Files
upstream-seaweedfs/weed/topology/balancer/replica_selection.go
upstream-mirror 89f5be005d
Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
snapshot of https://github.com/seaweedfs/seaweedfs.git (master, 2026-09-16; blobs > 131072B omitted)
2026-09-16 03:23:42 +05:00

162 lines
5.0 KiB
Go

package balancer
import (
"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
)
// Replica pairs a replica's placement location with the volume attributes
// replica-selection decisions need. Like Location for placement checks, it is
// the shared shape the shell (from master_pb) and workers adapt to. Selection
// functions return an index into the given slice (-1 when nothing qualifies),
// so callers can map the choice back to their own richer replica type.
type Replica struct {
Location Location
Size uint64
ModifiedAtSecond int64
CompactRevision uint32
ReadOnly bool
}
// SatisfyReplicaCurrentLocation reports whether the existing replicas already
// span the failure domains the policy requires (enough data centers, enough
// racks, and the same-rack count somewhere). A volume whose replica count is
// right but whose spread falls short still needs another replica.
func SatisfyReplicaCurrentLocation(rp *super_block.ReplicaPlacement, replicas []Location) bool {
dcCounts, rackCounts, _ := countReplicas(replicas)
if rp.DiffDataCenterCount+1 > len(dcCounts) {
return false
}
if rp.DiffRackCount+1 > len(rackCounts) {
return false
}
if rp.SameRackCount > 0 {
for _, rackCount := range rackCounts {
if rackCount >= rp.SameRackCount+1 {
return true
}
}
return false
}
return true
}
// PickOneReplicaToCopyFrom returns the most recently modified replica, the
// best source for adding a new replica.
func PickOneReplicaToCopyFrom(replicas []Replica) int {
mostRecent := -1
for i, r := range replicas {
if mostRecent < 0 || r.ModifiedAtSecond > replicas[mostRecent].ModifiedAtSecond {
mostRecent = i
}
}
return mostRecent
}
// IsMisplaced reports whether any replica sits at a location inconsistent
// with the replication policy given the other replicas' locations.
func IsMisplaced(replicas []Replica, rp *super_block.ReplicaPlacement) bool {
for i := range replicas {
others := otherThan(replicas, i)
locs := make([]Location, len(others))
for j, r := range others {
locs[j] = r.Location
}
if !SatisfyReplicaPlacement(rp, locs, replicas[i].Location) {
return true
}
}
return false
}
// PickSmallestReplica returns the smallest replica (ties broken by oldest
// then lowest compact revision).
func PickSmallestReplica(replicas []Replica) int {
smallest := -1
for i := range replicas {
if smallest < 0 || lessReplica(replicas[i], replicas[smallest]) {
smallest = i
}
}
return smallest
}
// PickOneReplicaToDelete selects the replica to trim when over-replicated.
// It only ever removes the smallest of multiple healthy writable replicas: a
// ReadOnly/integrity-flagged replica is never chosen for deletion, and the
// trim is refused (returns -1) when removing a writable replica would leave
// only ReadOnly survivors. Among the writable replicas it prefers one whose
// removal still satisfies placement, so the trim does not strip the only
// replica in a required failure domain; it falls back to the smallest
// writable if none keeps placement (a later misplaced cycle then
// re-balances).
func PickOneReplicaToDelete(replicas []Replica, rp *super_block.ReplicaPlacement) int {
var writable []int
for i, r := range replicas {
if !r.ReadOnly {
writable = append(writable, i)
}
}
if len(writable) < 2 {
return -1
}
var placementSafe []int
for _, i := range writable {
if !IsMisplaced(otherThan(replicas, i), rp) {
placementSafe = append(placementSafe, i)
}
}
if len(placementSafe) > 0 {
return pickSmallestAmong(replicas, placementSafe)
}
return pickSmallestAmong(replicas, writable)
}
// PickOneMisplacedVolume selects the replica to delete and recreate at a
// correct placement. This is relocation, not over-replication: unlike
// PickOneReplicaToDelete it must still act on read-only replicas (e.g. a full
// but misplaced volume), so it does not use the writable-survivor guard. It
// prefers a replica whose removal leaves the others well placed, and falls
// back to the smallest replica.
func PickOneMisplacedVolume(replicas []Replica, rp *super_block.ReplicaPlacement) int {
var deletionCandidates []int
for i := range replicas {
if !IsMisplaced(otherThan(replicas, i), rp) {
deletionCandidates = append(deletionCandidates, i)
}
}
if smallest := pickSmallestAmong(replicas, deletionCandidates); smallest >= 0 {
return smallest
}
return PickSmallestReplica(replicas)
}
func pickSmallestAmong(replicas []Replica, candidates []int) int {
smallest := -1
for _, i := range candidates {
if smallest < 0 || lessReplica(replicas[i], replicas[smallest]) {
smallest = i
}
}
return smallest
}
func lessReplica(a, b Replica) bool {
if a.Size != b.Size {
return a.Size < b.Size
}
if a.ModifiedAtSecond != b.ModifiedAtSecond {
return a.ModifiedAtSecond < b.ModifiedAtSecond
}
return a.CompactRevision < b.CompactRevision
}
func otherThan(replicas []Replica, index int) (others []Replica) {
for i := range replicas {
if index != i {
others = append(others, replicas[i])
}
}
return
}