honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Avoid using WindowsFS in ClusterRerouteIT (#52488) 

Issue #52000 looks like a case of cluster state updates being slower than
expected, but it seems that these slowdowns are relatively rare: most
invocations of `testDelayWithALargeAmountOfShards` take well under a minute in
CI, but there are occasional failures that take 6+ minutes instead.  When it
fails like this, cluster state persistence seems generally slow: most are
slower than expected, with some small updates even taking over 2 seconds to
complete.

The failures all have in common that they use `WindowsFS` to emulate Windows'
behaviour of refusing to delete files that are still open, by tracking all
files (really, inodes) and validating that deleted files are really closed
first. There is a suggestion that this is a little slow in the Lucene test
framework [1]. To see if we can attribute the slowdown to that common factor,
this commit suppresses the use of `WindowsFS` for this test suite.

[1] 4a513fa99f/lucene/test-framework/src/java/org/apache/lucene/util/TestRuleTemporaryFilesCleanup.java (L166)
This commit is contained in:
David Turner 2020-02-19 07:51:04 +00:00
parent 3e3d80e1c8
commit baf184c93f
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/src/test/java/org/elasticsearch/cluster/allocation/ClusterRerouteIT.java
View File

@ -22,6 +22,7 @@ package org.elasticsearch.cluster.allocation;
import org.apache.logging.log4j.Level; import org.apache.logging.log4j.Level;
import org.apache.logging.log4j.LogManager; import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger; import org.apache.logging.log4j.Logger;
import org.apache.lucene.util.LuceneTestCase;
import org.elasticsearch.action.admin.cluster.health.ClusterHealthResponse; import org.elasticsearch.action.admin.cluster.health.ClusterHealthResponse;
import org.elasticsearch.action.admin.cluster.reroute.ClusterRerouteResponse; import org.elasticsearch.action.admin.cluster.reroute.ClusterRerouteResponse;
import org.elasticsearch.action.admin.cluster.reroute.TransportClusterRerouteAction; import org.elasticsearch.action.admin.cluster.reroute.TransportClusterRerouteAction;
@ -57,7 +58,6 @@ import org.elasticsearch.test.ESIntegTestCase.ClusterScope;
import org.elasticsearch.test.ESIntegTestCase.Scope; import org.elasticsearch.test.ESIntegTestCase.Scope;
import org.elasticsearch.test.InternalTestCluster; import org.elasticsearch.test.InternalTestCluster;
import org.elasticsearch.test.MockLogAppender; import org.elasticsearch.test.MockLogAppender;
import org.elasticsearch.test.junit.annotations.TestLogging;
import java.nio.file.Path; import java.nio.file.Path;
import java.util.Arrays; import java.util.Arrays;
@ -75,6 +75,8 @@ import static org.hamcrest.Matchers.containsString;
import static org.hamcrest.Matchers.equalTo; import static org.hamcrest.Matchers.equalTo;
import static org.hamcrest.Matchers.hasSize; import static org.hamcrest.Matchers.hasSize;
// testDelayWithALargeAmountOfShards does a lot of cluster state updates, and WindowsFS slows it down too much (#52000)
@LuceneTestCase.SuppressFileSystems(value = "WindowsFS")
@ClusterScope(scope = Scope.TEST, numDataNodes = 0) @ClusterScope(scope = Scope.TEST, numDataNodes = 0)
public class ClusterRerouteIT extends ESIntegTestCase { public class ClusterRerouteIT extends ESIntegTestCase {
private final Logger logger = LogManager.getLogger(ClusterRerouteIT.class); private final Logger logger = LogManager.getLogger(ClusterRerouteIT.class);
@ -188,8 +190,6 @@ public class ClusterRerouteIT extends ESIntegTestCase {
rerouteWithAllocateLocalGateway(commonSettings); rerouteWithAllocateLocalGateway(commonSettings);
} }
@TestLogging(reason = "https://github.com/elastic/elasticsearch/issues/52000",
value = "org.elasticsearch.gateway.PersistedClusterStateService:DEBUG,org.elasticsearch.cluster.service.MasterService:DEBUG")
public void testDelayWithALargeAmountOfShards() throws Exception { public void testDelayWithALargeAmountOfShards() throws Exception {
Settings commonSettings = Settings.builder() Settings commonSettings = Settings.builder()
.put(ThrottlingAllocationDecider.CLUSTER_ROUTING_ALLOCATION_NODE_CONCURRENT_INCOMING_RECOVERIES_SETTING.getKey(), 1) .put(ThrottlingAllocationDecider.CLUSTER_ROUTING_ALLOCATION_NODE_CONCURRENT_INCOMING_RECOVERIES_SETTING.getKey(), 1)