iop/apps/edge/internal/service/service_internal_test.go

121 lines
3.2 KiB
Go

package service
import (
"context"
"errors"
"net"
"strings"
"testing"
"time"
toki "git.toki-labs.com/toki/proto-socket/go"
"google.golang.org/protobuf/proto"
edgeevents "iop/apps/edge/internal/events"
edgenode "iop/apps/edge/internal/node"
"iop/packages/go/config"
iop "iop/proto/gen/iop"
)
func TestSubmitRunModelQueueUsesRoutePolicyBeforeProviderInstancePolicy(t *testing.T) {
parserMap := toki.ParserMap{
toki.TypeNameOf(&iop.RunRequest{}): func(b []byte) (proto.Message, error) {
m := &iop.RunRequest{}
return m, proto.Unmarshal(b, m)
},
}
edgeConn, nodeConn := net.Pipe()
defer edgeConn.Close()
defer nodeConn.Close()
edgeClient := toki.NewTcpClient(edgeConn, 0, 0, parserMap)
nodeClient := toki.NewTcpClient(nodeConn, 0, 0, parserMap)
toki.AddListenerTyped[*iop.RunRequest](&nodeClient.Communicator, func(*iop.RunRequest) {})
reg := edgenode.NewRegistry()
reg.Register(&edgenode.NodeEntry{NodeID: "prov-node-route-policy", Client: edgeClient})
store := edgenode.NewNodeStore()
store.Add(&edgenode.NodeRecord{
ID: "prov-node-route-policy",
Adapters: config.AdaptersConf{
OllamaInstances: []config.OllamaInstanceConf{
{
Name: "ollama-local",
Enabled: true,
Capacity: 1,
MaxQueue: 10,
},
},
},
Runtime: config.RuntimeConf{Concurrency: 1},
})
bus := edgeevents.NewBus()
svc := New(reg, bus)
svc.SetNodeStore(store)
// run 1: fills capacity (capacity is 1)
res1, err := svc.SubmitRun(context.Background(), SubmitRunRequest{
ModelGroupKey: "route-policy-group",
Adapter: "ollama-local",
Background: true,
MaxQueue: 1,
})
if err != nil {
t.Fatalf("run1 error: %v", err)
}
defer res1.Close()
// run 2: enters queue in a separate goroutine
ctx2, cancel2 := context.WithCancel(context.Background())
defer cancel2()
errCh2 := make(chan error, 1)
go func() {
res2, err := svc.SubmitRun(ctx2, SubmitRunRequest{
ModelGroupKey: "route-policy-group",
Adapter: "ollama-local",
Background: true,
MaxQueue: 1,
})
if err == nil {
res2.Close()
}
errCh2 <- err
}()
// Wait explicitly until run 2 enters the queue
waitForQueueLen(t, svc.queue, "route-policy-group", 1)
// run 3: should be rejected immediately because queue is full (max queue = 1, and run2 is in the queue)
// We use a short timeout context to prevent blocking indefinitely if something fails.
ctx3, cancel3 := context.WithTimeout(context.Background(), 2*time.Second)
defer cancel3()
_, err3 := svc.SubmitRun(ctx3, SubmitRunRequest{
ModelGroupKey: "route-policy-group",
Adapter: "ollama-local",
Background: true,
MaxQueue: 1,
})
if err3 == nil {
t.Fatal("expected third run to fail immediately due to queue full")
}
if !strings.Contains(err3.Error(), "queue is full") {
t.Errorf("expected queue is full error, got: %v", err3)
}
// clean up run2 and verify it exits
cancel2()
select {
case err2 := <-errCh2:
if err2 == nil {
t.Error("expected run2 to fail with context cancelled, got nil")
} else if !errors.Is(err2, context.Canceled) {
t.Errorf("expected run2 to fail with context cancelled, got: %v", err2)
}
case <-time.After(1 * time.Second):
t.Error("timeout waiting for run2 goroutine to exit")
}
}