[ https://issues.apache.org/jira/browse/CASSANDRA-13265?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15901047#comment-15901047 ]
Christian Esken edited comment on CASSANDRA-13265 at 3/8/17 10:36 AM: ---------------------------------------------------------------------- bq. It should include drained messages as well OMG, right. I thought about that, and concluded it is correct to exclude. But obviously the messages are already drained from the queue, so they must be added. bq. We don't do/allow author tags OOPS, always this oversmart IDE :-) bq. This needs to be configurable Oh. Even more work. This is getting bigger than anticipated, but I am happy to do it. Thanks for the hints on how do do the Configuration. I will work on it later this day or tomorrow. was (Author: cesken): bq. It should include drained messages as well OMG, right. I thought about that concluded it is correct to exclude. But obviously the messages are already drained from the queue, so they must be added. bq. We don't do/allow author tags OOPS, always this oversmart IDE :-) bq. This needs to be configurable Oh. Even more work. This is getting bigger than anticipated, but I am happy to do it. Thanks for the hints on how do do the Configuration. I will work on it later this day or tomorrow. > Expiration in OutboundTcpConnection can block the reader Thread > --------------------------------------------------------------- > > Key: CASSANDRA-13265 > URL: https://issues.apache.org/jira/browse/CASSANDRA-13265 > Project: Cassandra > Issue Type: Bug > Environment: Cassandra 3.0.9 > Java HotSpot(TM) 64-Bit Server VM version 25.112-b15 (Java version > 1.8.0_112-b15) > Linux 3.16 > Reporter: Christian Esken > Assignee: Christian Esken > Attachments: cassandra.pb-cache4-dus.2017-02-17-19-36-26.chist.xz, > cassandra.pb-cache4-dus.2017-02-17-19-36-26.td.xz > > > I observed that sometimes a single node in a Cassandra cluster fails to > communicate to the other nodes. This can happen at any time, during peak load > or low load. Restarting that single node from the cluster fixes the issue. > Before going in to details, I want to state that I have analyzed the > situation and am already developing a possible fix. Here is the analysis so > far: > - A Threaddump in this situation showed 324 Threads in the > OutboundTcpConnection class that want to lock the backlog queue for doing > expiration. > - A class histogram shows 262508 instances of > OutboundTcpConnection$QueuedMessage. > What is the effect of it? As soon as the Cassandra node has reached a certain > amount of queued messages, it starts thrashing itself to death. Each of the > Thread fully locks the Queue for reading and writing by calling > iterator.next(), making the situation worse and worse. > - Writing: Only after 262508 locking operation it can progress with actually > writing to the Queue. > - Reading: Is also blocked, as 324 Threads try to do iterator.next(), and > fully lock the Queue > This means: Writing blocks the Queue for reading, and readers might even be > starved which makes the situation even worse. > ----- > The setup is: > - 3-node cluster > - replication factor 2 > - Consistency LOCAL_ONE > - No remote DC's > - high write throughput (100000 INSERT statements per second and more during > peak times). > -- This message was sent by Atlassian JIRA (v6.3.15#6346)