Status

...

...

...

...

...

Please keep the discussion on the mailing list rather than commenting on the wiki (wiki discussions get unwieldy fast).

...

1. In order to share a result, a sink must be provided.
2. Complicated applications become inefficient due to a large amount of IO on the intermediate results.
3. User experience is weakened for users using programing programming API (SQL users are not victims here because the temporary tables are created by the framework)

...

To address the above issues, we propose to add support for interactive programming in Flink Table API.

Public Interfaces

Table API

1. Add the following two new methods to the Flink Table class.

  /**
    * Cache this table to builtin table service or the specified customized table service.
    *
    * This method provides a hint to Flink that the current table maybe reused later so a
    * cache should be created to avoid regenerating this table.
    *
    * The following code snippet gives an example of how this method could be used.
    *
    * {{{
    *   valTable t = tEnv.fromCollection(data).as('country, 'color, 'count)
    *
    *   valCachedTable t1 = t.filter('count < 100).cache()
    *   // t1 is cached after it is computed for the first time.
    *   t1.execute().print()
    *
    *   // When t1 is used again to compute t2, it may not be re-computed.
    *   valTable t2 = t1.groupBy('country).select('country, 'count.sum as 'sum)
    *   t2.execute().print()
    *
    *   // Similarly when t1 is used again to compute t3, it may not be re-computed.
    *   valTable t3 = t1.groupBy('color).select('color, 'count.avg as 'avg)
    *   t3.execute().print()
    *
    * }}}
    *
    * @note Flink optimizer may decide to not use the cache if doing that will accelerate the
    * processing, or if the cache is no longer available for reasons such as the cache has
    * been invalidated.
    * @note The table cache could be create lazily. That means the cache may be created at 
    * the first time when the cached table is computed.
    * @note The table cache will be cleared when the user program exits.
	* @note This method is only supported in batch table and it is treated as No-Op for stream table
    *
    * @return the current table with a cache hint. The original table reference is not modified
    *               by the execution of this method. If this method is called on a table with cache 
	*               hint, the same table object will return.
    */
  def CachedTable cache(): Table


  /**
    ;

2. Add a CachedTable interface extend Table

public interface CachedTable extends Table {
  /**
    * Manually invalidate the cache of this table to release the physical resources. Users are
    * not required to invoke this method to release physical resource unless they want to. The
    * table caches are cleared when user program exits.
    *
    * @note After invalidated, the cache may be re-created if this table is used again.
    */
  defvoid invalidateCache(): Unit;
}

32. Add a close method to the TableEnvironment

...

As mentioned in the motivation section. The key idea of the FLIP is to allow the intermediate process results to be cached, so later references to that result does do not result in require duplicate computation. To achieve that, we need to introduce Cached Tables.

The cached tables are tables whose contents are saved by Flink as the user application runs. A cached Table can be created in two waysthe following way:

Explicit caching

• Users can call cache() method on a table to explicitly tell Flink to cache a Table.
• The cache() method returns a new Table CachedTable object with a flag set.
• The cache() method does not execute eagerly. Instead, the table will be cached when the DAG that contains the cached table runs.

Semantic of cache() method

TableEnvironment tEnv = ...
Table t1 = ...
TableCachedTable t2 = t1.cache()
...
tEnvt2.execute().print() // t1 is cached.
Table t3 = t1.select(...) // cache will NOT be used.
Table t4 = t2.select(...) // cache will be used.
...
t2.invalidateCache() // The following two lines of code are equivalent
t1.invalidateCache() // cache will be released
t2.invalidateCache() // cache will cache will be released
...
t1.execute().print() // cache will NOT be recreated
t2.execute().print() // cache will be recreated

...

When TableEnvironment is closed, the resources consumed by the cached tables will also be released. This usually happens when user application exits.

...

Sometimes users may want to release the resource used by a cached table before the application exits. In this case, users can call invalidateCache() on a table. This will immediately release the resources used to cache that table.

Explicitly ignore the cached intermediate result

In some rare cases, users may want to explicitly ignore the cached intermediate result. In this case, users need to give an explicit hint, such as:

table.hint("ignoreCache")

Right now Flink does not have a hint mechanism yet. So before such a hint mechanism is available. Users are not able to explicitly ignore a cached intermediate result.

Cache a stream table

Theoretically speaking, users can also cache a streaming table. The semantic will be storing the result somewhere (potentially with a TTL). However, caching a streaming table is usually not that useful. For simplicity, we would not support stream table caching in the first implementation. When cache() is invoked on a stream table, it will be treated as a No-Op. This leaves us room to add caching for stream tables in the future without asking users to change their code.

Implementation Details

To let the feature available out of the box, a default file system based cache service will be provided, which utilizes the cluster partition implemented in FLIP-67. This section describes the implementation details of the default table service.

Although the implementation details are transparent to the users, there are some related changes to make the default implementation work.

Default Intermediate Result Storage (Phase 1)

Intermediate result reuse

The architecture is illustrated below:

Image Removed

Each cached table consists of two pieces of information:

• Table metadata - name, location, etc.
• Table contents - the actual contents of the table

The default table service stores the metadata in the client (e.g. TableEnvironment) and the actual contents are stored in the Task Managers as cluster partitions(FLIP-67).

The end to end process is the following:

Step 1: Execute JOB_1 (write cached tables)

1. Users call table.cache(), the client
   1. adds a Sink to the cached node in the DAG. The default IntermediateResultStorage creates a BlockingShuffleSink
   2. generate an IntermediateResultId
   3. passes the IntermediateResultId created all the way from RelNode down to the Operators in the JobVertex
   4. Set IntermediateDataSetId to IntermediateResultId
2. The JobGraphGenerator recognizes the BlockingShuffleSink, removes the Sink and sets the result partition type of the producer to BLOCKING_PERSISTENT
3. The client submits the job
4. JobMaster executes the job like usual. After the job finishes, the TaskExecutor promotes the BLOCKING_PERSISTENT result partitions to cluster partitions instead of releasing them (Implemented in FLIP-67)
5. After the job finishes, JobMaster reports the information of the cluster partition (ClusterPartitionDescriptor) back to the client in form of a mapping of [IntermediateDataSetId -> [ClusterPartitionDescriptor]]
   1. The ClusterPartitionDescriptor should include a ShuffleDescriptor and some metadata, i.e. numberOfSubpartitions and partitionType
   2. The ClusterPartitionDescriptor will be serialized before sending back to the client and only be deserialized in the JobGraphGenerator
   3. The table environment on client maintain the mapping of CachedTable -> (IntermediateResultId, [ClusterPartitionDescriptor])

Step 2: Execute JOB_2 (read cached tables)

Implementation Details

To let the feature available out of the box, a default file system based cache service will be provided, which utilizes the cluster partition implemented in FLIP-67. This section describes the implementation details of the default table service.

Although the implementation details are transparent to the users, there are some related changes to make the default implementation work.

Default Intermediate Result Storage (Phase 1)

Intermediate result reuse

The architecture is illustrated below:

Each cached table consists of two pieces of information:

• Table metadata - name, location, etc.
• Table contents - the actual contents of the table

The metadata of the cached table is stored in the client (e.g. CatalogManager) and the actual contents are stored in the Task Managers as cluster partitions(FLIP-67).

The end to end process is the following:

Image Added

Step 1: Execute JOB_1 (write cached tables)

1. Users call table.cache(), the client
   
   1. Wrap the operation of the table with CacheOperation. The CacheOpeartion contains a generated IntermediateResultId
   2. While translating the operations to rel nodes, the planner adds a CacheSink, which contains the IntermediateResultId, to the cached node in the DAG. By adding a sink to the cached node, we can make sure that the optimizer would not affect the cached node
   3. The CacheSink is treated as a normal sink when the planner optimizes and translates the rel nodes to transformation
2. When the Executor(StreamGraphGenerator) translates the transformation to stream graph, it recognizes the CacheSink, removes the CacheSink, and sets the cache flag of the upstream node.
3. If the StreamingJobGraphGenerator see the node with the cache flag set, it sets the result partition type to BLOCKING_PERSISTENT
4. The client submits the job
5. JobMaster executes the job as usual. After the job finishes, the TaskExecutor promotes the BLOCKING_PERSISTENT result partitions to cluster partitions instead of releasing them (Implemented in FLIP-67)
6. After the job finishes, JobMaster reports the information of the cluster partition (ClusterPartitionDescriptor) back to the client in form of a mapping of [IntermediateDataSetId -> [ClusterPartitionDescriptor]]
   1. The ClusterPartitionDescriptor should include a ShuffleDescriptor and some metadata, i.e. numberOfSubpartitions and partitionType
   2. The ClusterPartitionDescriptor will be serialized before sending back to the client via JobResult and only be deserialized in the StreamingJobGraphGenerator
   3. The CatalogManager in the table environment maintain the mapping of CachedTable -> (IntermediateResultId, [ClusterPartitionDescriptor])

Step 2: Execute JOB_2 (read cached tables)

1. Later on, when the client submits another job whose DAG contains a CacheOperation, the planner
   1. looks up the available intermediate results in the CatalogManager
      
   2. creates a Source node(CacheSource) that contains the ClusterPartitionDescriptor
   3. replace the subtree of the cached node with the source node created
   4. The CacheSource is treated as a normal source when the planner optimizes and translates the rel nodes to transformation
2. The StreamGraphGenerator recognizes the CacheSource, includes the ClusterPartitionDescriptor in the StreamNode, and sets the operator/driver to NoOp.
   
3. When the StreamingJobGraphGenerator sees the StreamNode that contains the ClusterPartitionDescriptor, it will include the ClusterPartitionDescriptor in the JobVertex.
   
   1. The parallelism is set to
4. Later on, when the client submits another job whose DAG contains a cached node, the client
   1. looks up the available intermediate results
   2. creates a Source node(BlockingShuffleSource) that contains the ClusterPartitionDescriptor
   3. replace the subtree of the cached node with the source node created
5. The JobGraphGenerator sees a BlockingShuffleSource node, sets its downstream node’s cluster partition input and sets the operator/driver to NoOp. It will then remove itself from the JobGraph
   1. The parallelism is set to the maximum number of subpartitions among the cluster partitions . It ensures to ensure that all the subpartitions are read by the NoOp vertex
6. The shipStrategyName field in the output edge of the NoOp vertex contains information about how the record should be partitionedThe clients submit the jobclients submit the job
7. JobMaster does the following if the JobVertex has cluster partition input set contains the ClusterPartitionDescriptor
   
   1. It assumes Scheduler understands the cluster partition location
   2. Create InputGateDeploymentDescriptor with the ShuffleMaster
   3. assign the result partitions to each subtask based on locality
8. Task managers will run the given tasks as usual

...

Invalidate intermediate results

1. Users invoke TableCachedTable.invalidateCache()
1. Clients remove the intermediate result entry in the TableEnvironment.
2. Clients delete the corresponding cluster partitions with the REST API provided in FLIP-67.
3. The cluster partitions will then be released by the Task Managers that hold the cluster partitions.

Please refer to FLIP-67 for the implementation detail of steps 2 and 3.

Repartition

Repartition is needed when the cache consumer requires the input data to be partitioned in a specific way, i.e. hash partition, custom partition. When the JobGraphGenerator generates the job graph, it introduces a NoOp job vertex as the upstream vertex of the cache consumer and maintains the shipStrategyName of the output job edge. During execution, the task executor will make sure that the data is repartitioned.

Failover

If a Task Manager instance fails, Flink will bring it up again. However, all the intermediate results which have a partition on the failed TM will become unavailable.

In this case, the consuming job will throw an exception and the job will fail. As a result, PartitionTracker in ResourceManager will release all the cluster partitions that are impacted(implemented in FLIP-67). The TableEnvironment will fell back and resubmit the original DAG without using the cache. The original DAG will run as an ordinary job that follows the existing recovery strategy. Note that because there is no cache available, the TableEnvironment (planner) will again create a Sink to cache the result that was initially cached, therefore the cache will be recreated after the execution of the original DAG.

The above process is transparent to the users.

Changes needed

In order to implement the default intermediate result storage, the following changes are needed.

Runtime

• New result partition type: BLOCKING_PERSISTENT
• A BLOCKING_PERSISTENT result partition will not be deleted when the job exits.
• JobMaster reports IntermediateDataSetID to ClusterPartitionDescriptor mapping to Client.

Client

• Add IntermediateDataSetID to StreamTransformation and Operator
• TableEnvironment stores the Table → (IntermediateResultId, [ClusterPartitionDescriptor]) mapping
• Client replaces the source of the cached node before optimization.
• Client adds a sink to the node that should be cached.

Impact to optimization

When users explicitly cache a table, the DAG is implicitly changed. This is because the optimizer may decide to change the cached node if it were not explicitly cached. As of now, when a node has more than one downstream node in the DAG, that node will be computed multiple times. This could be solved by introducing partial optimization for subgraphs, which is a feature available in Blink but not in Flink yet. This is an existing problem in Flink and this FLIP does not attempt to address that.

Future works

Make cache service pluggable

In some cases, users may want to plugin their own cache service. In the future, we could add support for that.

Some API changes will be needed to support customized cache service. We will start another FLIP to discuss that. The change should not be much. Curious readers can read the google doc for some idea.

Add auto cache

Auto cache allows the BLOCKING shuffle boundaries to be persisted for later usage. It further relieves the users from thinking about when to explicitly cache in the program.

Add cache to DataStream API

As of now DataStream only supports stream processing. There is some idea of supporting both Stream and Batch (as finite stream) in DataStream. Once we do that, we can add the cache API to DataStream as well.

Compatibility, Deprecation, and Migration Plan

This FLIP proposes a new feature in Flink. It is fully backwards compatible.

Test Plan

Unit tests and Integration Tests will be added to test the proposed functionalities.

Rejected Alternatives

The semantic of the cache() / invalidateCache() API has gone through extended discussions. The rejected alternative semantics are documented below:

Rejected API Option 1

API

// Do not return anything
void cache();
// Alternatively, return the original table for chaining purpose.
Table cache();
 
// Physically uncache the table to release resource
void uncache();
 
// To explicitly ignore cache, not part of this proposal but in the future
Table hint(“ingoreCache”)

...

ClusterPartitionDescriptor

The ClusterPartitionDescriptor should have the necessary information to let another job to be able to consume the intermediate result. It includes the ShuffleDescriptor, along with some metadata about the intermediate result, i.e., numberOfSubpartitions, partitionType, and the IntermediateDataSetID. Since it contains the runtime class ShuffleDescriptor, it should not put into the flink-core module. Instead, it will get serialized before transfer back to the client-side, and only get deserialized in the StreamingJobGraphGenerator. We can put a ClusterPartitionDescriptor interface in the flink-core, and keep the implementation of the ClusterPartitionDescriptor in the flink-runtime. The JobResult contains the SerializedValue<ClusterPartitionDescriptor> will get sent back to the client-side.

Repartition

Repartition is needed when the cache consumer requires the input data to be partitioned in a specific way, i.e. hash partition, custom partition. When the StreamingJobGraphGenerator generates the job graph, it introduces a NoOp job vertex as the upstream vertex of the cache consumer and maintains the shipStrategyName of the output job edge. During execution, the task executor will make sure that the data is repartitioned.

Failover

If a Task Manager instance fails, Flink will bring it up again. However, all the intermediate results which have a partition on the failed TM will become unavailable.

In this case, the consuming job will throw an exception and the job will fail. As a result, PartitionTracker in ResourceManager will release all the cluster partitions that are impacted(implemented in FLIP-67). The TableEnvironment will fell back and resubmit the original DAG without using the cache. The original DAG will run as an ordinary job that follows the existing recovery strategy. Note that because there is no cache available, the TableEnvironment (planner) will again create a Sink to cache the result that was initially cached, therefore the cache will be recreated after the execution of the original DAG.

The above process is transparent to the users.

Cache in Per-Job Mode

In the per-job mode cluster, a cluster will be spun up on every submitted job and tore down when the submitted job finished. All lingering resources (files, etc) are cleared up, including the cluster partition in the TMs. Therefore, the cached table will not work in the Per-Job mode cluster. When a job that read from some cached table is submitted in Per-Job mode, the first submission of the job will fail and the failover mechanism will re-execute the origin DAG.

Impact of optimization

To explain how the optimizer affects the cache node, let look at a very simple DAG, where one scan node followed by a filter node, as shown below. The optimizer can push the filter to the scan node such that the scan node will produce fewer data to the downstream node. However, such optimization will affect the result of the scan node, which is an undesired behavior if we want to cache the scan node.

Image Added

To solve the problem above, when users explicitly cache a table, we will change the DAG implicitly by adding a special sink node to the cache table, as shown below. By doing this, we are able to ensure that the result of the cache node will not be affected by the optimizer and we can identify the job vertex that produces the cache table in StreamingJobGraphGenerator by the special sink. With Blink planner, when a DAG has multiple sinks, the multi sink optimization will break the DAG into multiple RelNodeBlocks, the cache node will be the output node of one of those RelNodeBlocks. In our example, it will be broken into three RelNodeBlocks. Then, the optimizer will run independently on each of those RelNodeBlocks so that the optimizer will not affect the result of the cache node.

Image Added

Future works

SQL integration

The most intuitive way to use the cache table with SQL is to create a temporary view. We can introduce a new keyword CACHED and combine it with the CREATE TEMPORARY VIEW syntax. For example, the following SQL will register the CachedTable Object in the Catalog. And the later SQL statement can refer to the temporary view in order to use the cache table. Such syntax should align well with the caching in the Table API, as the following SQL has a similar effect of running tEnv.registerTemporaryView("CachedTable", table.cache()) in Table API.

CREATE CACHE TEMPORARY VIEW CachedTable AS SELECT *

Add cache to DataStream API

As of now DataStream only supports stream processing. There is some idea of supporting both Stream and Batch (as finite stream) in DataStream. Once we do that, we can add the cache API to DataStream as well.

Cache a stream table

Theoretically speaking, users can also cache a streaming table. The semantic will be storing the result somewhere (potentially with a TTL). However, caching a streaming table is usually not that useful. For simplicity, we would not support stream table caching in the first implementation. When cache() is invoked on a stream table, it will be treated as a No-Op. This leaves us room to add caching for stream tables in the future without asking users to change their code.

Cache Eviction

The cached table utilizes the cluster partition implemented in FLIP-67 to store the intermediate result in the TMs. Therefore, it is possible that the TM could run out of space to hold the intermediate result if clients cache too many tables without releasing. When it happens, the job will fail with an exception. For simplicity, we would not implement an automatic mechanism to handle such failure in the first implementation. For now, it is up to the user to decide what to do when the failure happens. In the future, we could introduce some kind of eviction policy to release some cluster partition when the failure happens and re-run the job.

Compatibility, Deprecation, and Migration Plan

This FLIP proposes a new feature in Flink. It is fully backward compatible.

Implementation Plan

Change needed

In order to implement the cache table, the following changes are needed.

Client

• Add IntermediateDataSetID to StreamTransformation and Operator
• CatalogManager stores the Table → (IntermediateResultId, [ClusterPartitionDescriptor]) mapping
• Planner replaces the source of the cached node before optimization
• Planner adds a sink to the node that should be cached
• StreamGraphGenerator modifies the stream graph and sets the flag of the cache node accordingly
  
• StreamingJobGraphGenerator sets the result partition type and ClusterPartitionDescriptor of the JobVertex.

Runtime

• JobMaster reports IntermediateDataSetID to ClusterPartitionDescriptor mapping to Client.
• JobMaster can generate InputGateDeploymentDescriptor base on the ClusterPartitionDescriptor in the JobVertex.

Plan

The implementation should proceed in the following way, some of which can proceed concurrently:

1. Implementation in Runtime
   1. The ClusterPartitionDescriptors can generated and put into the JobResult.
   2. By using the ClusterPartitionDescriptor in step 1.a, we can execute a Job that reads from the cluster partition.
2. Implementation in StreamGraphGenerator and StreamingJobGraphGenerator
   1. Given the CacheSouce and CacheSInk, the JobGraph generated by the StreamingJobGraphGenerator has the ClusterPartitionDescriptor or have the ResultPartitionType set correctly.
3. Implementation in Planner
   1. Given an Operation Tree with CacheOperation, it can replace the cache node with CacheSource accordingly or add a CacheSink to the cache node.
4. Implementation in TableEnvironment/Table
   1. Implement the public-facing classes.
   2. CatalogManager can store the ClusterPartitionDescriptor of the cached node.

Test Plan

Unit tests and Integration Tests will be added to test the proposed functionalities.

Rejected Alternatives

The semantic of the cache() / invalidateCache() API has gone through extended discussions. The rejected alternative semantics are documented below:

Rejected API Option 1

API

TableEnvironment tEnv = ...
Table t = …
...
// cache the table
t.// Do not return anything
void cache();
// Alternatively, return the original table for chaining purpose.
Table cache();
… 
// AssumePhysically someuncache executionthe physicallytable createdto therelease cache.
tEnv.executeresource
void uncache();
... 
// TheTo optimizerexplicitly decideignore whether the cache, willnot bepart used or not.
t.foo();
...
// Physically release the cache.
t.uncache();

Pros

• Simple and intuitive, users only need to deal one variable of Table class

Cons

...

of this proposal but in the future
Table hint(“ingoreCache”)

Semantic

...

...

TableEnvironment tEnv = ...
Table t

...

 = …

...

...
// cache the table

...

t.cache();

...

…
// 

...

Assume some execution physically created the cache.
tEnv.execute()
...
// The optimizer decide whether the cache will be used or not.
t.foo();
...
// Physically release the cache.
t.uncache();

Pros

• Simple and intuitive, users only need to deal one variable of Table class

Cons

• Side effect: a table may be cached / uncached in a method invocation, while the caller does not know about this.

Rejected API Option 2

...

• Code Block
  language java title

...

• Side Effect Option

...

• 1

  { Table t = … // cache the table t.cache();

...

...

...

...

...

• ...

...

...

...

• //

...

• The

...

• cache

...

• may

...

• be

...

• released

...

• in

...

• foo()

...

...

• foo(t);

...

Semantic

...

...

...

...

• ...

...

...

• // cache

...

• is no longer available t.

...

• bar()

...

• }

...

...

...

• void foo(Table t) { // cache the table t.cache(); …. // Physically

...

• drop the

...

• table t.uncache();

...

Pros

• No side effect

Cons

• Optimizer has no chance to kick in.

• Users have to distinguish between original table / cached table.

• Adding auto cache becomes a backward incompatible change.

  }

  
  

Rejected API Option

...

2

API

// Return a CacheHandle
CacheHandle cache();
 
public interface CacheHandle {
  // Physically release cache resource
  void release();
}

Semantic

TableEnvironment tEnv = ...
Table t = …
...
// cache the table
CacheHandle handle1 = t.cache();
CacheHandle handle2 = t.cache;
…
// Assume some execution physically created the cache.
tEnv.execute()
...
// Optimizer decide whether cache will be used.
t.foo();
...
// Release the first handle, cache will not be released because handle 2 has not been released
handle1.release();
// Release the second handle, the cache will be released because all the cache handle have been released.
handle2.release();

Pros

• No side effect

• Users only deal with the variable.

• Easy to add auto caching.

Cons

• The behavior of t.foo() changes after t.cache(), the concern is that this is considered as “modifies” table t, which is against the immutable principle.

...