Uploaded image for project: 'Core Server'
  1. Core Server
  2. SERVER-54746

Two primaries in a replica set can satisfy write concern "majority".

    XMLWordPrintable

    Details

    • Type: Bug
    • Status: Closed
    • Priority: Major - P3
    • Resolution: Works as Designed
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: Replication
    • Labels:
      None
    • Operating System:
      ALL
    • Steps To Reproduce:
      Hide

      /*
       * This test demonstrates 2 primaries existing in the same replica set and both primaries
       * can satisfy majority write concern.
       *
       * Basically the test simulates below scenario
       * Note: 'P' refers primary, 'S' refers to secondary.
       * 1) [P, S0, S1] // Start a 3 node replica set.
       * 2) Partition A: [P] Partition B: [S0->P, S1] // Create n/w partition A & B.
       * 3) Partition A: [P, S2] Partition B: [P, S1] // Replace S1 by a new node S2 to Partition A using the  member id of S1.
       */
      load('jstests/replsets/rslib.js');
      (function() {
      'use strict';
       
      // Start a 3 node replica set.
      // [P, S0, S1]
      const rst = new ReplSetTest({
          nodes: [{}, {}, {rsConfig: {priority: 0}}],
          useBridge: true
      });
       
      // Disable Chaining and disable automatic election from happening due to liveness timeout.
      var config = rst.getReplSetConfig();
      config.settings = config.settings || {};
      config.settings["chainingAllowed"] = false;
      config.settings["electionTimeoutMillis"] = ReplSetTest.kForeverMillis;
       
      rst.startSet();
      rst.initiate(config);
       
      const dbName = jsTest.name();
      const collName = "coll";
       
      let primary1 = rst.getPrimary();
      const primaryDB = primary1.getDB(dbName);
      const primaryColl = primaryDB[collName];
      const secondaries = rst.getSecondaries();
       
      jsTestLog("Do a document write");
      assert.commandWorked(primaryColl.insert({_id: 1, x: 1}, {"writeConcern": {"w": 3}}));
      rst.awaitReplication();
       
      // Create a n/w partition such that we result in this state [P] [S0, S1].
      jsTestLog("Disconnect primary1 from all secondaries");
      primary1.disconnect([secondaries[0], secondaries[1]]);
       
      jsTestLog("Make secondary0 to be become primary");
      assert.commandWorked(secondaries[0].adminCommand({"replSetStepUp": 1}));
       
      // Now our network topology will be [P] [S0->P, S1].
      jsTestLog("Wait for secondary0 to become master");
      checkLog.contains(secondaries[0], "Transition to primary complete");
      let primary2 = secondaries[0];
       
       
      // Make sure the new writes is able to propagate to the newly added node.
      jsTestLog("Do a document write on the primary2");
      assert.commandWorked(
          primary2.getDB(dbName)[collName].insert({_id: 2, x: 2}, {"writeConcern": {"w": "majority"}}));
       
       
      jsTestLog("Adding a new voting node to the replica set");
      let origConfig = rst.getReplSetConfigFromNode(primary1.nodeId);
      const node4 = rst.add({
          rsConfig: {priority: 0, votes: 1},
          setParameter: {
              'numInitialSyncAttempts': 1
          }
      });
       
      // Simulate this network topology [P, S2] [P, S1].
      node4.disconnect([secondaries[0], secondaries[1]]);
       
      // Run a reconfig command on the primary1 to add node 4
      var newConfig = rst.getReplSetConfig();
      // Only reset members.
      origConfig.members[2].host = newConfig.members[3].host;
      origConfig.version += 1;
      assert.adminCommandWorkedAllowingNetworkError(
          primary1, {replSetReconfig: origConfig, maxTimeMS: ReplSetTest.kDefaultTimeoutMS});
       
      jsTestLog(
          "Do some document writes to verify we have 2 primaries and both satisfy write concern majority");
      assert.commandWorked(primary1.getDB(dbName)[collName].insert({_id: 3, x: "primary1 Doc"},
                                                                   {"writeConcern": {"w": "majority"}}));
      assert.commandWorked(primary2.getDB(dbName)[collName].insert({_id: 6, x: "primary2 Doc"},
                                                                   {"writeConcern": {"w": "majority"}}));
       
      jsTestLog("Verify our primary1 can be get re-elected.");
      assert.commandWorked(primary1.adminCommand({"replSetStepDown": 1000, "force": true}));
      assert.commandWorked(primary1.adminCommand({replSetFreeze: 0}));
      assert.commandWorked(primary1.adminCommand({"replSetStepUp": 1}));
       
      jsTestLog("Test completed");
      rst.stopSet();
      }());
      

      Show
      /* * This test demonstrates 2 primaries existing in the same replica set and both primaries * can satisfy majority write concern. * * Basically the test simulates below scenario * Note: 'P' refers primary, 'S' refers to secondary. * 1) [P, S0, S1] // Start a 3 node replica set. * 2) Partition A: [P] Partition B: [S0->P, S1] // Create n/w partition A & B. * 3) Partition A: [P, S2] Partition B: [P, S1] // Replace S1 by a new node S2 to Partition A using the member id of S1. */ load('jstests/replsets/rslib.js'); (function() { 'use strict';   // Start a 3 node replica set. // [P, S0, S1] const rst = new ReplSetTest({ nodes: [{}, {}, {rsConfig: {priority: 0}}], useBridge: true });   // Disable Chaining and disable automatic election from happening due to liveness timeout. var config = rst.getReplSetConfig(); config.settings = config.settings || {}; config.settings["chainingAllowed"] = false; config.settings["electionTimeoutMillis"] = ReplSetTest.kForeverMillis;   rst.startSet(); rst.initiate(config);   const dbName = jsTest.name(); const collName = "coll";   let primary1 = rst.getPrimary(); const primaryDB = primary1.getDB(dbName); const primaryColl = primaryDB[collName]; const secondaries = rst.getSecondaries();   jsTestLog("Do a document write"); assert.commandWorked(primaryColl.insert({_id: 1, x: 1}, {"writeConcern": {"w": 3}})); rst.awaitReplication();   // Create a n/w partition such that we result in this state [P] [S0, S1]. jsTestLog("Disconnect primary1 from all secondaries"); primary1.disconnect([secondaries[0], secondaries[1]]);   jsTestLog("Make secondary0 to be become primary"); assert.commandWorked(secondaries[0].adminCommand({"replSetStepUp": 1}));   // Now our network topology will be [P] [S0->P, S1]. jsTestLog("Wait for secondary0 to become master"); checkLog.contains(secondaries[0], "Transition to primary complete"); let primary2 = secondaries[0];     // Make sure the new writes is able to propagate to the newly added node. jsTestLog("Do a document write on the primary2"); assert.commandWorked( primary2.getDB(dbName)[collName].insert({_id: 2, x: 2}, {"writeConcern": {"w": "majority"}}));     jsTestLog("Adding a new voting node to the replica set"); let origConfig = rst.getReplSetConfigFromNode(primary1.nodeId); const node4 = rst.add({ rsConfig: {priority: 0, votes: 1}, setParameter: { 'numInitialSyncAttempts': 1 } });   // Simulate this network topology [P, S2] [P, S1]. node4.disconnect([secondaries[0], secondaries[1]]);   // Run a reconfig command on the primary1 to add node 4 var newConfig = rst.getReplSetConfig(); // Only reset members. origConfig.members[2].host = newConfig.members[3].host; origConfig.version += 1; assert.adminCommandWorkedAllowingNetworkError( primary1, {replSetReconfig: origConfig, maxTimeMS: ReplSetTest.kDefaultTimeoutMS});   jsTestLog( "Do some document writes to verify we have 2 primaries and both satisfy write concern majority"); assert.commandWorked(primary1.getDB(dbName)[collName].insert({_id: 3, x: "primary1 Doc"}, {"writeConcern": {"w": "majority"}})); assert.commandWorked(primary2.getDB(dbName)[collName].insert({_id: 6, x: "primary2 Doc"}, {"writeConcern": {"w": "majority"}}));   jsTestLog("Verify our primary1 can be get re-elected."); assert.commandWorked(primary1.adminCommand({"replSetStepDown": 1000, "force": true})); assert.commandWorked(primary1.adminCommand({replSetFreeze: 0})); assert.commandWorked(primary1.adminCommand({"replSetStepUp": 1}));   jsTestLog("Test completed"); rst.stopSet(); }());

      Description

      This is a just a side-effect of allowing a replica set member to be replaced by a new node (having different host address) with the member id same as replaced node's member id.

      Code snippet from validateOldAndNewConfigsCompatible() (that is called during reconfig procedure)

          // For every member config mNew in newConfig, if there exists member config mOld
          // in oldConfig such that mNew.getHostAndPort() == mOld.getHostAndPort(), it is required
          // that mNew.getId() == mOld.getId().
      

      Basically when member ids are equal, it is not required that their host name matches.

        Attachments

          Issue Links

            Activity

              People

              Assignee:
              backlog-server-repl Backlog - Replication Team
              Reporter:
              suganthi.mani Suganthi Mani
              Participants:
              Votes:
              0 Vote for this issue
              Watchers:
              9 Start watching this issue

                Dates

                Created:
                Updated:
                Resolved: