[ 
https://issues.apache.org/jira/browse/SOLR-11278?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16147149#comment-16147149
 ] 

Amrit Sarkar edited comment on SOLR-11278 at 8/30/17 12:31 PM:
---------------------------------------------------------------

Still rambling:

{code}
  /**
   * This test start cdcr source, adds data,starts target cluster, verifies 
replication,
   * stops cdcr replication and buffering, adds more data, re-enables cdcr and 
verify replication
   */
  public void testBootstrapWithSourceCluster() throws Exception {
    // start the target first so that we know its zkhost
    MiniSolrCloudCluster target = new MiniSolrCloudCluster(1, 
createTempDir("cdcr-target"), buildJettyConfig("/solr"));
    try {
      target.waitForAllNodes(30);
      System.out.println("Target zkHost = " + 
target.getZkServer().getZkAddress());
      System.setProperty("cdcr.target.zkHost", 
target.getZkServer().getZkAddress());

      MiniSolrCloudCluster source = new MiniSolrCloudCluster(1, 
createTempDir("cdcr-source"), buildJettyConfig("/solr"));
      try {
        source.waitForAllNodes(30);
        source.uploadConfigSet(configset("cdcr-source"), "cdcr-source");

        CollectionAdminRequest.createCollection("cdcr-source", "cdcr-source", 
1, 1)
            .withProperty("solr.directoryFactory", 
"solr.StandardDirectoryFactory")
            .process(source.getSolrClient());

        CloudSolrClient sourceSolrClient = source.getSolrClient();
        sourceSolrClient.setDefaultCollection("cdcr-source");
        int docs = (TEST_NIGHTLY ? 100 : 10);
        int numDocs = 0;
        for (int k = 0; k < docs; k++) {
          UpdateRequest req = new UpdateRequest();
          for (; numDocs < (k + 1) * 100; numDocs++) {
            SolrInputDocument doc = new SolrInputDocument();
            doc.addField("id", "source_" + numDocs);
            doc.addField("xyz", numDocs);
            req.add(doc);
          }
          req.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
          System.out.println("Adding " + docs + " docs with commit=true, 
numDocs=" + numDocs);
          req.process(sourceSolrClient);
        }

        QueryResponse response = sourceSolrClient.query(new SolrQuery("*:*"));
        assertEquals("", numDocs, response.getResults().getNumFound());

        // setup the target cluster
        target.uploadConfigSet(configset("cdcr-target"), "cdcr-target");
        CollectionAdminRequest.createCollection("cdcr-target", "cdcr-target", 
1, 1)
            .process(target.getSolrClient());
        CloudSolrClient targetSolrClient = target.getSolrClient();
        targetSolrClient.setDefaultCollection("cdcr-target");

        cdcrStart(targetSolrClient);
        cdcrStart(sourceSolrClient);

        System.out.println("bs status TX :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SX :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        response = getCdcrQueue(sourceSolrClient);
        System.out.println("Cdcr queue response: " + response.getResponse());
        long foundDocs = waitForTargetToSync(numDocs, targetSolrClient);

        System.out.println("bs status TY :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SY :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        assertEquals("Document mismatch on target after sync", numDocs, 
foundDocs);

        System.out.println("bs status TZ :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SZ :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        cdcrStop(sourceSolrClient);
        cdcrDisableBuffer(sourceSolrClient);

        System.out.println("bs status TA :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SA :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        int c = 0;
        for (int k = 0; k < 10; k++) {
          UpdateRequest req = new UpdateRequest();
          for (; c < (k + 1) * 100; c++, numDocs++) {
            SolrInputDocument doc = new SolrInputDocument();
            doc.addField("id", "source_" + numDocs);
            doc.addField("xyz", numDocs);
            req.add(doc);
          }
          req.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
          System.out.println("Adding 100 docs with commit=true, numDocs=" + 
numDocs);
          req.process(sourceSolrClient);
        }

        response = sourceSolrClient.query(new SolrQuery("*:*"));
        assertEquals("", numDocs, response.getResults().getNumFound());

        cdcrStart(sourceSolrClient);
        cdcrEnableBuffer(sourceSolrClient);

        System.out.println("bs status T1 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S1 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        foundDocs = waitForTargetToSync(numDocs, targetSolrClient);

        System.out.println("bs status T2 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S2 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        assertEquals("Document mismatch on target after sync", numDocs, 
foundDocs);

        System.out.println("bs status T3 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S3 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
      } finally {
        source.shutdown();
      }
    } finally {
      target.shutdown();
    }
  }
{code}

responses for BS ::

T - target, S - source
{code}
   [junit4]   1> bs status TX :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status SX :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TY :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SY :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TZ :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SZ :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TA :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SA :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status T1 :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status S1 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status T2 :: 
{responseHeader={status=0,QTime=0},STATUS=cancelled}
   [junit4]   1> bs status S2 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
{code}

{{bs status T3}} was never written as assertion was failed. *But why is 
bootstrap cancelled after waiting for the target for 120 sec?* 

{code}
[junit4]   1> bs status T2 :: 
{responseHeader={status=0,QTime=0},STATUS=cancelled}
   [junit4]   2> 167151 INFO  (qtp666966491-24) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167153 INFO  (qtp666966491-24) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167153 INFO  (qtp1588339772-65) [n:127.0.0.1:62339_solr 
c:cdcr-source s:shard1 r:core_node1 x:cdcr-source_shard1_replica1] 
o.a.s.c.S.Request [cdcr-source_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&_stateVer_=cdcr-source:4&action=bootstrap_status&wt=javabin&version=2}
 status=0 QTime=0
   [junit4]   1> bs status S2 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   2> 167155 INFO  (qtp666966491-23) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167161 INFO  (qtp666966491-30) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167163 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167166 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167168 INFO  (jetty-closer-14-thread-1) [    ] 
o.e.j.s.AbstractConnector Stopped 
ServerConnector@4b790cef{HTTP/1.1,[http/1.1]}{127.0.0.1:0}
   [junit4]   2> 167168 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167169 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.c.CoreContainer Shutting down CoreContainer instance=820972786
   [junit4]   2> 167169 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.node
   [junit4]   2> 167170 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.jvm
   [junit4]   2> 167170 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.jetty
[junit4]   2> 167173 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167175 INFO  (qtp666966491-23) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167176 INFO  (coreCloseExecutor-44-thread-1) 
[n:127.0.0.1:62339_solr c:cdcr-source s:shard1 r:core_node1 
x:cdcr-source_shard1_replica1] o.a.s.c.SolrCore [cdcr-source_shard1_replica1]  
CLOSING SolrCore org.apache.solr.core.SolrCore@500834bb
   [junit4]   2> 167176 INFO  (coreCloseExecutor-44-thread-1) 
[n:127.0.0.1:62339_solr c:cdcr-source s:shard1 r:core_node1 
x:cdcr-source_shard1_replica1] o.a.s.h.CdcrRequestHandler Solr core is being 
closed - shutting down CDCR handler @ cdcr-source:shard1
{code}

Source solr cluster shut down before bootstrap gets completed and issues 
CANCEL_BOOSTRAP. The assertions fail way before that. The question being why 
1000 docs are not getting bootstrapped?

If you look above, the CDCR Bootstrap status from the beginning is "running" 
and even if the first batch is successfully fetched to target and we shut down 
CDCR on source. , the status is still being "running". 

I am running more tests, will update shortly. This is the crux of the problem, 
no solution on the way still.


was (Author: sarkaramr...@gmail.com):
Still rambling:

{code}
  /**
   * This test start cdcr source, adds data,starts target cluster, verifies 
replication,
   * stops cdcr replication and buffering, adds more data, re-enables cdcr and 
verify replication
   */
  public void testBootstrapWithSourceCluster() throws Exception {
    // start the target first so that we know its zkhost
    MiniSolrCloudCluster target = new MiniSolrCloudCluster(1, 
createTempDir("cdcr-target"), buildJettyConfig("/solr"));
    try {
      target.waitForAllNodes(30);
      System.out.println("Target zkHost = " + 
target.getZkServer().getZkAddress());
      System.setProperty("cdcr.target.zkHost", 
target.getZkServer().getZkAddress());

      MiniSolrCloudCluster source = new MiniSolrCloudCluster(1, 
createTempDir("cdcr-source"), buildJettyConfig("/solr"));
      try {
        source.waitForAllNodes(30);
        source.uploadConfigSet(configset("cdcr-source"), "cdcr-source");

        CollectionAdminRequest.createCollection("cdcr-source", "cdcr-source", 
1, 1)
            .withProperty("solr.directoryFactory", 
"solr.StandardDirectoryFactory")
            .process(source.getSolrClient());

        CloudSolrClient sourceSolrClient = source.getSolrClient();
        sourceSolrClient.setDefaultCollection("cdcr-source");
        int docs = (TEST_NIGHTLY ? 100 : 10);
        int numDocs = 0;
        for (int k = 0; k < docs; k++) {
          UpdateRequest req = new UpdateRequest();
          for (; numDocs < (k + 1) * 100; numDocs++) {
            SolrInputDocument doc = new SolrInputDocument();
            doc.addField("id", "source_" + numDocs);
            doc.addField("xyz", numDocs);
            req.add(doc);
          }
          req.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
          System.out.println("Adding " + docs + " docs with commit=true, 
numDocs=" + numDocs);
          req.process(sourceSolrClient);
        }

        QueryResponse response = sourceSolrClient.query(new SolrQuery("*:*"));
        assertEquals("", numDocs, response.getResults().getNumFound());

        // setup the target cluster
        target.uploadConfigSet(configset("cdcr-target"), "cdcr-target");
        CollectionAdminRequest.createCollection("cdcr-target", "cdcr-target", 
1, 1)
            .process(target.getSolrClient());
        CloudSolrClient targetSolrClient = target.getSolrClient();
        targetSolrClient.setDefaultCollection("cdcr-target");

        cdcrStart(targetSolrClient);
        cdcrStart(sourceSolrClient);

        System.out.println("bs status TX :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SX :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        response = getCdcrQueue(sourceSolrClient);
        System.out.println("Cdcr queue response: " + response.getResponse());
        long foundDocs = waitForTargetToSync(numDocs, targetSolrClient);

        System.out.println("bs status TY :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SY :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        assertEquals("Document mismatch on target after sync", numDocs, 
foundDocs);

        System.out.println("bs status TZ :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SZ :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        cdcrStop(sourceSolrClient);
        cdcrDisableBuffer(sourceSolrClient);

        System.out.println("bs status TA :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status SA :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        int c = 0;
        for (int k = 0; k < 10; k++) {
          UpdateRequest req = new UpdateRequest();
          for (; c < (k + 1) * 100; c++, numDocs++) {
            SolrInputDocument doc = new SolrInputDocument();
            doc.addField("id", "source_" + numDocs);
            doc.addField("xyz", numDocs);
            req.add(doc);
          }
          req.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
          System.out.println("Adding 100 docs with commit=true, numDocs=" + 
numDocs);
          req.process(sourceSolrClient);
        }

        response = sourceSolrClient.query(new SolrQuery("*:*"));
        assertEquals("", numDocs, response.getResults().getNumFound());

        cdcrStart(sourceSolrClient);
        cdcrEnableBuffer(sourceSolrClient);

        System.out.println("bs status T1 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S1 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        foundDocs = waitForTargetToSync(numDocs, targetSolrClient);

        System.out.println("bs status T2 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S2 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));

        assertEquals("Document mismatch on target after sync", numDocs, 
foundDocs);

        System.out.println("bs status T3 :: " + 
invokeCdcrAction(targetSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
        System.out.println("bs status S3 :: " + 
invokeCdcrAction(sourceSolrClient, CdcrParams.CdcrAction.BOOTSTRAP_STATUS));
      } finally {
        source.shutdown();
      }
    } finally {
      target.shutdown();
    }
  }
{code}

responses for BS ::

T - target, S - source
{code}
   [junit4]   1> bs status TX :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status SX :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TY :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SY :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TZ :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SZ :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status TA :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status SA :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status T1 :: 
{responseHeader={status=0,QTime=0},STATUS=running}
   [junit4]   1> bs status S1 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   1> bs status T2 :: 
{responseHeader={status=0,QTime=0},STATUS=cancelled}
   [junit4]   1> bs status S2 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
{code}

{{bs status T3}} was never written as assertion was failed. *But why is 
bootstrap get cancelled after waiting for the target for 120 sec?* 

{code}
[junit4]   1> bs status T2 :: 
{responseHeader={status=0,QTime=0},STATUS=cancelled}
   [junit4]   2> 167151 INFO  (qtp666966491-24) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167153 INFO  (qtp666966491-24) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167153 INFO  (qtp1588339772-65) [n:127.0.0.1:62339_solr 
c:cdcr-source s:shard1 r:core_node1 x:cdcr-source_shard1_replica1] 
o.a.s.c.S.Request [cdcr-source_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&_stateVer_=cdcr-source:4&action=bootstrap_status&wt=javabin&version=2}
 status=0 QTime=0
   [junit4]   1> bs status S2 :: 
{responseHeader={status=0,QTime=0},STATUS=notfound,msg=No bootstrap found in 
running, completed or failed states}
   [junit4]   2> 167155 INFO  (qtp666966491-23) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167161 INFO  (qtp666966491-30) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167163 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167166 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167168 INFO  (jetty-closer-14-thread-1) [    ] 
o.e.j.s.AbstractConnector Stopped 
ServerConnector@4b790cef{HTTP/1.1,[http/1.1]}{127.0.0.1:0}
   [junit4]   2> 167168 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167169 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.c.CoreContainer Shutting down CoreContainer instance=820972786
   [junit4]   2> 167169 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.node
   [junit4]   2> 167170 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.jvm
   [junit4]   2> 167170 INFO  (jetty-closer-14-thread-1) [    ] 
o.a.s.m.SolrMetricManager Closing metric reporters for: solr.jetty
[junit4]   2> 167173 INFO  (qtp666966491-29) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167175 INFO  (qtp666966491-23) [n:127.0.0.1:62331_solr 
c:cdcr-target s:shard1 r:core_node1 x:cdcr-target_shard1_replica1] 
o.a.s.c.S.Request [cdcr-target_shard1_replica1]  webapp=/solr path=/cdcr 
params={qt=/cdcr&action=BOOTSTRAP_STATUS&wt=javabin&version=2} status=0 QTime=0
   [junit4]   2> 167176 INFO  (coreCloseExecutor-44-thread-1) 
[n:127.0.0.1:62339_solr c:cdcr-source s:shard1 r:core_node1 
x:cdcr-source_shard1_replica1] o.a.s.c.SolrCore [cdcr-source_shard1_replica1]  
CLOSING SolrCore org.apache.solr.core.SolrCore@500834bb
   [junit4]   2> 167176 INFO  (coreCloseExecutor-44-thread-1) 
[n:127.0.0.1:62339_solr c:cdcr-source s:shard1 r:core_node1 
x:cdcr-source_shard1_replica1] o.a.s.h.CdcrRequestHandler Solr core is being 
closed - shutting down CDCR handler @ cdcr-source:shard1
{code}

Source solr cluster shut down before bootstrap gets completed and issues 
CANCEL_BOOSTRAP. The assertions fail way before that. The question being why 
1000 docs are not getting bootstrapped?

If you look above, the CDCR Bootstrap status from the beginning is "running" 
and even if the first batch is successfully fetched to target and we shut down 
CDCR on source. , the status is still being "running". 

I am running more tests, will update shortly. This is the crux of the problem, 
no solution on the way still.

> CdcrBootstrapTest failing in branch_6_6
> ---------------------------------------
>
>                 Key: SOLR-11278
>                 URL: https://issues.apache.org/jira/browse/SOLR-11278
>             Project: Solr
>          Issue Type: Bug
>      Security Level: Public(Default Security Level. Issues are Public) 
>          Components: CDCR
>            Reporter: Amrit Sarkar
>            Assignee: Varun Thacker
>         Attachments: SOLR-11278.patch, test_results
>
>
> I ran beast for 10 rounds:
> ant beast -Dtestcase=CdcrBootstrapTest -Dtests.multiplier=2 -Dtests.slow=true 
> -Dtests.locale=vi -Dtests.timezone=Asia/Yekaterinburg -Dtests.asserts=true 
> -Dtests.file.encoding=US-ASCII -Dbeast.iters=10
> and seeing following failure:
> {code}
>   [beaster] [01:37:16.282] FAILURE  153s | 
> CdcrBootstrapTest.testBootstrapWithSourceCluster <<<
>   [beaster]    > Throwable #1: java.lang.AssertionError: Document mismatch on 
> target after sync expected:<2000> but was:<1000>
> {code}



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
For additional commands, e-mail: dev-h...@lucene.apache.org

Reply via email to