[Segment Replication] Bump segment infos counter before commit during…

… replica promotion (#4365) (#4397) * [Segment Replication] Bump segment infos counter before commit during replica promotion Signed-off-by: Suraj Singh <surajrider@gmail.com> * Add changelog entry Signed-off-by: Suraj Singh <surajrider@gmail.com> Signed-off-by: Suraj Singh <surajrider@gmail.com> Signed-off-by: Suraj Singh <surajrider@gmail.com>
opensearch-project · Sep 3, 2022 · 5985955 · 5985955
1 parent dfd0328
commit 5985955
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -46,6 +46,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 - PR reference to checkout code for changelog verifier ([#4296](https://github.com/opensearch-project/OpenSearch/pull/4296))
 - Restore using the class ClusterInfoRequest and ClusterInfoRequestBuilder from package 'org.opensearch.action.support.master.info' for subclasses ([#4324](https://github.com/opensearch-project/OpenSearch/pull/4324))
 - Fixed cancellation of segment replication events ([#4225](https://github.com/opensearch-project/OpenSearch/pull/4225))
+- [Segment Replication] Bump segment infos counter before commit during replica promotion ([#4365](https://github.com/opensearch-project/OpenSearch/pull/4365))
 
 ### Security
 

diff --git a/server/src/main/java/org/opensearch/index/engine/NRTReplicationEngine.java b/server/src/main/java/org/opensearch/index/engine/NRTReplicationEngine.java
@@ -56,6 +56,8 @@ public class NRTReplicationEngine extends Engine implements LifecycleAware {
     private final LocalCheckpointTracker localCheckpointTracker;
     private final WriteOnlyTranslogManager translogManager;
 
+    private static final int SI_COUNTER_INCREMENT = 10;
+
     public NRTReplicationEngine(EngineConfig engineConfig) {
         super(engineConfig);
         store.incRef();
@@ -142,6 +144,13 @@ public synchronized void updateSegments(final SegmentInfos infos, long seqNo) th
     public void commitSegmentInfos() throws IOException {
         // TODO: This method should wait for replication events to finalize.
         final SegmentInfos latestSegmentInfos = getLatestSegmentInfos();
+        /*
+         This is a workaround solution which decreases the chances of conflict on replica nodes when same file is copied
+         from two different primaries during failover. Increasing counter helps in avoiding this conflict as counter is
+         used to generate new segment file names. The ideal solution is to identify the counter from previous primary.
+         */
+        latestSegmentInfos.counter = latestSegmentInfos.counter + SI_COUNTER_INCREMENT;
+        latestSegmentInfos.changed();
         store.commitSegmentInfos(latestSegmentInfos, localCheckpointTracker.getMaxSeqNo(), localCheckpointTracker.getProcessedCheckpoint());
         translogManager.syncTranslog();
     }

diff --git a/server/src/test/java/org/opensearch/index/engine/NRTReplicationEngineTests.java b/server/src/test/java/org/opensearch/index/engine/NRTReplicationEngineTests.java
@@ -245,6 +245,8 @@ public void testCommitSegmentInfos() throws Exception {
             // ensure getLatestSegmentInfos returns an updated infos ref with correct userdata.
             final SegmentInfos latestSegmentInfos = nrtEngine.getLatestSegmentInfos();
             assertEquals(previousInfos.getGeneration(), latestSegmentInfos.getLastGeneration());
+            assertEquals(previousInfos.getVersion(), latestSegmentInfos.getVersion());
+            assertEquals(previousInfos.counter, latestSegmentInfos.counter);
             Map<String, String> userData = latestSegmentInfos.getUserData();
             assertEquals(processedCheckpoint, localCheckpointTracker.getProcessedCheckpoint());
             assertEquals(maxSeqNo, Long.parseLong(userData.get(MAX_SEQ_NO)));