Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CCR] Retry when no index shard stats can be found #34852

Merged
merged 6 commits into from
Oct 26, 2018
Merged

[CCR] Retry when no index shard stats can be found #34852

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
31bc047
[CCR] Retry when no index shard stats can be found
martijnvg Oct 25, 2018
190106f
added a comment
martijnvg Oct 25, 2018
4b2fb62
instead of just throwing IndexNotFoundException, throw a ShardNotFoun…
martijnvg Oct 25, 2018
b946e30
removed comment
martijnvg Oct 25, 2018
9fa3414
Merge remote-tracking branch 'es/master' into ccr_retry_when_no_index…
martijnvg Oct 25, 2018
66a0907
Merge remote-tracking branch 'es/master' into ccr_retry_when_no_index…
martijnvg Oct 26, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ...plugin/ccr/src/main/java/org/elasticsearch/xpack/ccr/action/ShardFollowTasksExecutor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,7 +185,7 @@ protected void nodeOperation(final AllocatedPersistentTask task, final ShardFoll
return;
}

if (ShardFollowNodeTask.shouldRetry(e)) {
if (ShardFollowNodeTask.shouldRetry(e) || e instanceof IndexNotFoundException) {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, actually, one comment; can you leave a comment here about this, since it's slightly different retry logic from elsewhere.

logger.debug(new ParameterizedMessage("failed to fetch follow shard global {} checkpoint and max sequence number",
shardFollowNodeTask), e);
threadPool.schedule(params.getMaxRetryDelay(), Ccr.CCR_THREAD_POOL_NAME, () -> nodeOperation(task, params, state));
Expand Down
94 changes: 94 additions & 0 deletions x-pack/plugin/ccr/src/test/java/org/elasticsearch/xpack/CcrIntegTestCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,9 @@

import org.elasticsearch.action.admin.cluster.health.ClusterHealthRequest;
import org.elasticsearch.action.admin.cluster.health.ClusterHealthResponse;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksAction;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksRequest;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksResponse;
import org.elasticsearch.action.admin.cluster.settings.ClusterUpdateSettingsRequest;
import org.elasticsearch.action.admin.indices.get.GetIndexResponse;
import org.elasticsearch.action.admin.indices.refresh.RefreshResponse;
Expand All @@ -24,9 +27,11 @@
import org.elasticsearch.common.Priority;
import org.elasticsearch.common.Strings;
import org.elasticsearch.common.UUIDs;
import org.elasticsearch.common.bytes.BytesReference;
import org.elasticsearch.common.network.NetworkModule;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.common.xcontent.XContentBuilder;
import org.elasticsearch.core.internal.io.IOUtils;
import org.elasticsearch.env.NodeEnvironment;
import org.elasticsearch.index.Index;
Expand All @@ -35,6 +40,7 @@
import org.elasticsearch.persistent.PersistentTasksCustomMetaData;
import org.elasticsearch.plugins.Plugin;
import org.elasticsearch.script.ScriptService;
import org.elasticsearch.tasks.TaskInfo;
import org.elasticsearch.test.ESIntegTestCase;
import org.elasticsearch.test.ESTestCase;
import org.elasticsearch.test.InternalTestCluster;
Expand All @@ -48,6 +54,9 @@
import org.elasticsearch.xpack.core.ccr.AutoFollowMetadata;
import org.elasticsearch.xpack.core.ccr.ShardFollowNodeTaskStatus;
import org.elasticsearch.xpack.core.ccr.action.FollowStatsAction;
import org.elasticsearch.xpack.core.ccr.action.PauseFollowAction;
import org.elasticsearch.xpack.core.ccr.action.PutFollowAction;
import org.elasticsearch.xpack.core.ccr.action.ResumeFollowAction;
import org.junit.After;
import org.junit.AfterClass;
import org.junit.Before;
Expand All @@ -59,14 +68,17 @@
import java.util.Collection;
import java.util.Collections;
import java.util.Locale;
import java.util.Map;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.TimeUnit;
import java.util.function.Function;

import static org.elasticsearch.common.xcontent.XContentFactory.jsonBuilder;
import static org.elasticsearch.discovery.DiscoveryModule.DISCOVERY_HOSTS_PROVIDER_SETTING;
import static org.elasticsearch.discovery.zen.SettingsBasedHostsProvider.DISCOVERY_ZEN_PING_UNICAST_HOSTS_SETTING;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertNoFailures;
import static org.hamcrest.Matchers.empty;
import static org.hamcrest.Matchers.equalTo;
import static org.hamcrest.Matchers.lessThanOrEqualTo;

Expand Down Expand Up @@ -279,6 +291,88 @@ protected void ensureEmptyWriteBuffers() throws Exception {
});
}

protected void pauseFollow(String... indices) throws Exception {
for (String index : indices) {
final PauseFollowAction.Request unfollowRequest = new PauseFollowAction.Request(index);
followerClient().execute(PauseFollowAction.INSTANCE, unfollowRequest).get();
}
ensureNoCcrTasks();
}

protected void ensureNoCcrTasks() throws Exception {
assertBusy(() -> {
final ClusterState clusterState = followerClient().admin().cluster().prepareState().get().getState();
final PersistentTasksCustomMetaData tasks = clusterState.getMetaData().custom(PersistentTasksCustomMetaData.TYPE);
assertThat(tasks.tasks(), empty());

ListTasksRequest listTasksRequest = new ListTasksRequest();
listTasksRequest.setDetailed(true);
ListTasksResponse listTasksResponse = followerClient().admin().cluster().listTasks(listTasksRequest).get();
int numNodeTasks = 0;
for (TaskInfo taskInfo : listTasksResponse.getTasks()) {
if (taskInfo.getAction().startsWith(ListTasksAction.NAME) == false) {
numNodeTasks++;
}
}
assertThat(numNodeTasks, equalTo(0));
}, 30, TimeUnit.SECONDS);
}

protected String getIndexSettings(final int numberOfShards, final int numberOfReplicas,
final Map<String, String> additionalIndexSettings) throws IOException {
final String settings;
try (XContentBuilder builder = jsonBuilder()) {
builder.startObject();
{
builder.startObject("settings");
{
builder.field("index.number_of_shards", numberOfShards);
builder.field("index.number_of_replicas", numberOfReplicas);
for (final Map.Entry<String, String> additionalSetting : additionalIndexSettings.entrySet()) {
builder.field(additionalSetting.getKey(), additionalSetting.getValue());
}
}
builder.endObject();
builder.startObject("mappings");
{
builder.startObject("doc");
{
builder.startObject("properties");
{
builder.startObject("f");
{
builder.field("type", "integer");
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
settings = BytesReference.bytes(builder).utf8ToString();
}
return settings;
}

public static PutFollowAction.Request putFollow(String leaderIndex, String followerIndex) {
PutFollowAction.Request request = new PutFollowAction.Request();
request.setRemoteCluster("leader_cluster");
request.setLeaderIndex(leaderIndex);
request.setFollowRequest(resumeFollow(followerIndex));
return request;
}

public static ResumeFollowAction.Request resumeFollow(String followerIndex) {
ResumeFollowAction.Request request = new ResumeFollowAction.Request();
request.setFollowerIndex(followerIndex);
request.setMaxRetryDelay(TimeValue.timeValueMillis(10));
request.setReadPollTimeout(TimeValue.timeValueMillis(10));
return request;
}

static void removeCCRRelatedMetadataFromClusterState(ClusterService clusterService) throws Exception {
CountDownLatch latch = new CountDownLatch(1);
clusterService.submitStateUpdateTask("remove-ccr-related-metadata", new ClusterStateUpdateTask() {
Expand Down
82 changes: 0 additions & 82 deletions x-pack/plugin/ccr/src/test/java/org/elasticsearch/xpack/ccr/IndexFollowingIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@

import org.apache.lucene.store.AlreadyClosedException;
import org.elasticsearch.ElasticsearchException;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksAction;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksRequest;
import org.elasticsearch.action.admin.cluster.node.tasks.list.ListTasksResponse;
import org.elasticsearch.action.admin.indices.close.CloseIndexRequest;
Expand Down Expand Up @@ -756,33 +755,6 @@ private CheckedRunnable<Exception> assertTask(final int numberOfPrimaryShards, f
};
}

private void pauseFollow(String... indices) throws Exception {
for (String index : indices) {
final PauseFollowAction.Request unfollowRequest = new PauseFollowAction.Request(index);
followerClient().execute(PauseFollowAction.INSTANCE, unfollowRequest).get();
}
ensureNoCcrTasks();
}

private void ensureNoCcrTasks() throws Exception {
assertBusy(() -> {
final ClusterState clusterState = followerClient().admin().cluster().prepareState().get().getState();
final PersistentTasksCustomMetaData tasks = clusterState.getMetaData().custom(PersistentTasksCustomMetaData.TYPE);
assertThat(tasks.tasks(), empty());

ListTasksRequest listTasksRequest = new ListTasksRequest();
listTasksRequest.setDetailed(true);
ListTasksResponse listTasksResponse = followerClient().admin().cluster().listTasks(listTasksRequest).get();
int numNodeTasks = 0;
for (TaskInfo taskInfo : listTasksResponse.getTasks()) {
if (taskInfo.getAction().startsWith(ListTasksAction.NAME) == false) {
numNodeTasks++;
}
}
assertThat(numNodeTasks, equalTo(0));
}, 30, TimeUnit.SECONDS);
}

private CheckedRunnable<Exception> assertExpectedDocumentRunnable(final int value) {
return () -> {
final GetResponse getResponse = followerClient().prepareGet("index2", "doc", Integer.toString(value)).get();
Expand All @@ -792,45 +764,6 @@ private CheckedRunnable<Exception> assertExpectedDocumentRunnable(final int valu
};
}

private String getIndexSettings(final int numberOfShards, final int numberOfReplicas,
final Map<String, String> additionalIndexSettings) throws IOException {
final String settings;
try (XContentBuilder builder = jsonBuilder()) {
builder.startObject();
{
builder.startObject("settings");
{
builder.field("index.number_of_shards", numberOfShards);
builder.field("index.number_of_replicas", numberOfReplicas);
for (final Map.Entry<String, String> additionalSetting : additionalIndexSettings.entrySet()) {
builder.field(additionalSetting.getKey(), additionalSetting.getValue());
}
}
builder.endObject();
builder.startObject("mappings");
{
builder.startObject("doc");
{
builder.startObject("properties");
{
builder.startObject("f");
{
builder.field("type", "integer");
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
}
builder.endObject();
settings = BytesReference.bytes(builder).utf8ToString();
}
return settings;
}

private String getIndexSettingsWithNestedMapping(final int numberOfShards, final int numberOfReplicas,
final Map<String, String> additionalIndexSettings) throws IOException {
final String settings;
Expand Down Expand Up @@ -968,19 +901,4 @@ private void assertTotalNumberOfOptimizedIndexing(Index followerIndex, int numbe
});
}

public static PutFollowAction.Request putFollow(String leaderIndex, String followerIndex) {
PutFollowAction.Request request = new PutFollowAction.Request();
request.setRemoteCluster("leader_cluster");
request.setLeaderIndex(leaderIndex);
request.setFollowRequest(resumeFollow(followerIndex));
return request;
}

public static ResumeFollowAction.Request resumeFollow(String followerIndex) {
ResumeFollowAction.Request request = new ResumeFollowAction.Request();
request.setFollowerIndex(followerIndex);
request.setMaxRetryDelay(TimeValue.timeValueMillis(10));
request.setReadPollTimeout(TimeValue.timeValueMillis(10));
return request;
}
}
62 changes: 62 additions & 0 deletions x-pack/plugin/ccr/src/test/java/org/elasticsearch/xpack/ccr/RestartIndexFollowingIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
/*
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
* or more contributor license agreements. Licensed under the Elastic License;
* you may not use this file except in compliance with the Elastic License.
*/

package org.elasticsearch.xpack.ccr;

import org.elasticsearch.common.xcontent.XContentType;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.xpack.CcrIntegTestCase;
import org.elasticsearch.xpack.core.ccr.action.PutFollowAction;

import java.util.Locale;

import static java.util.Collections.singletonMap;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
import static org.hamcrest.Matchers.equalTo;

public class RestartIndexFollowingIT extends CcrIntegTestCase {

@Override
protected int numberOfNodesPerCluster() {
return 1;
}

public void testFollowIndex() throws Exception {
final String leaderIndexSettings = getIndexSettings(1, 0,
singletonMap(IndexSettings.INDEX_SOFT_DELETES_SETTING.getKey(), "true"));
singletonMap(IndexSettings.INDEX_SOFT_DELETES_SETTING.getKey(), "true");
assertAcked(leaderClient().admin().indices().prepareCreate("index1").setSource(leaderIndexSettings, XContentType.JSON));
ensureLeaderGreen("index1");

final PutFollowAction.Request followRequest = putFollow("index1", "index2");
followerClient().execute(PutFollowAction.INSTANCE, followRequest).get();

final long firstBatchNumDocs = randomIntBetween(2, 64);
logger.info("Indexing [{}] docs as first batch", firstBatchNumDocs);
for (int i = 0; i < firstBatchNumDocs; i++) {
final String source = String.format(Locale.ROOT, "{\"f\":%d}", i);
leaderClient().prepareIndex("index1", "doc", Integer.toString(i)).setSource(source, XContentType.JSON).get();
}

assertBusy(() -> {
assertThat(followerClient().prepareSearch("index2").get().getHits().totalHits, equalTo(firstBatchNumDocs));
});

getFollowerCluster().fullRestart();
ensureFollowerGreen("index2");

final long secondBatchNumDocs = randomIntBetween(2, 64);
for (int i = 0; i < secondBatchNumDocs; i++) {
leaderClient().prepareIndex("index1", "doc").setSource("{}", XContentType.JSON).get();
}

assertBusy(() -> {
assertThat(followerClient().prepareSearch("index2").get().getHits().totalHits,
equalTo(firstBatchNumDocs + secondBatchNumDocs));
});
}

}