From 890e5c8bd873d9a5cd298f0121c11d93da81c080 Mon Sep 17 00:00:00 2001
From: chrislu <chris.lu@gmail.com>
Date: Thu, 20 Nov 2025 17:28:03 -0800
Subject: [PATCH] fix: add timeout to master volume lookup to prevent
 indefinite blocking

The masterVolumeProvider.LookupVolumeIds method was using the context
directly without a timeout, which could cause it to block indefinitely
if the master is slow to respond or unreachable.

Problem:
  err := pb.WithMasterClient(false, p.masterClient.GetMaster(ctx), ...)
  resp, err := client.LookupVolume(ctx, &master_pb.LookupVolumeRequest{...})

  - No timeout on gRPC call to master
  - Could block indefinitely if master is unresponsive
  - Inconsistent with FilerClient which uses 5s timeout
  - This is a fallback path (cache miss) but still needs protection

Scenarios where this could hang:
  1. Master server under heavy load (slow response)
  2. Network issues between client and master
  3. Master server hung or deadlocked
  4. Master in process of shutting down

Fix:
  timeoutCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
  defer cancel()

  err := pb.WithMasterClient(false, p.masterClient.GetMaster(timeoutCtx), ...)
  resp, err := client.LookupVolume(timeoutCtx, &master_pb.LookupVolumeRequest{...})

Benefits:
  - Prevents indefinite blocking on master lookup
  - Consistent with FilerClient timeout pattern (5 seconds)
  - Faster failure detection when master is unresponsive
  - Caller's context still honored (timeout is in addition, not replacement)
  - Improves overall system resilience

Note: 5 seconds is a reasonable default for volume lookups:
  - Long enough for normal master response (~10-50ms)
  - Short enough to fail fast on issues
  - Matches FilerClient's grpcTimeout default
---
 weed/wdclient/masterclient.go | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/weed/wdclient/masterclient.go b/weed/wdclient/masterclient.go
index 496daad3b..afbcbaa4b 100644
--- a/weed/wdclient/masterclient.go
+++ b/weed/wdclient/masterclient.go
@@ -34,8 +34,12 @@ func (p *masterVolumeProvider) LookupVolumeIds(ctx context.Context, volumeIds []
 
 	glog.V(2).Infof("Looking up %d volumes from master: %v", len(volumeIds), volumeIds)
 
-	err := pb.WithMasterClient(false, p.masterClient.GetMaster(ctx), p.masterClient.grpcDialOption, false, func(client master_pb.SeaweedClient) error {
-		resp, err := client.LookupVolume(ctx, &master_pb.LookupVolumeRequest{
+	// Use a timeout for the master lookup to prevent indefinite blocking
+	timeoutCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
+	defer cancel()
+
+	err := pb.WithMasterClient(false, p.masterClient.GetMaster(timeoutCtx), p.masterClient.grpcDialOption, false, func(client master_pb.SeaweedClient) error {
+		resp, err := client.LookupVolume(timeoutCtx, &master_pb.LookupVolumeRequest{
 			VolumeOrFileIds: volumeIds,
 		})
 		if err != nil {