Files
seaweedfs/weed/admin/plugin/registry_test.go
T
Чепурнов СемёнandChepurnov Simon 624a13ecc6 EC worker: pin jobs to replica-host workers, late-bind local source (#11718)
* feat: prefer same-host worker and local EC replica

Admin executor pick ranked idle workers only, so a job whose volume
lived on full-03 could still run on full-01 and pull the whole .dat
across the LAN. Rank workers whose Hello host matches any replica
first (fallback to others if the local worker is full).

Detection named Sources[0] / the lowest server id; execute then
SyncAndSelectBestReplica and could switch the copy source to another
rack. After sync, if a replica on this machine has a complete file
count, copy from that URL so affinity and pull stay on one host.

* feat: pin scheduler jobs to replica-host workers until load K

Reserve prefers the least-loaded replica-host worker and waits while
that load is below 5 instead of spilling to a free remote worker.
K=0 restores immediate spill. Waterfill uses reservation load so four
idle preferred workers each get a job.

* feat: park scheduled jobs on per-worker admin queues

Assign a detection batch to the least-loaded replica-host worker in
one pass, then let ExecutionConcurrency goroutines pop a home-runnable
job or steal when that home queue reaches K. Dispatch no longer holds
a job in reserve-backoff, so a free worker is not blocked by another
home's pin. Tracked jobs stay pending/queued and record the home
worker for the admin UI.

* fix: rehome queued jobs when the home worker dies

A live home still pins below K. A home missing from live executors
is stolen immediately onto a free worker so a short orphaned queue
does not sit until the dispatch window ends.

* feat: wait before stealing a dead home worker queue

Orphaned queues are held for 30s so a worker reconnect blink does
not dump jobs onto other machines. After the grace, steal without K
as before. Zero disables the wait. A home that comes back during
grace keeps its queue.

* fix: late-bind EC from to worker hostname

After replicas are consistent (equal FileCount), rebind encode source
to a volume server on the same hostname as worker -address. Any port
on that host is local. Diverged FileCount still uses the max replica.

* feat: assign homeless jobs to global FIFO

Jobs whose replica hostname has no registered worker skip pin and orphan grace.
Free workers take own home, then steal at K/orphan, then leftover FIFO.

* fix: take homeless FIFO before steal for no-home workers

Workers without a replica-host match take leftover first; steal (K/orphan)
only when FIFO is empty. Home workers keep own-queue, steal, then leftover.

---------

Co-authored-by: Chepurnov Simon <195125934+CHEPURNOV-S-S@users.noreply.github.com>
2026-10-13 05:31:34 +08:00

471 lines
13 KiB
Go

package plugin
import (
"reflect"
"testing"
"time"
"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
)
func TestRegistryPickDetectorPrefersMoreFreeSlots(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true, MaxDetectionConcurrency: 2, MaxExecutionConcurrency: 2},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-b",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true, MaxDetectionConcurrency: 4, MaxExecutionConcurrency: 4},
},
})
r.UpdateHeartbeat("worker-a", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-a",
DetectionSlotsUsed: 1,
DetectionSlotsTotal: 2,
})
r.UpdateHeartbeat("worker-b", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-b",
DetectionSlotsUsed: 1,
DetectionSlotsTotal: 4,
})
picked, err := r.PickDetector("vacuum")
if err != nil {
t.Fatalf("PickDetector: %v", err)
}
if picked.WorkerID != "worker-b" {
t.Fatalf("unexpected detector picked: got %s want worker-b", picked.WorkerID)
}
}
func TestRegistryPickExecutorAllowsSameWorker(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-x",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanDetect: true, CanExecute: true, MaxDetectionConcurrency: 1, MaxExecutionConcurrency: 1},
},
})
detector, err := r.PickDetector("balance")
if err != nil {
t.Fatalf("PickDetector: %v", err)
}
executor, err := r.PickExecutor("balance")
if err != nil {
t.Fatalf("PickExecutor: %v", err)
}
if detector.WorkerID != "worker-x" || executor.WorkerID != "worker-x" {
t.Fatalf("expected same worker for detect/execute, got detector=%s executor=%s", detector.WorkerID, executor.WorkerID)
}
}
func TestRegistryDetectableJobTypes(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true},
{JobType: "balance", CanDetect: false, CanExecute: true},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-b",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "ec", CanDetect: true, CanExecute: false},
{JobType: "vacuum", CanDetect: true, CanExecute: false},
},
})
got := r.DetectableJobTypes()
want := []string{"ec", "vacuum"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("unexpected detectable job types: got=%v want=%v", got, want)
}
}
func TestRegistryJobTypes(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true},
{JobType: "balance", CanExecute: true},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-b",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "ec", CanDetect: true},
},
})
got := r.JobTypes()
want := []string{"balance", "ec", "vacuum"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("unexpected job types: got=%v want=%v", got, want)
}
}
func TestRegistryListExecutorsSortedBySlots(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 2},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-b",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 4},
},
})
r.UpdateHeartbeat("worker-a", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-a",
ExecutionSlotsUsed: 1,
ExecutionSlotsTotal: 2,
})
r.UpdateHeartbeat("worker-b", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-b",
ExecutionSlotsUsed: 1,
ExecutionSlotsTotal: 4,
})
executors, err := r.ListExecutors("balance")
if err != nil {
t.Fatalf("ListExecutors: %v", err)
}
if len(executors) != 2 {
t.Fatalf("unexpected candidate count: got=%d", len(executors))
}
if executors[0].WorkerID != "worker-b" || executors[1].WorkerID != "worker-a" {
t.Fatalf("unexpected executor order: got=%s,%s", executors[0].WorkerID, executors[1].WorkerID)
}
}
func TestRegistryPickExecutorRoundRobinForTopTie(t *testing.T) {
t.Parallel()
r := NewRegistry()
for _, workerID := range []string{"worker-a", "worker-b", "worker-c"} {
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: workerID,
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 1},
},
})
}
got := make([]string, 0, 6)
for i := 0; i < 6; i++ {
executor, err := r.PickExecutor("balance")
if err != nil {
t.Fatalf("PickExecutor: %v", err)
}
got = append(got, executor.WorkerID)
}
want := []string{"worker-a", "worker-b", "worker-c", "worker-a", "worker-b", "worker-c"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("unexpected pick order: got=%v want=%v", got, want)
}
}
func TestRegistryListExecutorsRoundRobinForTopTie(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 2},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-b",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 2},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-c",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "balance", CanExecute: true, MaxExecutionConcurrency: 1},
},
})
r.UpdateHeartbeat("worker-a", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-a",
ExecutionSlotsUsed: 0,
ExecutionSlotsTotal: 2,
})
r.UpdateHeartbeat("worker-b", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-b",
ExecutionSlotsUsed: 0,
ExecutionSlotsTotal: 2,
})
r.UpdateHeartbeat("worker-c", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-c",
ExecutionSlotsUsed: 0,
ExecutionSlotsTotal: 1,
})
firstCall, err := r.ListExecutors("balance")
if err != nil {
t.Fatalf("ListExecutors first call: %v", err)
}
secondCall, err := r.ListExecutors("balance")
if err != nil {
t.Fatalf("ListExecutors second call: %v", err)
}
thirdCall, err := r.ListExecutors("balance")
if err != nil {
t.Fatalf("ListExecutors third call: %v", err)
}
if firstCall[0].WorkerID != "worker-a" || firstCall[1].WorkerID != "worker-b" || firstCall[2].WorkerID != "worker-c" {
t.Fatalf("unexpected first executor order: got=%s,%s,%s", firstCall[0].WorkerID, firstCall[1].WorkerID, firstCall[2].WorkerID)
}
if secondCall[0].WorkerID != "worker-b" || secondCall[1].WorkerID != "worker-a" || secondCall[2].WorkerID != "worker-c" {
t.Fatalf("unexpected second executor order: got=%s,%s,%s", secondCall[0].WorkerID, secondCall[1].WorkerID, secondCall[2].WorkerID)
}
if thirdCall[0].WorkerID != "worker-a" || thirdCall[1].WorkerID != "worker-b" || thirdCall[2].WorkerID != "worker-c" {
t.Fatalf("unexpected third executor order: got=%s,%s,%s", thirdCall[0].WorkerID, thirdCall[1].WorkerID, thirdCall[2].WorkerID)
}
}
func TestRegistrySkipsStaleWorkersForSelectionAndListing(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.staleAfter = 2 * time.Second
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-stale",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-fresh",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true},
},
})
r.mu.Lock()
r.sessions["worker-stale"].LastSeenAt = time.Now().Add(-10 * time.Second)
r.sessions["worker-fresh"].LastSeenAt = time.Now()
r.mu.Unlock()
picked, err := r.PickDetector("vacuum")
if err != nil {
t.Fatalf("PickDetector: %v", err)
}
if picked.WorkerID != "worker-fresh" {
t.Fatalf("unexpected detector: got=%s want=worker-fresh", picked.WorkerID)
}
if _, ok := r.Get("worker-stale"); ok {
t.Fatalf("expected stale worker to be hidden from Get")
}
if _, ok := r.Get("worker-fresh"); !ok {
t.Fatalf("expected fresh worker from Get")
}
listed := r.List()
if len(listed) != 1 || listed[0].WorkerID != "worker-fresh" {
t.Fatalf("unexpected listed workers: %+v", listed)
}
}
func TestRegistryReturnsNoDetectorWhenAllWorkersStale(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.staleAfter = 2 * time.Second
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true},
},
})
r.mu.Lock()
r.sessions["worker-a"].LastSeenAt = time.Now().Add(-10 * time.Second)
r.mu.Unlock()
if _, err := r.PickDetector("vacuum"); err == nil {
t.Fatalf("expected no detector when all workers are stale")
}
}
func TestRegistryHasCapableWorkerWithDetectCapability(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: false},
},
})
if !r.HasCapableWorker("vacuum") {
t.Fatalf("expected HasCapableWorker to return true for detect-capable worker")
}
if r.HasCapableWorker("balance") {
t.Fatalf("expected HasCapableWorker to return false for unknown job type")
}
}
func TestRegistryHasCapableWorkerWithExecuteCapability(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: false, CanExecute: true},
},
})
if !r.HasCapableWorker("vacuum") {
t.Fatalf("expected HasCapableWorker to return true for execute-capable worker")
}
}
func TestRegistryHasCapableWorkerReturnsFalseWhenNoWorkers(t *testing.T) {
t.Parallel()
r := NewRegistry()
if r.HasCapableWorker("vacuum") {
t.Fatalf("expected HasCapableWorker to return false with no workers")
}
}
func TestRegistryHasCapableWorkerSkipsStaleWorkers(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.staleAfter = 2 * time.Second
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-stale",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: true, CanExecute: true},
},
})
r.mu.Lock()
r.sessions["worker-stale"].LastSeenAt = time.Now().Add(-10 * time.Second)
r.mu.Unlock()
if r.HasCapableWorker("vacuum") {
t.Fatalf("expected HasCapableWorker to return false when all workers are stale")
}
}
func TestRegistryHasCapableWorkerIgnoresNilCapability(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-a",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "vacuum", CanDetect: false, CanExecute: false},
},
})
if r.HasCapableWorker("vacuum") {
t.Fatalf("expected HasCapableWorker to return false when capability has no detect or execute")
}
}
func TestListExecutorsPrefersMatchingReplicaHost(t *testing.T) {
t.Parallel()
r := NewRegistry()
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-remote",
Address: "10.87.0.4:33646",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "erasure_coding", CanExecute: true, MaxExecutionConcurrency: 8},
},
})
r.UpsertFromHello(&plugin_pb.WorkerHello{
WorkerId: "worker-local",
Address: "10.87.0.3:33646",
Capabilities: []*plugin_pb.JobTypeCapability{
{JobType: "erasure_coding", CanExecute: true, MaxExecutionConcurrency: 1},
},
})
r.UpdateHeartbeat("worker-remote", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-remote", ExecutionSlotsUsed: 0, ExecutionSlotsTotal: 8,
})
r.UpdateHeartbeat("worker-local", &plugin_pb.WorkerHeartbeat{
WorkerId: "worker-local", ExecutionSlotsUsed: 0, ExecutionSlotsTotal: 1,
})
// Without preference the emptier remote worker wins on slots.
plain, err := r.ListExecutors("erasure_coding")
if err != nil {
t.Fatalf("ListExecutors: %v", err)
}
if plain[0].WorkerID != "worker-remote" {
t.Fatalf("without preference want remote first, got %s", plain[0].WorkerID)
}
// Replica on :8080 of the same host as worker-local.
pref, err := r.ListExecutors("erasure_coding", "10.87.0.3:8080")
if err != nil {
t.Fatalf("ListExecutors preferred: %v", err)
}
if pref[0].WorkerID != "worker-local" {
t.Fatalf("preferred host want worker-local first, got %s", pref[0].WorkerID)
}
if pref[1].WorkerID != "worker-remote" {
t.Fatalf("remote should still be fallback, got %s", pref[1].WorkerID)
}
}
func TestJobReplicaHostsFromSourcesAndReplicaServers(t *testing.T) {
t.Parallel()
job := &plugin_pb.JobSpec{
Parameters: map[string]*plugin_pb.ConfigValue{
"source_server": {
Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "10.87.0.1:8080"},
},
"replica_servers": {
Kind: &plugin_pb.ConfigValue_StringList{
StringList: &plugin_pb.StringList{Values: []string{"10.87.0.1:8080", "10.87.0.2:8081"}},
},
},
},
}
got := JobReplicaHosts(job)
if len(got) != 2 {
t.Fatalf("got %v", got)
}
}