[
https://issues.apache.org/jira/browse/FLINK-1320?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14733540#comment-14733540
]
ASF GitHub Bot commented on FLINK-1320:
---------------------------------------
Github user StephanEwen commented on the pull request:
https://github.com/apache/flink/pull/1093#issuecomment-138269258
I think it looks larger than it is. Many small changes dues to changes
signatures of the MemoryManager and the MemorySegment instantiation.
Also, the vast majority of the code is benchmarks and tests.
Interesting to review is mainly:
- `MemorySegment`
- `HeapMemorySegment`
- `HybridMemorySegmentMemorySegment`
- The changes in the `TaskManager`
> Add an off-heap variant of the managed memory
> ---------------------------------------------
>
> Key: FLINK-1320
> URL: https://issues.apache.org/jira/browse/FLINK-1320
> Project: Flink
> Issue Type: Improvement
> Components: Local Runtime
> Reporter: Stephan Ewen
> Assignee: niraj rai
> Priority: Minor
>
> For (nearly) all memory that Flink accumulates (in the form of sort buffers,
> hash tables, caching), we use a special way of representing data serialized
> across a set of memory pages. The big work lies in the way the algorithms are
> implemented to operate on pages, rather than on objects.
> The core class for the memory is the {{MemorySegment}}, which has all methods
> to set and get primitives values efficiently. It is a somewhat simpler (and
> faster) variant of a HeapByteBuffer.
> As such, it should be straightforward to create a version where the memory
> segment is not backed by a heap byte[], but by memory allocated outside the
> JVM, in a similar way as the NIO DirectByteBuffers, or the Netty direct
> buffers do it.
> This may have multiple advantages:
> - We reduce the size of the JVM heap (garbage collected) and the number and
> size of long living alive objects. For large JVM sizes, this may improve
> performance quite a bit. Utilmately, we would in many cases reduce JVM size
> to 1/3 to 1/2 and keep the remaining memory outside the JVM.
> - We save copies when we move memory pages to disk (spilling) or through
> the network (shuffling / broadcasting / forward piping)
> The changes required to implement this are
> - Add a {{UnmanagedMemorySegment}} that only stores the memory adress as a
> long, and the segment size. It is initialized from a DirectByteBuffer.
> - Allow the MemoryManager to allocate these MemorySegments, instead of the
> current ones.
> - Make sure that the startup script pick up the mode and configure the heap
> size and the max direct memory properly.
> Since the MemorySegment is probably the most performance critical class in
> Flink, we must take care that we do this right. The following are critical
> considerations:
> - If we want both solutions (heap and off-heap) to exist side-by-side
> (configurable), we must make the base MemorySegment abstract and implement
> two versions (heap and off-heap).
> - To get the best performance, we need to make sure that only one class
> gets loaded (or at least ever used), to ensure optimal JIT de-virtualization
> and inlining.
> - We should carefully measure the performance of both variants. From
> previous micro benchmarks, I remember that individual byte accesses in
> DirectByteBuffers (off-heap) were slightly slower than on-heap, any larger
> accesses were equally good or slightly better.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
