[ 
https://issues.apache.org/jira/browse/SOLR-5935?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13955979#comment-13955979
 ] 

Otis Gospodnetic commented on SOLR-5935:
----------------------------------------

bq. Have you tried raising the total number of max connections?

I think the answer is yes, but Rafal can confirm tomorrow.

bq. Also, are you using the batch or streaming apis or one update per request?

Not sure about batch vs. streaming, but I think there were 10 docs per request.


> SolrCloud hangs under certain conditions
> ----------------------------------------
>
>                 Key: SOLR-5935
>                 URL: https://issues.apache.org/jira/browse/SOLR-5935
>             Project: Solr
>          Issue Type: Bug
>    Affects Versions: 4.6.1
>            Reporter: Rafał Kuć
>            Priority: Critical
>         Attachments: thread dumps.zip
>
>
> As discussed in a mailing list - let's try to find the reason while under 
> certain conditions SolrCloud can hang.
> I have an issue with one of the SolrCloud deployments. Six machines, a 
> collection with 6 shards with a replication factor of 3. It all runs on 6 
> physical servers, each with 24 cores. We've indexed about 32 million 
> documents and everything was fine until that point.
> Now, during performance tests, we run into an issue - SolrCloud hangs
> when querying and indexing is run at the same time. First we see a
> normal load on the machines, than the load starts to drop and thread
> dump shown numerous threads like this:
> {noformat}
> Thread 12624: (state = BLOCKED)
>  - sun.misc.Unsafe.park(boolean, long) @bci=0 (Compiled frame; information 
> may be imprecise)
>  - java.util.concurrent.locks.LockSupport.park(java.lang.Object) @bci=14, 
> line=186 (Compiled frame)
>  - 
> java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await() 
> @bci=42, line=2043 (Compiled frame)
>  - org.apache.http.pool.PoolEntryFuture.await(java.util.Date) @bci=50, 
> line=131 (Compiled frame)
>  - 
> org.apache.http.pool.AbstractConnPool.getPoolEntryBlocking(java.lang.Object, 
> java.lang.Object, long, java.util.concurrent.TimeUnit, 
> org.apache.http.pool.PoolEntryFuture) @bci=431, line=281 (Compiled frame)
>  - 
> org.apache.http.pool.AbstractConnPool.access$000(org.apache.http.pool.AbstractConnPool,
>  java.lang.Object, java.lang.Object, long, java.util.concurrent.TimeUnit, 
> org.apache.http.pool.PoolEntryFuture) @bci=8, line=62 (Compiled frame)
>  - org.apache.http.pool.AbstractConnPool$2.getPoolEntry(long, 
> java.util.concurrent.TimeUnit) @bci=15, line=176 (Compiled frame)
>  - org.apache.http.pool.AbstractConnPool$2.getPoolEntry(long, 
> java.util.concurrent.TimeUnit) @bci=3, line=169 (Compiled frame)
>  - org.apache.http.pool.PoolEntryFuture.get(long, 
> java.util.concurrent.TimeUnit) @bci=38, line=100 (Compiled frame)
>  - 
> org.apache.http.impl.conn.PoolingClientConnectionManager.leaseConnection(java.util.concurrent.Future,
>  long, java.util.concurrent.TimeUnit) @bci=4, line=212 (Compiled frame)
>  - 
> org.apache.http.impl.conn.PoolingClientConnectionManager$1.getConnection(long,
>  java.util.concurrent.TimeUnit) @bci=10, line=199 (Compiled frame)
>  - 
> org.apache.http.impl.client.DefaultRequestDirector.execute(org.apache.http.HttpHost,
>  org.apache.http.HttpRequest, org.apache.http.protocol.HttpContext) @bci=259, 
> line=456 (Compiled frame)
>  - 
> org.apache.http.impl.client.AbstractHttpClient.execute(org.apache.http.HttpHost,
>  org.apache.http.HttpRequest, org.apache.http.protocol.HttpContext) @bci=344, 
> line=906 (Compiled frame)
>  - 
> org.apache.http.impl.client.AbstractHttpClient.execute(org.apache.http.client.methods.HttpUriRequest,
>  org.apache.http.protocol.HttpContext) @bci=21, line=805 (Compiled frame)
>  - 
> org.apache.http.impl.client.AbstractHttpClient.execute(org.apache.http.client.methods.HttpUriRequest)
>  @bci=6, line=784 (Compiled frame)
>  - 
> org.apache.solr.client.solrj.impl.HttpSolrServer.request(org.apache.solr.client.solrj.SolrRequest,
>  org.apache.solr.client.solrj.ResponseParser) @bci=1175, line=395 
> (Interpreted frame)
>  - 
> org.apache.solr.client.solrj.impl.HttpSolrServer.request(org.apache.solr.client.solrj.SolrRequest)
>  @bci=17, line=199 (Compiled frame)
>  - 
> org.apache.solr.client.solrj.impl.LBHttpSolrServer.request(org.apache.solr.client.solrj.impl.LBHttpSolrServer$Req)
>  @bci=132, line=285 (Interpreted frame)
>  - 
> org.apache.solr.handler.component.HttpShardHandlerFactory.makeLoadBalancedRequest(org.apache.solr.client.solrj.request.QueryRequest,
>  java.util.List) @bci=13, line=214 (Compiled frame)
>  - org.apache.solr.handler.component.HttpShardHandler$1.call() @bci=246, 
> line=161 (Compiled frame)
>  - org.apache.solr.handler.component.HttpShardHandler$1.call() @bci=1, 
> line=118 (Interpreted frame)
>  - java.util.concurrent.FutureTask$Sync.innerRun() @bci=29, line=334 
> (Interpreted frame)
>  - java.util.concurrent.FutureTask.run() @bci=4, line=166 (Compiled frame)
>  - java.util.concurrent.Executors$RunnableAdapter.call() @bci=4, line=471 
> (Interpreted frame)
>  - java.util.concurrent.FutureTask$Sync.innerRun() @bci=29, line=334 
> (Interpreted frame)
>  - java.util.concurrent.FutureTask.run() @bci=4, line=166 (Compiled frame)
>  - 
> java.util.concurrent.ThreadPoolExecutor.runWorker(java.util.concurrent.ThreadPoolExecutor$Worker)
>  @bci=95, line=1145 (Compiled frame)
>  - java.util.concurrent.ThreadPoolExecutor$Worker.run() @bci=5, line=615 
> (Interpreted frame)
>  - java.lang.Thread.run() @bci=11, line=724 (Interpreted frame)
> {noformat}
> I've checked I/O statistics, GC working, memory usage, networking and
> all of that - those resources are not exhausted during the test.
> Hard autocommit is set to 15 seconds with openSearcher=false and
> softAutocommit to 4 hours. We have a fairly high query rate, but until
> we start indexing everything runs smooth.
> I've attached four thread dumps, stack_1 to stack_4. They were gathered 
> incrementally - stack_1 and stack_2 are when Solr was still able to respond, 
> stack_3 is Solr barely alive and stack_4 is Solr not responding at all.
> If more information is needed I can provide those.



--
This message was sent by Atlassian JIRA
(v6.2#6252)

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

Reply via email to