From b2cb0d01258a84af0dbd3ba4efda6eb4cecf1c8e Mon Sep 17 00:00:00 2001
From: morningman <morningman@163.com>
Date: Tue, 13 Aug 2019 17:59:32 +0800
Subject: [PATCH] Fix bug that bad replica can not be synchronized when report

When the replica is recovered from bad on BE, the report process
should change the bad status of replica on FE to false, or the replica
can not be recovered.
---
 fe/src/main/java/org/apache/doris/catalog/Catalog.java |  1 +
 .../org/apache/doris/catalog/TabletInvertedIndex.java  | 10 ++++++++--
 .../java/org/apache/doris/master/ReportHandler.java    |  6 ++++--
 3 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/fe/src/main/java/org/apache/doris/catalog/Catalog.java b/fe/src/main/java/org/apache/doris/catalog/Catalog.java
index 0cc9aa638ae7e4..26330385e36b6f 100644
--- a/fe/src/main/java/org/apache/doris/catalog/Catalog.java
+++ b/fe/src/main/java/org/apache/doris/catalog/Catalog.java
@@ -4227,6 +4227,7 @@ private void unprotectUpdateReplica(ReplicaPersistInfo info) {
         Replica replica = tablet.getReplicaByBackendId(info.getBackendId());
         Preconditions.checkNotNull(replica, info);
         replica.updateVersionInfo(info.getVersion(), info.getVersionHash(), info.getDataSize(), info.getRowCount());
+        replica.setBad(false);
     }
 
     public void replayAddReplica(ReplicaPersistInfo info) {
diff --git a/fe/src/main/java/org/apache/doris/catalog/TabletInvertedIndex.java b/fe/src/main/java/org/apache/doris/catalog/TabletInvertedIndex.java
index b87a5f3d69e307..a6006620554bff 100644
--- a/fe/src/main/java/org/apache/doris/catalog/TabletInvertedIndex.java
+++ b/fe/src/main/java/org/apache/doris/catalog/TabletInvertedIndex.java
@@ -349,11 +349,17 @@ private boolean needSync(Replica replicaInFe, TTabletInfo backendTabletInfo) {
         }
         long versionInFe = replicaInFe.getVersion();
         long versionHashInFe = replicaInFe.getVersionHash();
+        
         if (backendTabletInfo.getVersion() > versionInFe
-                || (versionInFe == backendTabletInfo.getVersion()
-                        && versionHashInFe != backendTabletInfo.getVersion_hash())) {
+                || (versionInFe == backendTabletInfo.getVersion() && versionHashInFe != backendTabletInfo.getVersion_hash())) {
+            // backend replica's version is larger or newer than replica in FE, sync it.
+            return true;
+        } else if (versionInFe == backendTabletInfo.getVersion() && versionHashInFe == backendTabletInfo.getVersion_hash()
+                && replicaInFe.isBad()) {
+            // backend replica's version is equal to replica in FE, but replica in FE is bad, while backend replica is good, sync it
             return true;
         }
+        
         return false;
     }
     
diff --git a/fe/src/main/java/org/apache/doris/master/ReportHandler.java b/fe/src/main/java/org/apache/doris/master/ReportHandler.java
index a040ad70a70d35..462ddde216144e 100644
--- a/fe/src/main/java/org/apache/doris/master/ReportHandler.java
+++ b/fe/src/main/java/org/apache/doris/master/ReportHandler.java
@@ -436,7 +436,8 @@ private static void sync(Map<Long, TTablet> backendTablets, ListMultimap<Long, L
                         }
 
                         if (metaVersion < backendVersion
-                                || (metaVersion == backendVersion && metaVersionHash != backendVersionHash)) {
+                                || (metaVersion == backendVersion && metaVersionHash != backendVersionHash)
+                                || (metaVersion == backendVersion && metaVersionHash == backendVersionHash && replica.isBad())) {
                             
                             // This is just a optimization for the old compatibility
                             // The init version in FE is (1-0), in BE is (2-0)
@@ -455,7 +456,8 @@ private static void sync(Map<Long, TTablet> backendTablets, ListMultimap<Long, L
                             // 1. PUSH finished in BE but failed or not yet report to FE
                             // 2. repair for VERSION_INCOMPLETE finished in BE, but failed or not yet report to FE
                             replica.updateVersionInfo(backendVersion, backendVersionHash, dataSize, rowCount);
-                            
+                            replica.setBad(false);
+
                             if (replica.getLastFailedVersion() < 0 && !isInitVersion) {
                                 // last failed version < 0 means this replica becomes health after sync,
                                 // so we write an edit log to sync this operation