mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-16 19:40:43 +02:00
* Add shared super_block.ResolveReplicaPlacement; use it in ec_balance * Add ecbalancer.FromActiveTopology snapshot constructor for EC encode/repair * Add ecbalancer.Place greenfield/repair placement core (strict + durability-first) * topology: add GetEffectiveAvailableEcShardSlots; FromActiveTopology uses shard-granular free slots GetDisksWithEffectiveCapacity flattens reserved shard slots into volume slots via integer truncation, so an in-flight EC task reserving a non-multiple-of- DataShardsCount number of shards was lost from the snapshot and freeSlots was over-reported. GetEffectiveAvailableEcShardSlots subtracts the full reservation impact at shard granularity. * ecbalancer.Place: reject nodes without a free disk of the requested type FromActiveTopology keeps all disk types in the snapshot, so an SSD-only request could be routed to a node with only HDD capacity (pickBestDiskOnNode then returns disk 0 on the wrong tier). Filter rack/node selection to those with a free disk of the requested type. * ecbalancer.Place: enforce ReplicaPlacement DiffDataCenterCount (per-DC shard cap) * ecbalancer: enforce DiffDataCenterCount in balance (cross-DC phase + cross-rack DC cap) Adds a cross-DC corrective phase that drains data centers holding more than DiffDataCenterCount shards of a volume, and a per-DC cap on cross-rack move targets. Both are no-ops when DiffDataCenterCount is unset, so balance output is unchanged for non-DC placements. * topology: ratio-aware EC shard slots and provisional empty-disk slot GetEffectiveAvailableEcShardSlots now takes the target collection's data-shard count, so a 4+2 volume's larger shards are not over-counted at 10 per volume slot; and it keeps the one provisional slot for freshly started empty servers that report max=0, matching getEffectiveAvailableCapacityUnsafe. FromActiveTopology threads the ratio through. * ecbalancer.Place: explicit disk-type filter signal (fix HDD vs any ambiguity) HardDriveType normalizes to "", which collided with "" meaning any disk. Add Constraints.FilterDiskType and normalize both sides so a hdd request matches disks reported as "" and never leaks to SSD, while filter=false still means any. * ecbalancer: add clearShardAccounting for repair snapshot reconciliation Clears one disk's copy of a shard from per-domain accounting and recomputes the node-level union (preserving a kept copy on another disk of the same node), without crediting capacity. Repair uses it to drop to-be-deleted copies before placing missing shards. * ecbalancer: don't cap cross-DC target racks when DiffRackCount is unset len(racks)+1 wrongly limited each target rack (3 in a 2-rack cluster), so draining a DC could stop short of the DiffDataCenterCount cap. Use MaxShardCount+1 as the effectively-unlimited default. * topology/ecbalancer: ratio-correct EC capacity accounting Reservation shard slots (default ShardsPerVolumeSlot units) are now converted to the target ratio before subtracting, and existing EC shards are charged by size (targetDataShards/shardDataShards) so a 2+1 shard isn't counted as one 10+4 slot. Per-shard ratio lookup is behind shardDataShards (OSS uses the standard ratio). * ecbalancer.Place: candidate tiering and eligible-rack caps Adds a per-disk eligibility/preference abstraction so Place supports: - preferred-tag whole-plan retry (try disks carrying the earliest tags first, widen to all only if a tier cannot place every shard; reports SpilledOutsidePreferredTags), - soft disk-type spill via DiskTypePolicy (Any/Prefer/Require): Prefer fills the preferred type then spills, reporting SpilledToOtherDiskType; Require filters, - even per-rack caps that divide by racks holding an eligible disk, so a tiered cluster (e.g. SSDs in 2 of 4 racks) isn't capped impossibly low. Disk tags carried via Node.AddDiskTags + FromActiveTopology. * ecbalancer: export ClearShardAccounting for repair snapshot reconciliation * ecbalancer: address review feedback (ratio rounding, bitmap walk, same-DC moves) - topology/ecbalancer: round shard-reservation and existing-shard footprint up when converting to target-ratio shard slots, so a sub-slot reservation is not truncated to zero and free capacity is not overstated for low-data-shard layouts (targetDataShards < ds). - erasure_coding: add ShardBits.All iterator and use it across the balancer, cross-DC phase, and placement scoring instead of scanning 0..MaxShardCount and probing Has on every id. - ecbalancer: allow same-DC cross-rack moves when a DC already sits at its DiffDataCenterCount cap; a same-DC move leaves the DC total unchanged. Add a regression test that fails without the guard. - ecbalancer cross-DC phase: pick targets via the eligible-aware pickNodeInRackEligible/pickBestDiskEligible helpers so the disk-type filter is honored and a 0 disk id is not mistaken for a valid selection. * ecbalancer: test ecShardSlotsOnDisk fractional round-up Cover the mixed-ratio path (targetDataShards < existing data shards) so a shard's fractional footprint is never floored to zero and free capacity is not overstated. Exercises the round-up via the targetDataShards parameter; OSS uses the standard ratio at runtime while the enterprise build hits it with real per-volume ratios. * ecbalancer: assert node B rack in TestFromActiveTopology * ecbalancer: split Destination into separate DataCenter and bare Rack Replace the composite "dc:rack" Rack field on Destination with separate DataCenter and bare Rack values, matching topology.DiskInfo and the worker-task convention. Callers (and tests) read the data center directly instead of parsing the composite with strings.SplitN. * shell ec.balance: use utilization-based global balancing (parity with worker) The shell's global rebalance phase balanced by raw shard count; switch it to fractional fullness (shards/capacity), as the worker already does. On uniform capacity the two agree; on heterogeneous capacity it fills nodes proportionally instead of driving small-capacity nodes toward full. Updates the heterogeneous-capacity regression test to assert even fullness (~equal shards/capacity per node) rather than even shard count. * ecbalancer: bounded-proportional per-DC shard spread DiffDataCenterCount was enforced only as a ceiling (drain-to-cap), which could leave a within-cap-but-lopsided DC distribution under a loose cap (e.g. 10/4 of 14 with cap=10). Now the cross-DC phase, the cross-rack DC guard, and Place all target boundedMaxPerDC = min(DiffDataCenterCount, max(ceil(total/numDCs), parityShards)): shards spread proportionally across DCs, but no tighter than the durability floor (once each DC holds <= parityShards a DC loss is recoverable, so further spreading only adds cross-DC/WAN traffic). No-op when DiffDataCenterCount is 0; identical to before when the cap is the binding constraint. * ecbalancer: drop DiffDataCenterCount enforcement for EC placement The 1-byte volume ReplicaPlacement packs xyz into x*100+y*10+z<=255, so the DC digit can only be 0-2 -- far too small to be a meaningful per-DC EC shard cap (a cap of 1-2 would demand 7-14 DCs for a 10+4 volume). It's volume replica-placement, not an EC spec. Removes the cross-DC balance phase, the DC guard in the cross-rack phase, and the per-DC cap in Place (and the just-added bounded-proportional logic); EC relies on the RP-independent rack/node even spread instead. Rack/node caps (DiffRackCount/SameRackCount) are unchanged. Per-domain EC caps are left for a real EC placement spec. * ecbalancer: enforce per-disk durability cap; symmetric reserve/release Place now refuses to put more than parityShards shards of a volume on a single disk (pickBestDiskEligible skips a disk once it holds parityShards of the volume, a hard cap not relaxed even in durability-first). Previously Place assigned by free capacity, so a skewed near-full cluster could pile >parityShards onto one disk -> losing it loses the volume; only distinct-disk count was checked. This covers encode and repair (both route through Place); the caller skips/leaves the volume rather than minting an unrecoverable layout. Also makes reserveShard decrement freeSlots unconditionally, symmetric with releaseShard's unconditional increment (the old guarded decrement could credit a phantom slot on release if a shard were ever reserved onto a full disk). * ecbalancer: add Topology.ReleaseVolumeShards (clear + credit) for greenfield encode Releases all of a volume's shards from the snapshot and credits the freed disk capacity, so a greenfield encode can plan as if stale EC shards from a prior failed attempt are gone. Safe to credit because the encode task deletes stale shards (cleanupStaleEcShards) before distributing the new ones. Distinct from ClearShardAccounting (repair), which does not credit. * ecbalancer: ReleaseVolumeShards credits node freeSlots, not just disks releaseShard only increments per-disk freeSlots, but rack capacity is summed from node freeSlots (buildRacks) and node freeSlots gates node eligibility. Crediting only disks left a node/rack looking full after releasing stale shards, so a greenfield encode still couldn't use the freed capacity. Now credits the node by the total disk-slots freed. * ecbalancer: correct PlacementMode docs (encode uses durability-first) PlaceStrict was labeled '(encode)' but encode uses PlaceDurabilityFirst. Clarify that durability-first is used by both encode and repair, reports relaxations in PlaceResult.Relaxed, and never relaxes the per-disk durability cap. * ecbalancer: treat SameRackCount as a direct per-node shard cap The 3rd ReplicaPlacement digit now caps shards per node at exactly the digit value, matching how DiffRackCount (2nd digit) caps per rack, instead of allowing digit+1 per node. This makes the per-rack and per-node caps consistent and matches the documented "digits cap EC shards per rack and per node" semantics; e.g. 011 now means at most one shard per rack and one per node.
406 lines
9.8 KiB
Go
406 lines
9.8 KiB
Go
package erasure_coding
|
|
|
|
import (
|
|
"fmt"
|
|
"iter"
|
|
"math/bits"
|
|
"sort"
|
|
"strings"
|
|
"sync"
|
|
|
|
"github.com/dustin/go-humanize"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
|
|
)
|
|
|
|
// ShardBits is a bitmap representing which shards are present (bit 0 = shard 0, etc.)
|
|
type ShardBits uint32
|
|
|
|
// Has checks if a shard ID is present in the bitmap
|
|
func (sb ShardBits) Has(id ShardId) bool {
|
|
return id < MaxShardCount && sb&(1<<id) != 0
|
|
}
|
|
|
|
// Set sets a shard ID in the bitmap
|
|
func (sb ShardBits) Set(id ShardId) ShardBits {
|
|
if id >= MaxShardCount {
|
|
return sb
|
|
}
|
|
return sb | (1 << id)
|
|
}
|
|
|
|
// Clear clears a shard ID from the bitmap
|
|
func (sb ShardBits) Clear(id ShardId) ShardBits {
|
|
if id >= MaxShardCount {
|
|
return sb
|
|
}
|
|
return sb &^ (1 << id)
|
|
}
|
|
|
|
// Count returns the number of set bits using popcount
|
|
func (sb ShardBits) Count() int {
|
|
return bits.OnesCount32(uint32(sb))
|
|
}
|
|
|
|
// All iterates the shard ids present in the bitmap, in ascending order. It walks
|
|
// only the set bits (trailing-zero scan), so cost scales with the number of
|
|
// shards present rather than the full id range. Prefer this over scanning
|
|
// 0..MaxShardCount and calling Has on each id.
|
|
func (sb ShardBits) All() iter.Seq[ShardId] {
|
|
return func(yield func(ShardId) bool) {
|
|
for b := uint32(sb); b != 0; b &= b - 1 {
|
|
if !yield(ShardId(bits.TrailingZeros32(b))) {
|
|
return
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// ShardsInfo encapsulates information for EC shards with memory-efficient storage
|
|
type ShardsInfo struct {
|
|
mu sync.RWMutex
|
|
shards []ShardInfo // Sorted by Id
|
|
shardBits ShardBits
|
|
}
|
|
|
|
func NewShardsInfo() *ShardsInfo {
|
|
return &ShardsInfo{
|
|
shards: make([]ShardInfo, 0, TotalShardsCount),
|
|
}
|
|
}
|
|
|
|
// Initializes a ShardsInfo from a VolumeEcShardInformationMessage proto.
|
|
func ShardsInfoFromVolumeEcShardInformationMessage(vi *master_pb.VolumeEcShardInformationMessage) *ShardsInfo {
|
|
res := NewShardsInfo()
|
|
if vi == nil {
|
|
return res
|
|
}
|
|
|
|
var id ShardId
|
|
var j int
|
|
// Build shards directly to avoid locking in Set() since res is not yet shared
|
|
newShards := make([]ShardInfo, 0, 8)
|
|
for bitmap := vi.EcIndexBits; bitmap != 0; bitmap >>= 1 {
|
|
if bitmap&1 != 0 {
|
|
var size ShardSize
|
|
if j < len(vi.ShardSizes) {
|
|
size = ShardSize(vi.ShardSizes[j])
|
|
}
|
|
j++
|
|
newShards = append(newShards, NewShardInfo(id, size))
|
|
}
|
|
id++
|
|
}
|
|
res.shards = newShards
|
|
res.shardBits = ShardBits(vi.EcIndexBits)
|
|
|
|
return res
|
|
}
|
|
|
|
// Returns a count of shards from a VolumeEcShardInformationMessage proto.
|
|
func GetShardCount(vi *master_pb.VolumeEcShardInformationMessage) int {
|
|
if vi == nil {
|
|
return 0
|
|
}
|
|
return ShardBits(vi.EcIndexBits).Count()
|
|
}
|
|
|
|
// EcShardsTotalSize returns the sum of all shard sizes (data + parity) in
|
|
// the message. Walks vi.ShardSizes directly rather than materializing a
|
|
// ShardsInfo, which is significantly cheaper for callers that only need the
|
|
// aggregate size.
|
|
func EcShardsTotalSize(vi *master_pb.VolumeEcShardInformationMessage) int64 {
|
|
if vi == nil {
|
|
return 0
|
|
}
|
|
var total int64
|
|
for _, s := range vi.ShardSizes {
|
|
total += s
|
|
}
|
|
return total
|
|
}
|
|
|
|
// EcShardsDataSize returns the sum of sizes for data shards only (parity
|
|
// shards excluded). Data shards are those with id < dataShards; all higher
|
|
// shard ids are treated as parity. Passing dataShards <= 0 falls back to
|
|
// the upstream default of DataShardsCount (10), which is correct for the
|
|
// fixed 10+4 layout. Forks with per-volume ratio metadata (e.g. the
|
|
// data_shards field carried on an extended VolumeEcShardInformationMessage)
|
|
// should pass the per-volume value so logical sizes remain accurate under
|
|
// custom EC policies like 6+3 or 16+6.
|
|
func EcShardsDataSize(vi *master_pb.VolumeEcShardInformationMessage, dataShards int) int64 {
|
|
if vi == nil {
|
|
return 0
|
|
}
|
|
if dataShards <= 0 {
|
|
dataShards = DataShardsCount
|
|
}
|
|
var total int64
|
|
var id ShardId
|
|
var j int
|
|
for bitmap := vi.EcIndexBits; bitmap != 0; bitmap >>= 1 {
|
|
if bitmap&1 != 0 {
|
|
if int(id) < dataShards && j < len(vi.ShardSizes) {
|
|
total += vi.ShardSizes[j]
|
|
}
|
|
j++
|
|
}
|
|
id++
|
|
}
|
|
return total
|
|
}
|
|
|
|
// Returns a string representation for a ShardsInfo.
|
|
func (sp *ShardsInfo) String() string {
|
|
sp.mu.RLock()
|
|
defer sp.mu.RUnlock()
|
|
var sb strings.Builder
|
|
for i, s := range sp.shards {
|
|
if i > 0 {
|
|
sb.WriteString(" ")
|
|
}
|
|
fmt.Fprintf(&sb, "%d:%s", s.Id, humanize.Bytes(uint64(s.Size)))
|
|
}
|
|
return sb.String()
|
|
}
|
|
|
|
// AsSlice converts a ShardsInfo to a slice of ShardInfo structs, ordered by shard ID.
|
|
func (si *ShardsInfo) AsSlice() []ShardInfo {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
res := make([]ShardInfo, len(si.shards))
|
|
copy(res, si.shards)
|
|
return res
|
|
}
|
|
|
|
// Count returns the number of EC shards using popcount on the bitmap.
|
|
func (si *ShardsInfo) Count() int {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
return si.shardBits.Count()
|
|
}
|
|
|
|
// Has verifies if a shard ID is present using bitmap check.
|
|
func (si *ShardsInfo) Has(id ShardId) bool {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
return si.shardBits.Has(id)
|
|
}
|
|
|
|
// Ids returns a list of shard IDs, in ascending order.
|
|
func (si *ShardsInfo) Ids() []ShardId {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
ids := make([]ShardId, len(si.shards))
|
|
for i, s := range si.shards {
|
|
ids[i] = s.Id
|
|
}
|
|
return ids
|
|
}
|
|
|
|
// IdsInt returns a list of shards ID as int, in ascending order.
|
|
func (si *ShardsInfo) IdsInt() []int {
|
|
ids := si.Ids()
|
|
res := make([]int, len(ids))
|
|
for i, id := range ids {
|
|
res[i] = int(id)
|
|
}
|
|
return res
|
|
}
|
|
|
|
// IdsUint32 returns a list of shards ID as uint32, in ascending order.
|
|
func (si *ShardsInfo) IdsUint32() []uint32 {
|
|
return ShardIdsToUint32(si.Ids())
|
|
}
|
|
|
|
// Set sets or updates a shard's information.
|
|
func (si *ShardsInfo) Set(shard ShardInfo) {
|
|
if shard.Id >= MaxShardCount {
|
|
return
|
|
}
|
|
si.mu.Lock()
|
|
defer si.mu.Unlock()
|
|
|
|
// Check if already exists
|
|
if si.shardBits.Has(shard.Id) {
|
|
// Find and update
|
|
idx := si.findIndex(shard.Id)
|
|
if idx >= 0 {
|
|
si.shards[idx] = shard
|
|
}
|
|
return
|
|
}
|
|
|
|
// Add new shard
|
|
si.shardBits = si.shardBits.Set(shard.Id)
|
|
|
|
// Find insertion point to keep sorted
|
|
idx := sort.Search(len(si.shards), func(i int) bool {
|
|
return si.shards[i].Id > shard.Id
|
|
})
|
|
|
|
// Insert at idx
|
|
si.shards = append(si.shards, ShardInfo{})
|
|
copy(si.shards[idx+1:], si.shards[idx:])
|
|
si.shards[idx] = shard
|
|
}
|
|
|
|
// Delete deletes a shard by ID.
|
|
func (si *ShardsInfo) Delete(id ShardId) {
|
|
if id >= MaxShardCount {
|
|
return
|
|
}
|
|
si.mu.Lock()
|
|
defer si.mu.Unlock()
|
|
|
|
if !si.shardBits.Has(id) {
|
|
return // Not present
|
|
}
|
|
|
|
si.shardBits = si.shardBits.Clear(id)
|
|
|
|
// Find and remove from slice
|
|
idx := si.findIndex(id)
|
|
if idx >= 0 {
|
|
si.shards = append(si.shards[:idx], si.shards[idx+1:]...)
|
|
}
|
|
}
|
|
|
|
// Bitmap returns a bitmap for all existing shard IDs.
|
|
func (si *ShardsInfo) Bitmap() uint32 {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
return uint32(si.shardBits)
|
|
}
|
|
|
|
// Size returns the size of a given shard ID, if present.
|
|
func (si *ShardsInfo) Size(id ShardId) ShardSize {
|
|
if id >= MaxShardCount {
|
|
return 0
|
|
}
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
|
|
if !si.shardBits.Has(id) {
|
|
return 0
|
|
}
|
|
|
|
idx := si.findIndex(id)
|
|
if idx >= 0 {
|
|
return si.shards[idx].Size
|
|
}
|
|
return 0
|
|
}
|
|
|
|
// TotalSize returns the size for all shards.
|
|
func (si *ShardsInfo) TotalSize() ShardSize {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
var total ShardSize
|
|
for _, s := range si.shards {
|
|
total += s.Size
|
|
}
|
|
return total
|
|
}
|
|
|
|
// Sizes returns a compact slice of present shard sizes, from first to last.
|
|
func (si *ShardsInfo) Sizes() []ShardSize {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
|
|
res := make([]ShardSize, len(si.shards))
|
|
for i, s := range si.shards {
|
|
res[i] = s.Size
|
|
}
|
|
return res
|
|
}
|
|
|
|
// SizesInt64 returns a compact slice of present shard sizes, from first to last, as int64.
|
|
func (si *ShardsInfo) SizesInt64() []int64 {
|
|
sizes := si.Sizes()
|
|
res := make([]int64, len(sizes))
|
|
for i, s := range sizes {
|
|
res[i] = int64(s)
|
|
}
|
|
return res
|
|
}
|
|
|
|
// Copy creates a copy of a ShardInfo.
|
|
func (si *ShardsInfo) Copy() *ShardsInfo {
|
|
si.mu.RLock()
|
|
defer si.mu.RUnlock()
|
|
|
|
newShards := make([]ShardInfo, len(si.shards))
|
|
copy(newShards, si.shards)
|
|
|
|
return &ShardsInfo{
|
|
shards: newShards,
|
|
shardBits: si.shardBits,
|
|
}
|
|
}
|
|
|
|
// DeleteParityShards removes parity shards from a ShardInfo.
|
|
func (si *ShardsInfo) DeleteParityShards() {
|
|
for id := DataShardsCount; id < TotalShardsCount; id++ {
|
|
si.Delete(ShardId(id))
|
|
}
|
|
}
|
|
|
|
// MinusParityShards creates a ShardInfo copy, but with parity shards removed.
|
|
func (si *ShardsInfo) MinusParityShards() *ShardsInfo {
|
|
result := si.Copy()
|
|
result.DeleteParityShards()
|
|
return result
|
|
}
|
|
|
|
// Add merges all shards from another ShardInfo into this one.
|
|
func (si *ShardsInfo) Add(other *ShardsInfo) {
|
|
other.mu.RLock()
|
|
// Copy shards to avoid holding lock on 'other' while calling si.Set, which could deadlock.
|
|
shardsToAdd := make([]ShardInfo, len(other.shards))
|
|
copy(shardsToAdd, other.shards)
|
|
other.mu.RUnlock()
|
|
|
|
for _, s := range shardsToAdd {
|
|
si.Set(s)
|
|
}
|
|
}
|
|
|
|
// Subtract removes all shards present on another ShardInfo.
|
|
func (si *ShardsInfo) Subtract(other *ShardsInfo) {
|
|
other.mu.RLock()
|
|
// Copy shards to avoid holding lock on 'other' while calling si.Delete, which could deadlock.
|
|
shardsToRemove := make([]ShardInfo, len(other.shards))
|
|
copy(shardsToRemove, other.shards)
|
|
other.mu.RUnlock()
|
|
|
|
for _, s := range shardsToRemove {
|
|
si.Delete(s.Id)
|
|
}
|
|
}
|
|
|
|
// Plus returns a new ShardInfo consisting of (this + other).
|
|
func (si *ShardsInfo) Plus(other *ShardsInfo) *ShardsInfo {
|
|
result := si.Copy()
|
|
result.Add(other)
|
|
return result
|
|
}
|
|
|
|
// Minus returns a new ShardInfo consisting of (this - other).
|
|
func (si *ShardsInfo) Minus(other *ShardsInfo) *ShardsInfo {
|
|
result := si.Copy()
|
|
result.Subtract(other)
|
|
return result
|
|
}
|
|
|
|
// findIndex finds the index of a shard by ID using binary search.
|
|
// Must be called with lock held. Returns -1 if not found.
|
|
func (si *ShardsInfo) findIndex(id ShardId) int {
|
|
idx := sort.Search(len(si.shards), func(i int) bool {
|
|
return si.shards[i].Id >= id
|
|
})
|
|
if idx < len(si.shards) && si.shards[idx].Id == id {
|
|
return idx
|
|
}
|
|
return -1
|
|
}
|