UNIFIED MAPREDUCE FRAMEWORK FOR LARGE-SCALE DATA PROCESSING
    2.
    发明申请
    UNIFIED MAPREDUCE FRAMEWORK FOR LARGE-SCALE DATA PROCESSING 有权
    用于大规模数据处理的统一映射框架

    公开(公告)号:US20150356157A1

    公开(公告)日:2015-12-10

    申请号:US14458811

    申请日:2014-08-13

    CPC classification number: G06F17/30569 G06F9/5066

    Abstract: According to some embodiments, a method for processing input data comprises creating a MapReducer object corresponding to a MapReduce environment; and receiving, by a MapReduce interface, a plurality of input parameters comprising the input data; a mapper function; a reducer function; and the MapReducer object; and using the MapReduce interface to process the input data by one or more processors in the MapReduce environment using the mapper function and the reducer function. According to some embodiments, the method further comprises creating a second MapReducer object, wherein the second MapReducer object corresponds to a second MapReduce environment; receiving, by the MapReduce interface, the second MapReducer object in place of the first MapReducer object; and utilizing the MapReduce interface to process the input data by the one or more processors in the second MapReduce environment using the mapper function and the reducer function.

    Abstract translation: 根据一些实施例,一种用于处理输入数据的方法包括:创建与MapReduce环境相对应的MapReducer对象; 以及通过MapReduce接口接收包括所述输入数据的多个输入参数; 一个映射函数; 减速机功能; 和MapReducer对象; 并使用MapReduce接口通过MapReduce环境中的一个或多个处理器使用映射器函数和reducer函数来处理输入数据。 根据一些实施例,该方法还包括创建第二MapReducer对象,其中第二MapReducer对象对应于第二MapReduce环境; 通过MapReduce接口接收第二个MapReducer对象来代替第一个MapReducer对象; 并利用MapReduce接口在第二MapReduce环境中使用映射器函数和reducer函数来处理输入数据。

    DATASTORE MECHANISM FOR MANAGING OUT-OF-MEMORY DATA
    4.
    发明申请
    DATASTORE MECHANISM FOR MANAGING OUT-OF-MEMORY DATA 审中-公开
    用于管理无记忆数据的数据机制

    公开(公告)号:US20150356138A1

    公开(公告)日:2015-12-10

    申请号:US14458895

    申请日:2014-08-13

    CPC classification number: G06F16/24532 G06F9/5066 G06F16/2219 G06F16/2471

    Abstract: According to some embodiments, a method for making input data available for processing by one or more processors comprises storing one or more parameters, wherein the one or more parameters comprise information identifying a location of the input data; and creating a datastore object using the one or more parameters, wherein the datastore object interfaces the input data and includes a read method for reading a chunk, the chunk being a subset of the input data, and having a size that does not exceed a memory size assigned to the one or more processors. According to some embodiments, the one or more parameters further comprise one or more of a type of the input data; a format of the input data; an offset for reading from the input data; a size of the chunk; a condition for determining the chunk; and a query for deriving the input data.

    Abstract translation: 根据一些实施例,用于使输入数据可用于一个或多个处理器进行处理的方法包括存储一个或多个参数,其中所述一个或多个参数包括标识输入数据的位置的信息; 以及使用所述一个或多个参数来创建数据存储对象,其中所述数据存储对象接口所述输入数据,并且包括用于读取块的读取方法,所述块是所述输入数据的子集,并且具有不超过存储器的大小 大小分配给一个或多个处理器。 根据一些实施例,一个或多个参数进一步包括输入数据的一种或多种; 输入数据的格式; 用于从输入数据读取的偏移量; 大块的大块; 确定块的条件; 以及用于导出输入数据的查询。

Patent Agency Ranking