Permalink
Commits on Mar 22, 2010
  1. @afeinberg

    No longer hard-coding HDFS replication factor.

    	HDFS replication factor was set equal to Voldemort
    	replication factor. This doesn't bring benefit (you can't
    	ensure the HDFS fetcher jobs use distinct data nodes), could
    	cause potential issues, can be done done without hard-coding
    	(by setting it as a parameter when running the M/R job).
    Eric Tschetter committed with afeinberg Mar 19, 2010
  2. @afeinberg
Commits on Mar 18, 2010
  1. @afeinberg
  2. @afeinberg
  3. @afeinberg

    Added configurable keep-alive option for socket connections.

        Solves problem where long standing idle tcp connections between
        clients and servers are covertly closed by intermediary firewalls.
    Michael Lambert committed with afeinberg Mar 2, 2010
Commits on Mar 16, 2010
  1. @afeinberg

    Improve AsyncOperationTest.

    afeinberg committed Mar 16, 2010
  2. @afeinberg
  3. @kirktrue

    Clean up of the StoreVerifier to make it more obvious that it's verif…

    …ying based on the remote metadata store. Cleans the code up a bit. Also relaxed serialization on the ClientStoreVerifier so that the actual get call occurs outside of the synchronized block. Alas, it should make no difference as there's only one thread performing verification ;)
    kirktrue committed Mar 16, 2010
  4. @kirktrue

    Issue 228: Improve threshold failure detector logging when node marke…

    …d as unavailable due to exceeding request timeouts
    
    Clean up of the logging to output a message detailing that the timeouts have been exceeded when marking the node as unavailable. Also cleaned up the logging to only output the node ID instead of the node ID *and* all of its partitions (which, in a production system is very verbose).
    kirktrue committed Mar 16, 2010
  5. @kirktrue

    Issue 229: IllegalArgumentException using nio

    Replicating the assertion in position(int newPosition) in our code so as to print a better error message in order to help debug.
    kirktrue committed Mar 16, 2010
  6. @afeinberg
  7. @afeinberg
  8. @Omega1 @afeinberg

    Fixed issue 230: AdminClient#addStore could fail under concurrent load

    Synchronized store addition so concurrent editting/saving of
    configuration data doesn't occur: ConfigurationStorageEngine
    does not support that.
    Omega1 committed with afeinberg Mar 11, 2010
  9. @afeinberg

    Improved AdminTool, RebalanceUtils.

    	* Added a shell script to invoke AdminTool.
    	* AdminTool: no longer require store name.
    	* RebalanceUtils: change RebalanceUtils.propagateCluster
    	  to allow propagation to *some* of nodes in a cluster, vs.
    	  all nodes in a cluster.
    afeinberg committed Mar 15, 2010
  10. @afeinberg
  11. @afeinberg

    Created a command line interface to AdminClient.

    Added support for restore from replication.
    afeinberg committed Feb 26, 2010
  12. @afeinberg

    Merge branch 'benchmark-tool'

    afeinberg committed Mar 16, 2010
  13. @afeinberg

    Switched to System.nanoTime().

    afeinberg committed Mar 16, 2010
  14. @kirktrue
Commits on Mar 15, 2010
  1. @kirktrue @afeinberg

    Simulate caching requests, collect percentiles for request times.

     *  Reissuing requests to stimulate caching on the server. Wrap
        the core KeyProvider in an implementation that pulls out
        previously issued key and reuse an entry from that set
        randomly.
    
     *  Collect request times and store them in an array that is used
    	to collect percentiles. Didn't add it to the "m" case as I'm
    	not sure if that makes any sense.
    kirktrue committed with afeinberg Mar 15, 2010
  2. @kirktrue
  3. @afeinberg
  4. @afeinberg
  5. @afeinberg
  6. @afeinberg

    Added support for sending requests only to a specific node.

        - Created a tool to filter a request file for requests destined *only*
          for a specific node.
        - Added a -node option to RemoteTest to bootstrap only from a
          specified node rather than go to node 0 of the cluster.
    afeinberg committed Feb 24, 2010
  7. @afeinberg
  8. @afeinberg
  9. @afeinberg
  10. @afeinberg

    Simple improvements for RemoteTest: verbose mode, ignore nulls, don't…

    … count exceptions as succesful for throughput counts.
    afeinberg committed Feb 23, 2010
  11. @kirktrue

    Implemented the ability for the server-side routing based StoreVerifi…

    …er to create metadata store based nodes on the fly. Also added a new unit test to ensure this.
    kirktrue committed Mar 15, 2010
  12. @afeinberg
  13. @afeinberg
Commits on Mar 13, 2010
  1. @afeinberg

    Cleaned up the asynchronous operation service.

    	Renamed AsyncOperationRunner to AsyncOperationService.
    
    	Cleaned up AsyncOperationRepository.
    
    	Renamed AsyncOperationRepository to AsyncOperationCache.
    afeinberg committed Mar 13, 2010
  2. @afeinberg
Commits on Mar 9, 2010
  1. @afeinberg