Merge pull request #370 from Luap99/ENOBUFS

handle ENOBUFS when writing to VM socket

pkg/tap/switch.go

@@ -7,6 +7,7 @@ import (
 	"net"
 	"sync"
 	"sync/atomic"
+	"syscall"
 
 	"github.com/containers/gvisor-tap-vsock/pkg/types"
 	"github.com/google/gopacket"
@@ -167,18 +168,21 @@ func (e *Switch) txBuf(id int, conn protocolConn, buf []byte) error {
 	if conn.protocolImpl.Stream() {
 		size := conn.protocolImpl.(streamProtocol).Buf()
 		conn.protocolImpl.(streamProtocol).Write(size, len(buf))
-
-		if _, err := conn.Write(append(size, buf...)); err != nil {
-			e.disconnect(id, conn)
-			return err
-		}
-	} else {
+		buf = append(size, buf...)
+	}
+	for {
 		if _, err := conn.Write(buf); err != nil {
+			if errors.Is(err, syscall.ENOBUFS) {
+				// socket buffer can be full keep retrying sending the same data
+				// again until it works or we get a different error
+				// https://github.com/containers/gvisor-tap-vsock/issues/367
+				continue
+			}
 			e.disconnect(id, conn)
 			return err
 		}
+		return nil
 	}
-	return nil
 }
 
 func (e *Switch) disconnect(id int, conn net.Conn) {

test/basic_test.go

@@ -74,10 +74,10 @@ var _ = ginkgo.Describe("dns", func() {
 		gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
 		gomega.Expect(string(out)).To(gomega.ContainSubstring(`_ldap._tcp.google.com	service = 5 0 389 ldap.google.com.`))
 	})
-	ginkgo.It("should resolve TXT for wikipedia.org", func() {
-		out, err := sshExec("nslookup -query=txt wikipedia.org")
+	ginkgo.It("should resolve TXT for crc.dev", func() {
+		out, err := sshExec("nslookup -query=txt crc.dev")
 		gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
-		gomega.Expect(string(out)).To(gomega.ContainSubstring(`"v=spf1 -all"`))
+		gomega.Expect(string(out)).To(gomega.ContainSubstring(`text = "v=spf1`))
 	})
 
 	ginkgo.It("should resolve gateway.containers.internal", func() {