Package org.apache.flink.runtime.io.network.partition.consumer

Class InputGate

java.lang.Object
org.apache.flink.runtime.io.network.partition.consumer.InputGate
All Implemented Interfaces:
AutoCloseable, AvailabilityProvider, ChannelStateHolder, PullingAsyncDataInput<BufferOrEvent>
Direct Known Subclasses:
IndexedInputGate, UnionInputGate
public abstract class InputGate extends Object implements PullingAsyncDataInput<BufferOrEvent>, AutoCloseable, ChannelStateHolder
An input gate consumes one or more partitions of a single produced intermediate result.

Each intermediate result is partitioned over its producing parallel subtasks; each of these partitions is furthermore partitioned into one or more subpartitions.

As an example, consider a map-reduce program, where the map operator produces data and the reduce operator consumes the produced data. 


 +-----+              +---------------------+              +--------+
 | Map | = produce => | Intermediate Result | <= consume = | Reduce |
 +-----+              +---------------------+              +--------+

When deploying such a program in parallel, the intermediate result will be partitioned over its producing parallel subtasks; each of these partitions is furthermore partitioned into one or more subpartitions. 


                            Intermediate result
               +-----------------------------------------+
               |                      +----------------+ |              +-----------------------+
 +-------+     | +-------------+  +=> | Subpartition 1 | | <=======+=== | Input Gate | Reduce 1 |
 | Map 1 | ==> | | Partition 1 | =|   +----------------+ |         |    +-----------------------+
 +-------+     | +-------------+  +=> | Subpartition 2 | | <==+    |
               |                      +----------------+ |    |    | Subpartition request
               |                                         |    |    |
               |                      +----------------+ |    |    |
 +-------+     | +-------------+  +=> | Subpartition 1 | | <==+====+
 | Map 2 | ==> | | Partition 2 | =|   +----------------+ |    |         +-----------------------+
 +-------+     | +-------------+  +=> | Subpartition 2 | | <==+======== | Input Gate | Reduce 2 |
               |                      +----------------+ |              +-----------------------+
               +-----------------------------------------+

In the above example, two map subtasks produce the intermediate result in parallel, resulting in two partitions (Partition 1 and 2). Each of these partitions is further partitioned into two subpartitions -- one for each parallel reduce subtask. As shown in the Figure, each reduce task will have an input gate attached to it. This will provide its input, which will consist of one subpartition from each partition of the intermediate result.