xds: Fix intermittent failure in RingHashLoadBalancerTest.allSubchannelsInTransientFailure

Deliver TRANSIENT_FAILURE in deterministic server order using subchannelList
instead of iterating over subchannels.values() (HashMap), and expect 2
connections.

Why this became flaky with the new PickFirst LB:
Old PickFirst unconditionally invoked subchannel.requestConnection() on each
call without checking connection state, so triggering proactive connections
twice always produced 2 connection requests regardless of iteration order
(either [A, B] or [A, A]).

New PickFirst deduplicates connection requests if a subchannel is already in
CONNECTING state. When iterating over a HashMap, if the same subchannel was
triggered twice, New PickFirst deduplicated it to 1 connection, leading to the
assumption in grpc#13094 that New PickFirst would always yield 1 connection.
However, if two distinct subchannels were triggered (e.g. server1 then server2),
New PickFirst does not deduplicate and yields 2 connections, causing
verifyConnection(1) to fail intermittently.

Fix this by iterating deterministically in server order, which reliably triggers
two distinct subchannels (server1 and server2) in both old and new PickFirst.

TAG=agy
CONV=d59ec8a0-3bb7-41f8-bb11-76e843a2dada

Author: kannanjgithub

xds/src/test/java/io/grpc/xds/RingHashLoadBalancerTest.java

@@ -719,17 +719,17 @@ public void allSubchannelsInTransientFailure() {
     // Map each server address to exactly one ring entry.
     RingHashConfig config = new RingHashConfig(3, 3, "");
     List<EquivalentAddressGroup> servers = createWeightedServerAddrs(1, 1, 1);
-    initializeLbSubchannels(config, servers);
+    List<Subchannel> subchannelList = initializeLbSubchannels(config, servers);
 
     // Bring all subchannels to TRANSIENT_FAILURE.
-    for (Subchannel subchannel : subchannels.values()) {
+    for (Subchannel subchannel : subchannelList) {
       deliverSubchannelState(subchannel, ConnectivityStateInfo.forTransientFailure(
           Status.UNAVAILABLE.withDescription(
               subchannel.getAddresses().getAddresses() + " unreachable")));
     }
     verify(helper, atLeastOnce())
         .updateBalancingState(eq(TRANSIENT_FAILURE), pickerCaptor.capture());
-    verifyConnection(PickFirstLoadBalancerProvider.isEnabledNewPickFirst() ? 1 : 2);
+    verifyConnection(2);
 
     // Picking subchannel triggers connection. RPC hash hits server0.
     PickSubchannelArgs args = getDefaultPickSubchannelArgsForServer(0);