Support DNS period resolving mechanism (#6240)

CHANGES.md

@@ -37,6 +37,7 @@ Release Notes.
 * Fix RestTemplate plugin recording url tag with wrong port
 * Support collecting logs and forwarding through gRPC.
 * Support config `agent.sample_n_per_3_secs` can be changed in the runtime.
+* Support DNS periodic resolving mechanism to update backend service.
 
 #### OAP-Backend
 * Make meter receiver support MAL.

apm-sniffer/apm-agent-core/src/main/java/org/apache/skywalking/apm/agent/core/conf/Config.java

@@ -163,11 +163,14 @@ public class Config {
          * Get profile task list interval
          */
         public static int GET_PROFILE_TASK_INTERVAL = 20;
-
         /**
          * Get agent dynamic config interval
          */
         public static int GET_AGENT_DYNAMIC_CONFIG_INTERVAL = 20;
+        /**
+         * If true, skywalking agent will enable periodically resolving DNS to update receiver service addresses.
+         */
+        public static boolean IS_RESOLVE_DNS_PERIODICALLY = false;
     }
 
     public static class Profile {

apm-sniffer/apm-agent-core/src/main/java/org/apache/skywalking/apm/agent/core/remote/GRPCChannelManager.java

@@ -21,6 +21,8 @@ package org.apache.skywalking.apm.agent.core.remote;
 import io.grpc.Channel;
 import io.grpc.Status;
 import io.grpc.StatusRuntimeException;
+
+import java.net.InetAddress;
 import java.util.Arrays;
 import java.util.Collections;
 import java.util.LinkedList;
@@ -29,6 +31,8 @@ import java.util.Random;
 import java.util.concurrent.Executors;
 import java.util.concurrent.ScheduledFuture;
 import java.util.concurrent.TimeUnit;
+import java.util.stream.Collectors;
+
 import org.apache.skywalking.apm.agent.core.boot.BootService;
 import org.apache.skywalking.apm.agent.core.boot.DefaultImplementor;
 import org.apache.skywalking.apm.agent.core.boot.DefaultNamedThreadFactory;
@@ -37,6 +41,8 @@ import org.apache.skywalking.apm.agent.core.logging.api.ILog;
 import org.apache.skywalking.apm.agent.core.logging.api.LogManager;
 import org.apache.skywalking.apm.util.RunnableWithExceptionProtection;
 
+import static org.apache.skywalking.apm.agent.core.conf.Config.Collector.IS_RESOLVE_DNS_PERIODICALLY;
+
 @DefaultImplementor
 public class GRPCChannelManager implements BootService, Runnable {
     private static final ILog LOGGER = LogManager.getLogger(GRPCChannelManager.class);
@@ -92,6 +98,23 @@ public class GRPCChannelManager implements BootService, Runnable {
     @Override
     public void run() {
         LOGGER.debug("Selected collector grpc service running, reconnect:{}.", reconnect);
+        if (IS_RESOLVE_DNS_PERIODICALLY && reconnect) {
+            String backendService = Config.Collector.BACKEND_SERVICE.split(",")[0];
+            try {
+                String[] domainAndPort = backendService.split(":");
+
+                List<String> newGrpcServers = Arrays
+                        .stream(InetAddress.getAllByName(domainAndPort[0]))
+                        .map(InetAddress::getHostAddress)
+                        .map(ip -> String.format("%s:%s", ip, domainAndPort[1]))
+                        .collect(Collectors.toList());
+
+                grpcServers = newGrpcServers;
+            } catch (Throwable t) {
+                LOGGER.error(t, "Failed to resolve {} of backend service.", backendService);
+            }
+        }
+
         if (reconnect) {
             if (grpcServers.size() > 0) {
                 String server = "";

docs/en/setup/service-agent/java-agent/README.md

@@ -95,6 +95,7 @@ property key | Description | Default |
 `collector.grpc_upstream_timeout`|How long grpc client will timeout in sending data to upstream. Unit is second.|`30` seconds|
 `collector.get_profile_task_interval`|Sniffer get profile task list interval.|`20`|
 `collector.get_agent_dynamic_config_interval`|Sniffer get agent dynamic config interval|`20`|
+`collector.dns_period_resolve_active`|If true, skywalking agent will enable periodically resolving DNS to update receiver service addresses.|`false`|
 `logging.level`|Log level: TRACE, DEBUG, INFO, WARN, ERROR, OFF. Default is info.|`INFO`|
 `logging.file_name`|Log file name.|`skywalking-api.log`|
 `logging.output`| Log output. Default is FILE. Use CONSOLE means output to stdout. |`FILE`|