wdclient: prefer local volume replicas over remote-tier replicas on lookup

LookupFileIdWithFallback (and the publicUrl variant in FilerClient)
didn't honor the DataInRemote flag when shuffling URLs, so the
DataInRemote patch only took effect in LookupVolumeServerUrl. Apply
the same ReorderToFront(localUrls) to sameDcUrls/otherDcUrls so
non-remote replicas stay at the front, matching the existing vidMap
convention.

weed/wdclient/filer_client.go

@@ -468,6 +468,7 @@ func (fc *FilerClient) GetLookupFileIdFunction() LookupFileIdFunctionType {
 
 		// Build URLs with publicUrl preference, and also prefer same DC
 		var sameDcUrls, otherDcUrls []string
+		localUrls := make(map[string]bool)
 		dataCenter := fc.GetDataCenter()
 		for _, loc := range locations {
 			url := loc.PublicUrl
@@ -475,6 +476,10 @@ func (fc *FilerClient) GetLookupFileIdFunction() LookupFileIdFunctionType {
 				url = loc.Url
 			}
 			httpUrl := "http://" + url + "/" + fileId
+			glog.V(4).Infof("lookup %s => %s, data in remote storage tier: %v", fileId, url, loc.DataInRemote)
+			if !loc.DataInRemote {
+				localUrls[httpUrl] = true
+			}
 			if dataCenter != "" && dataCenter == loc.DataCenter {
 				sameDcUrls = append(sameDcUrls, httpUrl)
 			} else {
@@ -484,6 +489,12 @@ func (fc *FilerClient) GetLookupFileIdFunction() LookupFileIdFunctionType {
 		// Shuffle to distribute load across volume servers
 		rand.Shuffle(len(sameDcUrls), func(i, j int) { sameDcUrls[i], sameDcUrls[j] = sameDcUrls[j], sameDcUrls[i] })
 		rand.Shuffle(len(otherDcUrls), func(i, j int) { otherDcUrls[i], otherDcUrls[j] = otherDcUrls[j], otherDcUrls[i] })
+		// Keep local volumes in front so remote-tier replicas are only used as fallback,
+		// mirroring vidMap.LookupVolumeServerUrl
+		if len(localUrls) > 0 {
+			sameDcUrls = util.ReorderToFront(localUrls, sameDcUrls)
+			otherDcUrls = util.ReorderToFront(localUrls, otherDcUrls)
+		}
 		// Prefer same data center
 		fullUrls = append(sameDcUrls, otherDcUrls...)
 		return fullUrls, nil

weed/wdclient/vidmap_client.go

@@ -13,6 +13,7 @@ import (
 
 	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/pb"
+	"github.com/seaweedfs/seaweedfs/weed/util"
 )
 
 // VolumeLocationProvider is the interface for looking up volume locations
@@ -90,8 +91,13 @@ func (vc *vidMapClient) LookupFileIdWithFallback(ctx context.Context, fileId str
 
 	// Build HTTP URLs from locations, preferring same data center
 	var sameDcUrls, otherDcUrls []string
+	localUrls := make(map[string]bool)
 	for _, loc := range locations {
 		httpUrl := "http://" + loc.Url + "/" + fileId
+		glog.V(4).Infof("lookup %s => %s, data in remote storage tier: %v", fileId, loc.Url, loc.DataInRemote)
+		if !loc.DataInRemote {
+			localUrls[httpUrl] = true
+		}
 		if dataCenter != "" && dataCenter == loc.DataCenter {
 			sameDcUrls = append(sameDcUrls, httpUrl)
 		} else {
@@ -103,6 +109,13 @@ func (vc *vidMapClient) LookupFileIdWithFallback(ctx context.Context, fileId str
 	rand.Shuffle(len(sameDcUrls), func(i, j int) { sameDcUrls[i], sameDcUrls[j] = sameDcUrls[j], sameDcUrls[i] })
 	rand.Shuffle(len(otherDcUrls), func(i, j int) { otherDcUrls[i], otherDcUrls[j] = otherDcUrls[j], otherDcUrls[i] })
 
+	// Keep local volumes in front so remote-tier replicas are only used as fallback,
+	// mirroring vidMap.LookupVolumeServerUrl
+	if len(localUrls) > 0 {
+		sameDcUrls = util.ReorderToFront(localUrls, sameDcUrls)
+		otherDcUrls = util.ReorderToFront(localUrls, otherDcUrls)
+	}
+
 	// Prefer same data center
 	fullUrls = append(sameDcUrls, otherDcUrls...)
 	return fullUrls, nil

weed/wdclient/vidmap_client_localfirst_test.go

@@ -0,0 +1,65 @@
+package wdclient
+
+import (
+	"context"
+	"strings"
+	"testing"
+)
+
+type testLocationProvider struct {
+	locations map[string][]Location
+}
+
+func (p *testLocationProvider) LookupVolumeIds(ctx context.Context, volumeIds []string) (map[string][]Location, error) {
+	result := make(map[string][]Location)
+	for _, vid := range volumeIds {
+		if locs, found := p.locations[vid]; found {
+			result[vid] = locs
+		}
+	}
+	return result, nil
+}
+
+// TestLookupFileIdWithFallbackLocalFirst ensures volumes whose data is still
+// local are tried before remote-tier replicas, on the provider (cache miss) path.
+func TestLookupFileIdWithFallbackLocalFirst(t *testing.T) {
+	vc := newVidMapClient(&testLocationProvider{
+		locations: map[string][]Location{
+			"5": {
+				{Url: "10.0.0.1:8080", DataInRemote: true},
+				{Url: "10.0.0.2:8080", DataInRemote: false},
+			},
+		},
+	}, "", 5)
+
+	urls, err := vc.LookupFileIdWithFallback(context.Background(), "5,abcdef0123456789")
+	if err != nil {
+		t.Fatalf("lookup failed: %v", err)
+	}
+	if len(urls) != 2 {
+		t.Fatalf("expected 2 urls, got %v", urls)
+	}
+	if !strings.Contains(urls[0], "10.0.0.2:8080") {
+		t.Errorf("expected local replica first, got %v", urls)
+	}
+}
+
+// TestLookupFileIdWithFallbackAllRemote keeps shuffled order when every replica is remote.
+func TestLookupFileIdWithFallbackAllRemote(t *testing.T) {
+	vc := newVidMapClient(&testLocationProvider{
+		locations: map[string][]Location{
+			"6": {
+				{Url: "10.0.0.1:8080", DataInRemote: true},
+				{Url: "10.0.0.2:8080", DataInRemote: true},
+			},
+		},
+	}, "", 5)
+
+	urls, err := vc.LookupFileIdWithFallback(context.Background(), "6,abcdef0123456789")
+	if err != nil {
+		t.Fatalf("lookup failed: %v", err)
+	}
+	if len(urls) != 2 {
+		t.Fatalf("expected 2 urls, got %v", urls)
+	}
+}