackKey uniquely identifies a rack within a data center.
type rackKey struct {
DataCenter string
@@ -44,6 +55,17 @@ func IsGoodMove(rp *super_block.ReplicaPlacement, existingReplicas []types.Repli
return false
}
+ // Best-effort machine anti-affinity: don't move a replica onto a host that
+ // already holds another replica of this volume, so a single machine failure
+ // can't take out two replicas.
+ if target.Host != "" {
+ for _, r := range afterMove {
+ if r.Host == target.Host {
+ return false
+ }
+ }
+ }
+
return satisfyReplicaPlacement(rp, afterMove, target)
}
diff --git a/weed/worker/tasks/balance/replica_placement_test.go b/weed/worker/tasks/balance/replica_placement_test.go
index 303fb192bd..baa8f1eb71 100644
--- a/weed/worker/tasks/balance/replica_placement_test.go
+++ b/weed/worker/tasks/balance/replica_placement_test.go
@@ -29,6 +29,24 @@ func TestIsGoodMove_NoReplication(t *testing.T) {
}
}
+func TestIsGoodMove_MachineAntiAffinity(t *testing.T) {
+ // rep 001 allows two copies in one rack, so replica placement alone would permit
+ // moving onto another port of a host that already holds a replica; machine
+ // anti-affinity must reject that and allow a distinct host.
+ existing := []types.ReplicaLocation{
+ {DataCenter: "dc1", Rack: "r1", NodeID: "10.0.0.1:8080", Host: "10.0.0.1"},
+ {DataCenter: "dc1", Rack: "r1", NodeID: "10.0.0.2:8080", Host: "10.0.0.2"},
+ }
+ onSameMachine := types.ReplicaLocation{DataCenter: "dc1", Rack: "r1", NodeID: "10.0.0.1:8081", Host: "10.0.0.1"}
+ if IsGoodMove(rp(t, "001"), existing, "10.0.0.2:8080", onSameMachine) {
+ t.Error("move onto a machine already holding a replica should be rejected")
+ }
+ onOtherMachine := types.ReplicaLocation{DataCenter: "dc1", Rack: "r1", NodeID: "10.0.0.3:8080", Host: "10.0.0.3"}
+ if !IsGoodMove(rp(t, "001"), existing, "10.0.0.2:8080", onOtherMachine) {
+ t.Error("move onto a distinct machine should be allowed")
+ }
+}
+
func TestIsGoodMove_001_SameRack(t *testing.T) {
// 001 = 1 replica on same rack (2 total on same rack)
existing := []types.ReplicaLocation{
diff --git a/weed/worker/tasks/ec_balance/detection.go b/weed/worker/tasks/ec_balance/detection.go
index d62d394db2..4fe2e764bc 100644
--- a/weed/worker/tasks/ec_balance/detection.go
+++ b/weed/worker/tasks/ec_balance/detection.go
@@ -6,6 +6,7 @@ import (
"time"
"github.com/seaweedfs/seaweedfs/weed/glog"
+ "github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
@@ -198,6 +199,9 @@ func buildBalancerTopology(topoInfo *master_pb.TopologyInfo, config *Config) (*e
}
node := topo.AddNode(dn.Id, dc.Id, rackKey, freeSlots)
+ // Group servers sharing a host so a volume's shards spread across
+ // machines, not just nodes (servers on one host are one fault domain).
+ node.SetHost(pb.NewServerAddressFromDataNode(dn).ToHost())
perDiskFree := 0
if diskCount := len(diskTypeOf); diskCount > 0 && freeSlots > 0 {
diff --git a/weed/worker/tasks/ec_balance/detection_test.go b/weed/worker/tasks/ec_balance/detection_test.go
index 66d473952e..16a3431bcd 100644
--- a/weed/worker/tasks/ec_balance/detection_test.go
+++ b/weed/worker/tasks/ec_balance/detection_test.go
@@ -2,6 +2,7 @@ package ec_balance
import (
"context"
+ "net"
"testing"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
@@ -50,6 +51,51 @@ func TestBuildBalancerTopology(t *testing.T) {
}
}
+// TestBuildBalancerTopologyGroupsByHost: two volume servers on host 10.0.0.1
+// (different ports) plus three other hosts, a 10+4 volume concentrated on the
+// 10.0.0.1 machine. Four machines is enough to spread within parity, so after
+// planning the 10.0.0.1 machine must hold <=4 shards of the volume -- which only
+// holds if its two ports are grouped into one machine (host wired into the build).
+func TestBuildBalancerTopologyGroupsByHost(t *testing.T) {
+ mkNode := func(id string, bits uint32) *master_pb.DataNodeInfo {
+ di := &master_pb.DiskInfo{Type: "", MaxVolumeCount: 100}
+ if bits != 0 {
+ di.EcShardInfos = []*master_pb.VolumeEcShardInformationMessage{{Id: 100, Collection: "col1", DiskId: 0, EcIndexBits: bits}}
+ }
+ return &master_pb.DataNodeInfo{Id: id, DiskInfos: map[string]*master_pb.DiskInfo{"": di}}
+ }
+ topoInfo := &master_pb.TopologyInfo{
+ DataCenterInfos: []*master_pb.DataCenterInfo{{
+ Id: "dc1",
+ RackInfos: []*master_pb.RackInfo{{Id: "rack1", DataNodeInfos: []*master_pb.DataNodeInfo{
+ mkNode("10.0.0.1:8080", 0x007F), // shards 0-6 on host 10.0.0.1
+ mkNode("10.0.0.1:8081", 0x3F80), // shards 7-13 on host 10.0.0.1
+ mkNode("10.0.0.2:8080", 0),
+ mkNode("10.0.0.3:8080", 0),
+ mkNode("10.0.0.4:8080", 0),
+ }}},
+ }},
+ }
+
+ topo, _ := buildBalancerTopology(topoInfo, NewDefaultConfig())
+ moves := ecbalancer.Plan(topo, ecbalancer.Options{ImbalanceThreshold: 0.01})
+
+ host := func(nodeID string) string { h, _, _ := net.SplitHostPort(nodeID); return h }
+ count := map[string]int{"10.0.0.1": 14}
+ for _, m := range moves {
+ if m.VolumeID != 100 {
+ continue
+ }
+ count[host(m.SourceNode)]--
+ if m.SourceNode != m.TargetNode { // non-dedup move
+ count[host(m.TargetNode)]++
+ }
+ }
+ if count["10.0.0.1"] > 4 {
+ t.Errorf("machine 10.0.0.1 holds %d shards of the volume after balancing, want <=4 (host grouping not applied)", count["10.0.0.1"])
+ }
+}
+
func TestBuildBalancerTopologyCollectionFilter(t *testing.T) {
config := NewDefaultConfig()
config.CollectionFilter = "other" // does not match the volume's collection
diff --git a/weed/worker/types/data_types.go b/weed/worker/types/data_types.go
index cd30405974..e42006163b 100644
--- a/weed/worker/types/data_types.go
+++ b/weed/worker/types/data_types.go
@@ -12,6 +12,7 @@ type ReplicaLocation struct {
DataCenter string
Rack string
NodeID string
+ Host string // physical machine (host/IP); servers sharing a host are one fault domain
}
// ClusterInfo contains cluster information for task detection