From 7f7d3337a05f2de8c82a5862e74e1bd7def2aff7 Mon Sep 17 00:00:00 2001
From: Siyao Meng <siyao@apache.org>
Date: Tue, 3 Nov 2020 13:47:28 -0800
Subject: [PATCH] HDDS-4404. Datanode can go OOM when a Recon or SCM Server is
 very slow in processing reports

Change-Id: I94df595074a0b3cff7acdd4e220302d6f7bd49b0
---
 .../common/states/endpoint/HeartbeatEndpointTask.java     | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/common/states/endpoint/HeartbeatEndpointTask.java b/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/common/states/endpoint/HeartbeatEndpointTask.java
index da2034d93c2d..911b4b1536c2 100644
--- a/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/common/states/endpoint/HeartbeatEndpointTask.java
+++ b/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/common/states/endpoint/HeartbeatEndpointTask.java
@@ -147,8 +147,12 @@ public EndpointStateMachine.EndPointStates call() throws Exception {
       rpcEndpoint.setLastSuccessfulHeartbeat(ZonedDateTime.now());
       rpcEndpoint.zeroMissedCount();
     } catch (IOException ex) {
-      // put back the reports which failed to be sent
-      putBackReports(requestBuilder);
+      // don't resend reports to recon as it could be down for days
+      // DN is expected to work fine without recon and not go OOM
+      if (!rpcEndpoint.isPassive()) {
+        // put back the reports which failed to be sent
+        putBackReports(requestBuilder);
+      }
 
       rpcEndpoint.logIfNeeded(ex);
     } finally {