[jira] [Resolved] (IMPALA-2550) Switch to per-query exec rpc

["Marcel Kornacker (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/IMPALA-2550?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Marcel Kornacker resolved IMPALA-2550.
--------------------------------------
       Resolution: Fixed
    Fix Version/s: Impala 2.9.0

commit 368115cdae98344e5c826f099582a60aa536951d
Author: Marcel Kornacker <ma...@cloudera.com>
Date:   Mon Oct 31 14:42:51 2016 -0700

    IMPALA-2550: Switch to per-query exec rpc
    
    Coordinator:
    - FragmentInstanceState -> BackendState, which in turn records
      FragmentInstanceStats
    
    QueryState
    - does query-wide setup in a separate thread (which also launches
      the instance exec threads)
    - has a query-wide 'prepared' state at which point all static setup
      is done and all FragmentInstanceStates are accessible
    
    Also renamed QueryExecState to ClientRequestState.
    
    Simplified handling of execution status (in FragmentInstanceState):
    - status only transmitted via ReportExecStatus rpc
    - in particular, it's not returned anymore from the Cancel rpc
    
    FIS: Fixed bugs related to partially-prepared state (in Close() and ReleaseThreadToken())
    
    Change-Id: I20769e420711737b6b385c744cef4851cee3facd
    Reviewed-on: http://gerrit.cloudera.org:8080/6535
    Reviewed-by: Marcel Kornacker <ma...@cloudera.com>
    Tested-by: Impala Public Jenkins


> Switch to per-query exec rpc
> ----------------------------
>
>                 Key: IMPALA-2550
>                 URL: https://issues.apache.org/jira/browse/IMPALA-2550
>             Project: IMPALA
>          Issue Type: Sub-task
>          Components: Distributed Exec
>    Affects Versions: Impala 2.3.0
>            Reporter: Henry Robinson
>            Assignee: Marcel Kornacker
>              Labels: scalability
>             Fix For: Impala 2.9.0
>
>
> The execution-related rpcs in ImpalaInternalService (ExecPlanFragment, CancelPlanFragment) are currently fragment-instance oriented. This is very inefficient because a) starting up a single query involves lots of rpcs, b) it makes it hard to share query-wide data structures such as the descriptor table.
> Instead, let's move to a per-query focus and replace the existing "execute" and "cancel" rpcs with per-query equivalents.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)