[jira] [Created] (ZOOKEEPER-3072) Race condition in throttling

["Botond Hejj (JIRA)" <ji...@apache.org>]

Botond Hejj created ZOOKEEPER-3072:
--------------------------------------

             Summary: Race condition in throttling
                 Key: ZOOKEEPER-3072
                 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3072
             Project: ZooKeeper
          Issue Type: Bug
          Components: server
    Affects Versions: 3.5.4, 3.5.3, 3.5.2, 3.5.1, 3.5.0
            Reporter: Botond Hejj


There is a race condition in the server throttling code. It is possible that the disableRecv is called after enableRecv.

Basically, the I/O work thread does this in processPacket: [https://github.com/apache/zookeeper/blob/release-3.5.3/src/java/main/org/apache/zookeeper/server/ZooKeeperServer.java#L1102] 

                submitRequest(si);

            }

        }

        cnxn.incrOutstandingRequests(h);

    }

 

incrOutstandingRequests() checks for limit breach, and potentially turns on throttling, [https://github.com/apache/zookeeper/blob/release-3.5.3/src/java/main/org/apache/zookeeper/server/NIOServerCnxn.java#L384]

 

submitRequest() will create a logical request and en-queue it so that Processor thread can pick it up. After being de-queued by Processor thread, it does necessary handling, and then calls this [https://github.com/apache/zookeeper/blob/release-3.5.3/src/java/main/org/apache/zookeeper/server/FinalRequestProcessor.java#L459] :

 

            cnxn.sendResponse(hdr, rsp, "response");

 

and in sendResponse(), it first appends to outgoing buffer, and then checks if un-throttle is needed:  [https://github.com/apache/zookeeper/blob/release-3.5.3/src/java/main/org/apache/zookeeper/server/NIOServerCnxn.java#L708]

 

However, if there is a context switch between submitRequest() and cnxn.incrOutstandingRequests(), so that Processor thread completes cnxn.sendResponse() call before I/O thread switches back, then enableRecv() will happen before disableRecv(), and enableRecv() will fail the CAS ops, while disableRecv() will succeed, resulting in a deadlock: un-throttle is needed for letting in requests, and sendResponse is needed to trigger un-throttle, but sendResponse() requires an incoming message. From that point on, ZK server will no longer select the affected client socket for read, leading to the observed client-side failure in the subject.

If you would like to reproduce this than setting the globalOutstandingLimit down to 1 makes this reproducible easier as throttling starts with less requests. 

 



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)